diff --git a/doc/API/api.conf b/doc/API/api.conf
index f44efb9485e76827741769d89a7ebba626218363..3b307dd88a1c45879a1d6ef37f93f7f804c193b1 100644
--- a/doc/API/api.conf
+++ b/doc/API/api.conf
@@ -3,8 +3,10 @@
# modules
# The list of objects to document. Objects can be named using
# dotted names, module filenames, or package directory names.
-# Alases for this option include "objects" and "values".
-modules: ../../src/Modules, ../../src/*.py
+# Aliases for this option include "objects" and "values".
+#modules: ../../src/Modules, ../../src/*.py
+modules: ../../src/Modules, ../../src/*.py
+#modules: src/Modules/Db.py, src/Modules/File.py, src/Modules/Config.py
# output
# The type of output that should be generated. Should be one
@@ -27,7 +29,7 @@ docformat: epytext
# name
# The documented project's name.
-name: Mutalyzer 2.0
+name: "Mutalyzer 2.0"
# url
# The documented project's URL.
@@ -67,7 +69,7 @@ imports: no
# An integer indicating how verbose epydoc should be. The default
# value is 0; negative values will supress warnings and errors;
# positive values will give more verbose output.
-verbosity: 0
+verbosity: 1
# parse
# Whether or not parsing should be used to examine objects.
@@ -75,7 +77,7 @@ parse: yes
# introspect
# Whether or not introspection should be used to examine objects.
-introspect: no
+introspect: yes
# graph
# The list of graph types that should be automatically included
@@ -87,7 +89,7 @@ graph: all
# dotpath
# The path to the Graphviz "dot" executable, used to generate
# graphs.
-dotpath: /usr/local/bin/dot
+dotpath: /usr/bin/dot
# sourcecode
# Whether or not to include syntax highlighted source code in
@@ -97,9 +99,9 @@ dotpath: /usr/local/bin/dot
# pstat
# The name of one or more pstat files (generated by the profile
# or hotshot module). These are used to generate call graphs.
-pstat: profile.out
+#pstat: profile.out
# separate-classes
# Whether each class should be listed in its own section when
# generating LaTeX or PDF output.
-separate-classes: no
+separate-classes: yes
diff --git a/src/BatchChecker.py b/src/BatchChecker.py
index 626db21faa40f6e2d90bea950d08932fbf3e3264..6241b88c9506e8856522e5b1537cc48e02887ad7 100644
--- a/src/BatchChecker.py
+++ b/src/BatchChecker.py
@@ -1,4 +1,16 @@
#!/usr/bin/python
+
+"""
+@requires: os
+@requires: sys
+@requires: daemon
+@requires: signal
+@requires: fcntl
+@requires: ftplib
+@requires: Modules.Config
+@requires: Modules.Db.Batch
+@requires: Modules.Scheduler
+"""
import os
import sys
import daemon
@@ -10,7 +22,9 @@ from Modules.Db import Batch
from Modules import Scheduler
def sigusr1_daemon_notified(*args):
- """Stop the Daemon with SIGUSR1 signal: kill -10 PID"""
+ """
+ Stop the Daemon with SIGUSR1 signal: kill -10 PID
+ """
sys.exit()
# Change dir
diff --git a/src/Modules/Config.py b/src/Modules/Config.py
index 9eb1401e3a81bad03b867a88ed5e7d440a8b3e91..94b9c66f2c702e2a7a58e73707965569547257fa 100644
--- a/src/Modules/Config.py
+++ b/src/Modules/Config.py
@@ -1,43 +1,40 @@
#!/usr/bin/python
"""
- Module for reading the config file and splitting up the variables into
- subclasses. Each of these subclasses are used to configure a specific
- module.
-
- Public classes:
- Config ; Read the configuration file and store the data in subclasses.
+Module for reading the config file and splitting up the variables into
+subclasses. Each of these subclasses are used to configure a specific
+module.
"""
class Config() :
"""
- Read the configuration file and store the data in subclasses.
-
- Public subclasses:
- Retriever ; Container for the Retriever configuration variables.
- Db ; Container for the Db configuration variables.
- Output ; Container for the Output configuration variables.
- Mutator ; Container for the Mutator configuration variables.
- Scheduler ; Container for the Scheduler configuration variables.
- File ; Container for the File configuration variables.
- GBparser ; Container for the File configuration variables.
-
- Special Methods:
- __init__ ; Read the configuration file and initialise the
- subclasses.
+ Read the configuration file and store the data in subclasses.
+
+ Special Methods:
+ - __init__ ; Read the configuration file and initialise the
+ subclasses.
"""
+ # Public subclasses:
+ # - Retriever ; Container for the Retriever configuration variables.
+ # - Db ; Container for the Db configuration variables.
+ # - Output ; Container for the Output configuration variables.
+ # - Mutator ; Container for the Mutator configuration variables.
+ # - Scheduler ; Container for the Scheduler configuration variables.
+ # - File ; Container for the File configuration variables.
+ # - GBparser ; Container for the File configuration variables.
+
class Retriever() :
"""
- Container class for the Retriever configuration variables.
+ Container class for the Retriever configuration variables.
- Public variables:
- email ; Email address used for Entrez.
- cache ; Location of the cache directory.
- cachesize ; Maximum size of the cache directory in bytes.
- maxDldSize ; Maximum size of a GenBank record in bytes.
- minDldSize ; Minimum size of a GenBank record in bytes.
- lrgURL ; base URL of LRG files
+ Public variables:
+ - email ; Email address used for Entrez.
+ - cache ; Location of the cache directory.
+ - cachesize ; Maximum size of the cache directory in bytes.
+ - maxDldSize ; Maximum size of a GenBank record in bytes.
+ - minDldSize ; Minimum size of a GenBank record in bytes.
+ - lrgURL ; base URL of LRG files.
"""
pass
@@ -45,31 +42,31 @@ class Config() :
class Db() :
"""
- Container class for the Db configuration variables.
+ Container class for the Db configuration variables.
- Public variables:
- internalDb ; Name of the internal database.
- dbNames ; Name of the mapping databases
- LocalMySQLuser ; Username for the local databases.
- LocalMySQLhost ; Hostname of the local databases.
+ Public variables:
+ - internalDb ; Name of the internal database.
+ - dbNames ; Name of the mapping databases
+ - LocalMySQLuser ; Username for the local databases.
+ - LocalMySQLhost ; Hostname of the local databases.
- RemoteMySQLuser ; Username for the remote UCSC database.
- RemoteMySQLhost ; Hostname of the UCSC database server.
- UpdateInterval ; Time window (in days) to search for
- updates.
- TempFile ; Location for downloaded updates.
+ - RemoteMySQLuser ; Username for the remote UCSC database.
+ - RemoteMySQLhost ; Hostname of the UCSC database server.
+ - UpdateInterval ; Time window (in days) to search for
+ updates.
+ - TempFile ; Location for downloaded updates.
"""
#Db
class Output() :
"""
- Container class for the Output configuration variables.
+ Container class for the Output configuration variables.
- Public variables:
- log ; Name and location of the logfile.
- datestring ; Prefix for log messages.
- loglevel ; Default level for logging.
- outputlevel ; Default level for output.
+ Public variables:
+ - log ; Name and location of the logfile.
+ - datestring ; Prefix for log messages.
+ - loglevel ; Default level for logging.
+ - outputlevel ; Default level for output.
"""
pass
@@ -77,14 +74,14 @@ class Config() :
class Mutator() :
"""
- Container class for the Mutator configuration variables.
+ Container class for the Mutator configuration variables.
- Public variables:
- flanksize ; Length of the flanking sequences in the
- visualisation.
- maxvissize ; Maximum length of the variation in the
- visualisation.
- flankclipsize ; Length of the inserted/deleted flanks.
+ Public variables:
+ - flanksize ; Length of the flanking sequences in the
+ visualisation.
+ - maxvissize ; Maximum length of the variation in the
+ visualisation.
+ - flankclipsize ; Length of the inserted/deleted flanks.
"""
pass
@@ -92,14 +89,14 @@ class Config() :
class Scheduler() :
"""
- Container class for the Scheduler configuration variables.
+ Container class for the Scheduler configuration variables.
- Public variables:
- processName ; Name of the scheduler in the process list.
- mailFrom ; Return e-mail address.
- mailMessage ; Template e-mail.
- mailSubject ; Subject of the e-mail.
- resultsDir ; Location of the results.
+ Public variables:
+ - processName ; Name of the scheduler in the process list.
+ - mailFrom ; Return e-mail address.
+ - mailMessage ; Template e-mail.
+ - mailSubject ; Subject of the e-mail.
+ - resultsDir ; Location of the results.
"""
pass
@@ -107,10 +104,10 @@ class Config() :
class Batch() :
"""
- Container class for the Scheduler configuration variables.
+ Container class for the Scheduler configuration variables.
- Public variables:
- PIDfile ; Location of the PID file
+ Public variables:
+ - PIDfile ; Location of the PID file.
"""
pass
@@ -118,15 +115,15 @@ class Config() :
class File() :
"""
- Container class for the File configuration variables.
+ Container class for the File configuration variables.
- Public variables:
- bufSize ; Amount of bytes to be read for determining the file
+ Public variables:
+ - bufSize ; Amount of bytes to be read for determining the file
type.
- header ; The obligatory header in batch request files.
- tempDir ; Directory for temporary files.
- threshold ; The threshold under which the percentage of errors
- is allowed in a batchfile
+ - header ; The obligatory header in batch request files.
+ - tempDir ; Directory for temporary files.
+ - threshold ; The threshold under which the percentage of errors
+ is allowed in a batchfile.
"""
pass
@@ -134,34 +131,36 @@ class Config() :
class GBparser() :
"""
- Container class for the GBparser configuration variables.
+ Container class for the GBparser configuration variables.
- Public variables:
- upstream ; Number of upstream nucleotides when searching for a
- transcript.
- downstream ; Number of downstream nucleotides when searching for a
- transcript.
+ Public variables:
+ - upstream ; Number of upstream nucleotides when searching for a
+ transcript.
+ - downstream ; Number of downstream nucleotides when searching for a
+ transcript.
"""
pass
- #File
+ #GBparser
class GenRecord() :
pass
def __init__(self) :
"""
- Initialise the class with variables read from the configuration
- file. In principle, this is the only place in the code where a
- hard coded constant is used (the name and path to the configuration
- file).
-
- Public subclasses (altered):
- Retriever ; Initialised with Retriever configuration variables.
- Db ; Initialised with Db configuration variables.
- Output ; Initialised with Output configuration variables.
- Mutator ; Initialised with Mutator configuration variables.
- Scheduler ; Initialised with Scheduler configuration variables.
+ Initialise the class with variables read from the configuration
+ file. In principle, this is the only place in the code where a
+ hard coded constant is used (the name and path to the configuration
+ file).
+
+ Public subclasses (altered):
+ - Retriever ; Initialised with Retriever configuration variables.
+ - Db ; Initialised with Db configuration variables.
+ - Output ; Initialised with Output configuration variables.
+ - Mutator ; Initialised with Mutator configuration variables.
+ - Scheduler ; Initialised with Scheduler configuration variables.
+
+ @requires: ConfigObj
"""
from configobj import ConfigObj # ConfigObj()
diff --git a/src/Modules/Crossmap.py b/src/Modules/Crossmap.py
index 24a0a89362e773e1674491a6da334f59343a8ec4..08c5747a43c41af32bc6662f814e7523f1c51b92 100644
--- a/src/Modules/Crossmap.py
+++ b/src/Modules/Crossmap.py
@@ -1,74 +1,86 @@
#!/usr/bin/python
"""
- Module for conversion from genomic coordinates to coding sequence
- orientated coordinates and vice versa.
- The conversions are done based upon a list of splice sites, the CDS start
- and stop and the orientation of a transcript.
+Module for conversion from genomic coordinates to coding sequence
+orientated coordinates and vice versa.
+The conversions are done based upon a list of splice sites, the CDS start
+and stop and the orientation of a transcript.
- Public classes:
- Crossmap ; Convert from g. to c. or n. notation or vice versa.
"""
+#Public classes:
+# - Crossmap ; Convert from g. to c. or n. notation or vice versa.
class Crossmap() :
"""
- Convert from g. to c. or n. notation or vice versa.
-
- Private variables:
- __STOP ; CDS stop in c. notation.
- __crossmapping ; A list that contains either c. or n. positions
- corresponding to the g. positions in the RNA list.
-
- Public variables:
- RNA ; The list of RNA splice sites.
- CDS ; CDS start and stop (if present).
- orientation ; The orientation of the transcript: 1 = forward
- -1 = reverse.
-
- Special methods:
- __init__(RNA, CDS, orientation) ; Initialise the class and do the
- cross mapping of the splice
- sites.
-
- Private methods:
- __plus(a, b) ; A protected '+' that skips 0 if
- a <= 0 and a + b >= 0.
- __minus(a, b) ; A protected '-' that skips 0 if
- a >= 0 and a - b <= 0.
- __minusr(a, b) ; A protected '-' that skips 0 if
- a > 0 and b < 0.
- __crossmap_splice_sites() ; Calculate the __crossmapping list.
-
- Public methods:
- int2main(a) ; Translate from __STOP to '*' notation.
- main2int(s) ; Translate from '*' to __STOP notation.
- g2x(a) ; Translate from g. notation to c. or n. notation.
- x2g(a, b) ; Translate c. or n. notation to g. notation.
+ Convert from I{g.} to I{c.} or I{n.} notation or vice versa.
+
+ Private variables:
+ - __STOP ; CDS stop in I{c.} notation.
+ - __crossmapping ; A list that contains either I{c.} or I{n.} positions
+ corresponding to the I{g.} positions in the RNA list.
+
+ Public variables:
+ - RNA ; The list of RNA splice sites.
+ - CDS ; CDS start and stop (if present).
+ - orientation ; The orientation of the transcript: 1 = forward
+ -1 = reverse.
+
+ Special methods:
+ - __init__(RNA, CDS, orientation) ; Initialise the class and do the
+ cross mapping of the splice sites.
+
+ Private methods:
+ - __plus(a, b) ; A protected '+' that skips 0 if
+ a <= 0 and a + b >= 0.
+ - __minus(a, b) ; A protected '-' that skips 0 if
+ a >= 0 and a - b <= 0.
+ - __minusr(a, b) ; A protected '-' that skips 0 if
+ a > 0 and b < 0.
+ - __crossmap_splice_sites() ; Calculate the __crossmapping list.
+
+ Public methods:
+ - int2main(a) ; Translate from __STOP to '*' notation.
+ - main2int(s) ; Translate from '*' to __STOP notation.
+ - g2x(a) ; Translate from I{g.} notation to I{c.} or I{n.} notation.
+ - x2g(a, b) ; Translate I{c.} or I{n.} notation to I{g.} notation.
+ - int2offset(t) ; Convert a tuple of integers to offset-notation.
+ - offset2int(s) ; Convert an offset in HGVS notation to an integer.
+ - tuple2string(t) ; Convert a tuple (main, offset) in __STOP notation
+ to I{c.} notation.
+ - g2c(a) ; Uses both g2x() and tuple2string() to translate a genomic
+ position to __STOP notation to I{c.} notation.
+ - info() ; Return transcription start, transcription end and CDS stop.
+ - getSpliceSite(number) ; Return the coordinate of a splice site.
+ - numberOfIntrons() ; Returns the number of introns.
+ - numberOfExons() ; Returns the number of exons.
"""
def __init__(self, RNA, CDS, orientation) :
"""
- Initialise the class and do the cross mapping of the splice sites.
-
- Arguments:
- RNA ; The list of RNA splice sites.
- CDS ; CDS start and stop (may be empty).
- orientation ; The orientation of the transcript.
-
- Private variables (altered):
- __STOP ; CDS stop in c. notation.
- __crossmapping ; A list that contains either c. or n. positions
- corresponding to the g. positions in the RNA
- list.
- __trans_start ; Transcription start site in c. notation.
- __trans_end ; Transcription end side in c. notation.
-
- Public variables (altered):
- RNA ; The list of RNA splice sites.
- CDS ; CDS start and stop (if present).
- orientation ; The orientation of the transcript: 1 = forward
- -1 = reverse.
- """
+ Initialise the class and do the cross mapping of the splice sites.
+
+ Private variables (altered):
+ - __STOP ; CDS stop in I{c.} notation.
+ - __crossmapping ; A list that contains either I{c.} or I{n.}
+ positions corresponding to the I{g.} positions in
+ the RNA list.
+ - __trans_start ; Transcription start site in I{c.} notation.
+ - __trans_end ; Transcription end side in I{c.} notation.
+
+ @arg RNA: The list of RNA splice sites
+ @type RNA: list
+ @arg CDS: CDS start and stop (if present, may be empty)
+ @type CDS: list
+ @arg orientation: The orientation of the transcript
+ - 1 = forward
+ - E{-}1 = reverse
+ @type orientation: integer
+ """
+# Public variables (altered):
+# - RNA ; The list of RNA splice sites.
+# - CDS ; CDS start and stop (if present).
+# - orientation ; The orientation of the transcript: 1 = forward
+# -1 = reverse.
self.__STOP = None
self.__crossmapping = len(RNA) * [None]
@@ -88,16 +100,17 @@ class Crossmap() :
def __plus(self, a, b) :
"""
- This method returns a + b unless a is smaller than zero and the
- result is larger than zero, in that case it returns a + b + 1.
- In effect the number 0 is skipped while adding.
+ This method returns a + b unless a is smaller than zero and the
+ result is larger than zero, in that case it returns a + b + 1.
+ In effect the number 0 is skipped while adding.
- Arguments:
- a ; First argument of the addition.
- b ; Second argument of the addition.
+ @arg a: First argument of the addition
+ @type a: integer
+ @arg b: Second argument of the addition
+ @type b: integer
- Returns:
- integer ; a + b or a + b + 1.
+ @return: a + b or a + b + 1
+ @rtype: integer
"""
r = a + b
@@ -110,16 +123,17 @@ class Crossmap() :
def __minus(self, a, b) :
"""
- This method returns a - b unless a is larger than zero and the
- result is smaller than zero, in that case it returns (a - b) - 1.
- In effect the number 0 is skipped while subtracting.
+ This method returns a - b unless a is larger than zero and the
+ result is smaller than zero, in that case it returns (a - b) - 1.
+ In effect the number 0 is skipped while subtracting.
- Arguments:
- a ; First argument of the subtraction.
- b ; Second argument of the subtraction.
+ @arg a: First argument of the subtraction
+ @type a: integer
+ @arg b: Second argument of the subtraction
+ @type b: integer
- Returns:
- integer ; a - b or (a - b) - 1.
+ @return: a - b or (a - b) - 1
+ @rtype: integer
"""
r = a - b
@@ -132,16 +146,17 @@ class Crossmap() :
def __minusr(self, a, b) :
"""
- This method returns a - b unless a is larger than zero and b is
- smaller than zero, in that case it returns (a - b) - 1.
- In effect the number 0 is skipped while subtracting.
+ This method returns a - b unless a is larger than zero and b is
+ smaller than zero, in that case it returns (a - b) - 1.
+ In effect the number 0 is skipped while subtracting.
- Arguments:
- a ; First argument of the subtraction.
- b ; Second argument of the subtraction.
+ @arg a: First argument of the subtraction
+ @type a: integer
+ @arg b: Second argument of the subtraction
+ @type b: integer
- Returns:
- integer ; a - b or (a - b) - 1.
+ @return: a - b or (a - b) - 1
+ @rtype: integer
"""
r = a - b
@@ -154,46 +169,50 @@ class Crossmap() :
def __crossmap_splice_sites(self) :
"""
- This method calculates either:
- 1: The c. notation of the CDS start and stop, including splice
- sites.
- 2: The c. notation of the RNA splice sites.
- 3: The n. notation of the RNA splice sites.
-
- For option 1 only provide an list with CDS splice sites.
- For option 2 provide an list with RNA splice sites and one with
- the CDS start and stop.
- For option 3 only provide an list with RNA splice sites.
-
- Examples:
- - Get the n. notation of the RNA splice sites. The input is in
+ This method calculates either:
+ 1. The I{c.} notation of the CDS start and stop, including splice
+ sites.
+ 2. The I{c.} notation of the RNA splice sites.
+ 3. The I{n.} notation of the RNA splice sites.
+
+ For option 1 only provide an list with CDS splice sites.
+ For option 2 provide an list with RNA splice sites and one with
+ the CDS start and stop.
+ For option 3 only provide an list with RNA splice sites.
+
+ Examples:
+
+ Crossmap(RNA, [], 1)
+ - Get the I{n.} notation of the RNA splice sites. The input is in
forward notation.
- Crossmap(RNA, [], 1)
- - Get the c. notation of the CDS start and stop, and the internal
+
+ Crossmap(CDS, [], 1)
+ - Get the I{c.} notation of the CDS start and stop, and the internal
splice sites. The input is in forward notation.
- Crossmap(CDS, [], 1)
- - Get the c. notation of the RNA splice sites. The input is in
+
+ Crossmap(RNA, CDS, -1)
+ - Get the I{c.} notation of the RNA splice sites. The input is in
reverse complement.
- Crossmap(RNA, CDS, -1)
+
- The output is straightforward, except for the c. notation of the
- downstream RNA splice sites. This is denoted by __STOP + the
- distance to the stop codon, as an alternative to the *-notation.
+ The output is straightforward, except for the I{c.} notation of the
+ downstream RNA splice sites. This is denoted by __STOP + the
+ distance to the stop codon, as an alternative to the *-notation.
- Private variables (altered):
- __crossmapping ; A list that contains either c. or n. positions
- corresponding to the g. positions in the RNA
- list.
+ Private variables (altered):
+ - __crossmapping ; A list that contains either I{c.} or I{n.} positions
+ corresponding to the I{g.} positions in the RNA
+ list.
- Private variables:
- __STOP ; A large number to indicate positions after CDS
- stop.
+ Private variables:
+ - __STOP ; A large number to indicate positions after CDS
+ stop.
- Public variables:
- RNA ; The list of RNA splice sites.
- CDS ; CDS start and stop (if present).
- orientation ; The orientation of the transcript: 1 = forward
- -1 = reverse.
+ Public variables:
+ - RNA ; The list of RNA splice sites.
+ - CDS ; CDS start and stop (if present).
+ - orientation ; The orientation of the transcript: 1 = forward,
+ -1 = reverse.
"""
RNAlen = len(self.RNA)
@@ -237,47 +256,49 @@ class Crossmap() :
def g2x(self, a) :
"""
- This function calculates either:
- 1: The n. notation from a g. notation.
- 2: The c. notation from a g. notation.
-
- For option 1 only provide an array with mRNA splice sites and one
- with the c. notation of the splice sites.
- For option 2 provide an array with mRNA splice sites, one with the
- c. notation of the splice sites and an array with the CDS start and
- stop.
-
- Examples:
- - Get the n. notation of a g. position i. The input is in forward
+ This function calculates either:
+ 1. The I{n.} notation from a I{g.} notation.
+ 2. The I{c.} notation from a I{g.} notation.
+
+ For option 1 only provide an array with mRNA splice sites and one
+ with the I{c.} notation of the splice sites.
+ For option 2 provide an array with mRNA splice sites, one with the
+ I{c.} notation of the splice sites and an array with the CDS start and
+ stop.
+
+ Examples:
+
+ Crossmap(RNA, [], 1)
+ g2x(i)
+ - Get the I{n.} notation of a I{g.} position i. The input is in forward
+ notation.
+
+ Crossmap(mRNA, CDS, -1);
+ g2x(i);
+ - Get the I{c.} notation of a I{g.} position i. The input is in reverse
notation.
- Crossmap(RNA, [], 1)
- g2x(i)
- - Get the c. notation of a g. position i. The input is in reverse
- notation.
- Crossmap(mRNA, CDS, -1);
- g2x(i);
- The output is fully compatible with the HVGS nomenclature as
- defined on 01-07-2009.
+ The output is fully compatible with the HVGS nomenclature as defined
+ on 01-07-2009.
- Arguments:
- a ; The genomic position that must be translated.
+ Private variables:
+ - __crossmapping ; A list that contains either I{c.} or I{n.} positions
+ corresponding to the I{g.} positions in the RNA
+ list.
+ - __STOP ; A large number to indicate positions after CDS
+ stop.
- Private variables:
- __crossmapping ; A list that contains either c. or n. positions
- corresponding to the g. positions in the RNA
- list.
- __STOP ; A large number to indicate positions after CDS
- stop.
+ Public variables:
+ - RNA ; The list of RNA splice sites.
+ - CDS ; CDS start and stop (if present).
+ - orientation ; The orientation of the transcript: 1 = forward,
+ -1 = reverse.
- Public variables:
- RNA ; The list of RNA splice sites.
- CDS ; CDS start and stop (if present).
- orientation ; The orientation of the transcript: 1 = forward
- -1 = reverse.
+ @arg a: The genomic position that must be translated
+ @type a: integer
- Returns:
- string ; The c. or n. notation of position a.
+ @return: The I{c.} or I{n.} notation of position a
+ @rtype: string
"""
# TODO update documentation.
@@ -313,39 +334,42 @@ class Crossmap() :
def x2g(self, a, b) :
"""
- This function calculates either:
- 1: The g. notation from a n. notation.
- 2: The g. notation from a c. notation.
+ This function calculates either:
+ 1. The I{g.} notation from a I{n.} notation.
+ 2. The I{g.} notation from a I{c.} notation.
- Whether option 1 or 2 applies depends on the content of mRNAm.
+ Whether option 1 or 2 applies depends on the content of mRNAm.
- Examples:
- - Get the g. notation of a n. position i. The input is in forward
- notation.
- Crossmap(RNA, [], 1)
- x2g(i)
- - Get the g. notation of a c. position i with offset j. The input
- is in reverse notation.
- Crossmap(mRNA, CDS, -1);
- x2g(i, j);
+ Examples:
- Arguments:
- a ; The n. or c. position to be translated.
- b ; The offset of position a.
+ Crossmap(RNA, [], 1)
+ x2g(i)
+ - Get the I{g.} notation of a I{n.} position i. The input is in forward
+ notation.
- Private variables:
- __crossmapping ; A list that contains either c. or n. positions
- corresponding to the g. positions in the RNA
- list.
+ Crossmap(mRNA, CDS, -1);
+ x2g(i, j);
+ - Get the I{g.} notation of a I{c.} position i with offset j. The input
+ is in reverse notation.
- Public variables:
- RNA ; The list of RNA splice sites.
- orientation ; The orientation of the transcript: 1 = forward
- -1 = reverse.
+ Private variables:
+ - __crossmapping ; A list that contains either I{c.} or I{n.} positions
+ corresponding to the I{g.} positions in the RNA
+ list.
+
+ Public variables:
+ - RNA ; The list of RNA splice sites.
+ - orientation ; The orientation of the transcript: 1 = forward
+ -1 = reverse.
- Returns:
- integer ; A g. position.
+ @arg a: The I{n.} or I{c.} position to be translated
+ @type a: integer
+ @arg b: The offset of position a
+ @type b: integer
+
+ @return: A I{g.} position
+ @rtype: integer
"""
d = self.orientation
@@ -373,16 +397,16 @@ class Crossmap() :
def int2main(self, a) :
"""
- This method converts the __STOP notation to the '*' notation.
+ This method converts the __STOP notation to the '*' notation.
- Arguments:
- a ; An integer in __STOP notation.
+ Private variables:
+ - __STOP ; CDS stop in I{c.} notation.
- Private variables:
- __STOP ; CDS stop in c. notation.
+ @arg a: An integer in __STOP notation
+ @type a: integer
- Returns:
- string ; The converted notation (may be unaltered).
+ @return: The converted notation (may be unaltered)
+ @rtype: string
"""
if a > self.__STOP :
@@ -393,16 +417,16 @@ class Crossmap() :
def main2int(self, s) :
"""
- This method converts the '*' notation to the __STOP notation.
+ This method converts the '*' notation to the __STOP notation.
- Arguments:
- s ; A string in '*' notation.
+ Private variables:
+ - __STOP ; CDS stop in I{c.} notation.
- Private variables:
- __STOP ; CDS stop in c. notation.
+ @arg s: A string in '*' notation
+ @type s: string
- Returns:
- integer ; The converted notation (may be unaltered).
+ @return: The converted notation (may be unaltered)
+ @rtype: integer
"""
if s[0] == '*' :
@@ -413,15 +437,15 @@ class Crossmap() :
def int2offset(self, t) :
"""
- Convert a tuple of integers to offset-notation. This adds a `+',
- and `u' or `d' to the offset when appropriate. The main value is
- not returned.
+ Convert a tuple of integers to offset-notation. This adds a `+',
+ and `u' or `d' to the offset when appropriate. The main value is
+ not returned.
- Arguments:
- t ; A tuple of integers: (main, offset) in __STOP notation.
+ @arg t: A tuple of integers: (main, offset) in __STOP notation
+ @type t: tuple
- Returns:
- string ; The offset in HGVS notation.
+ @return: The offset in HGVS notation
+ @rtype: string
"""
if t[1] > 0 : # The exon boundary is downstream.
@@ -439,15 +463,15 @@ class Crossmap() :
def offset2int(self, s) :
"""
- Convert an offset in HGVS notation to an integer. This removes
- `+', `u' and `d' when present. It also converts a `?' to something
- sensible.
+ Convert an offset in HGVS notation to an integer. This removes
+ `+', `u' and `d' when present. It also converts a `?' to something
+ sensible.
- Arguments:
- s ; An offset in HGVS notation.
+ @arg s: An offset in HGVS notation
+ @type s: string
- Returns:
- int ; The offset as an integer.
+ @return: The offset as an integer
+ @rtype: integer
"""
if not s : # No offset given.
@@ -468,36 +492,52 @@ class Crossmap() :
def tuple2string(self, t) :
"""
- Convert a tuple (main, offset) in __STOP notation to c. notation.
+ Convert a tuple (main, offset) in __STOP notation to I{c.} notation.
- Arguments:
- t ; A tuple (main, offset) in __STOP notation.
+ @arg t: A tuple (main, offset) in __STOP notation
+ @type t: tuple
- Returns:
- string ; The position in HGVS notation.
+ @return: The position in HGVS notation
+ @rtype: string
"""
return str(self.int2main(t[0])) + str(self.int2offset(t))
#tuple2string
def g2c(self, a) :
+ """
+ Uses both g2x() and tuple2string() to translate a genomic position
+ to __STOP notation to I{c.} notation.
+
+ @arg a: The genomic position that must be translated
+ @type a: integer
+
+ @return: The position in HGVS notation
+ @rtype: string
+ """
return self.tuple2string(self.g2x(a))
#g2c
def info(self) :
"""
- Return transcription start, transcription end and CDS stop.
+ Return transcription start, transcription end and CDS stop.
- Returns:
- triple ; (trans_start, trans_stop, CDS_stop)
+ @return: (trans_start, trans_stop, CDS_stop)
+ @rtype: triple
"""
return (self.__trans_start, self.__trans_end, self.__STOP)
#info
def getSpliceSite(self, number) :
- #TODO documentation
"""
+ Return the coordinate of a splice site.
+
+ @arg number: the number of the RNA splice site counting from
+ transcription start.
+ @type number: integer
+ @return: coordinate of the RNA splice site.
+ @rtype: integer
"""
if self.orientation == 1 :
@@ -506,15 +546,21 @@ class Crossmap() :
#getSpliceSite
def numberOfIntrons(self) :
- #TODO documentation
"""
+ Returns the number of introns.
+
+ @return: number of introns
+ @rtype: integer
"""
return len(self.RNA) / 2 - 1
def numberOfExons(self) :
- #TODO documentation
"""
+ Returns the number of exons.
+
+ @return: number of exons
+ @rtype: integer
"""
return len(self.RNA) / 2
diff --git a/src/Modules/Db.py b/src/Modules/Db.py
index 4e40c521b43c4bf5e29160dfbcd1ce50357d3c40..375de4e8a945b8944f7a9442a792673284e75a5f 100644
--- a/src/Modules/Db.py
+++ b/src/Modules/Db.py
@@ -1,21 +1,27 @@
#!/usr/bin/python
"""
- Module for database access.
- The Db class is a superclass of the rest of the classes and should not be
- used as such. The superclass mainly consists of a wrapper for SQL
- statements.
-
-
- Public classes:
- Db ; Log in to a database and keep it open for queries.
- Mapping ; Mapping of transcripts and genes.
- Remote ; Retrieving updates for the mapping databases.
- Update ; Updating the mapping databases.
- Cache ; Cache administration.
- Batch ; Batch checker.
+Module for database access.
+The Db class is a superclass of the rest of the classes and should not be
+used as such. The superclass mainly consists of a wrapper for SQL
+statements.
+
+@requires: MySQLdb
+@requires: types
+@requires: time
+@requires: os
+@requires: Modules.Misc
"""
+#Public classes:
+# - Db ; Log in to a database and keep it open for queries.
+# - Mapping ; Mapping of transcripts and genes.
+# - Remote ; Retrieving updates for the mapping databases.
+# - Update ; Updating the mapping databases.
+# - Cache ; Cache administration.
+# - Batch ; Batch checker.
+
+
import MySQLdb # connect(), escape_string()
import types # TupleType
import time # strftime()
@@ -32,29 +38,31 @@ from Modules import Misc # ID()
class Db() :
"""
- Log in to a database and keep it open for queries.
+ Log in to a database and keep it open for queries.
- Private variables:
- __db ; Interface to the database.
+ Private variables:
+ - __db ; Interface to the database.
- Special methods:
- __init__(dbName, mySqlUser, mySqlHost) ; Do the login.
+ Special methods:
+ - __init__(dbName, mySqlUser, mySqlHost) ; Do the login.
- Public methods:
- query(statement) ; General query function.
+ Public methods:
+ - query(statement) ; General query function.
"""
def __init__(self, dbName, mySqlUser, mySqlHost) :
"""
- Log in to the database.
+ Log in to the database.
- Arguments:
- dbName ; The name of the database to use.
- mySqlUser ; User name for the database.
- mySqlHost ; Host name for the database.
+ Private variables (altered):
+ - __db ; The interface to the database.
- Private variables (altered):
- __db ; The interface to the database.
+ @arg dbName: The name of the database to use
+ @type dbName: string
+ @arg mySqlUser: User name for the database
+ @type mySqlUser: string
+ @arg mySqlHost: Host name for the database
+ @type mySqlHost: string
"""
self.__db = MySQLdb.connect(user = mySqlUser, db = dbName,
@@ -63,17 +71,16 @@ class Db() :
def query(self, statement) :
"""
- Query the database.
+ Query the database.
- Arguments:
- statement ; The statement that is to be queried, consists of
- a tuple: (string, (args)).
+ Private variables:
+ - __db ; Interface to the database.
- Returns:
- list ; The result of the query.
+ @arg statement: The statement that is to be queried
+ @type statement: tuple (string, (args))
- Private variables:
- __db ; Interface to the database.
+ @return: The result of the query
+ @rtype: list
"""
# Convert the arguments to a tuple.
@@ -107,38 +114,38 @@ class Db() :
class Mapping(Db) :
"""
- Database functions for mapping of transcripts and genes.
-
- Special methods:
- __init__(build, config) ; Initialise the class.
-
- Public methods:
- get_protAcc(mrnaAcc) ; Query the database for a protein ID.
- get_NM_info(mrnaAcc) ; Retrieve various data for an NM number.
- get_NM_version(mrnaAcc) ; Get the version number of an accession
- number.
- get_Transcripts(chrom, ; Get a list of transcripts, given a
- position, chromosome and a range.
- overlap)
- get_GeneName(mrnaAcc) ; Get the gene name, given an NM number.
- isChrom(name) ; Check whether we know this name to be
- a chromosome name.
-
- Inherited methods from Db:
- query(statement) ; General query function.
-
- SQL tables from dbNames:
- map ; Accumulated mapping info.
+ Database functions for mapping of transcripts and genes.
+
+ Special methods:
+ - __init__(build, config) ; Initialise the class.
+
+ Public methods:
+ - get_protAcc(mrnaAcc) ; Query the database for a protein ID.
+ - get_NM_info(mrnaAcc) ; Retrieve various data for an NM number.
+ - get_NM_version(mrnaAcc) ; Get the version number of an accession
+ number.
+ - get_Transcripts(chrom, p1, p2, overlap) ; Get a list of transcripts,
+ given a chromosome and a range.
+ - get_GeneName(mrnaAcc) ; Get the gene name, given an NM number.
+ - isChrom(name) ; Check whether we know this name to be
+ a chromosome name.
+
+ Inherited methods from Db:
+ - query(statement) ; General query function.
+
+ SQL tables from dbNames:
+ - map ; Accumulated mapping info.
"""
def __init__(self, build, config) :
"""
- Initialise the Db parent class. Use the local database for a
- certain build.
+ Initialise the Db parent class. Use the local database for a certain
+ build.
- Arguments:
- build ; The version of the mapping database.
- config ; Configuration variables.
+ @arg build: The version of the mapping database
+ @type build: string
+ @arg config: Configuration variables
+ @type config: class instance
"""
Db.__init__(self, build, config.LocalMySQLuser, config.LocalMySQLhost)
@@ -146,16 +153,16 @@ class Mapping(Db) :
def get_protAcc(self, mrnaAcc) :
"""
- Query the database for a protein ID given an mRNA ID.
+ Query the database for a protein ID given an mRNA ID.
- Arguments:
- mrnaAcc ; The ID of an mRNA.
+ SQL tables from dbNames:
+ - map ; Accumulated mapping info.
- SQL tables from dbNames:
- map ; Accumulated mapping info.
+ @arg mrnaAcc: The ID of an mRNA
+ @type mrnaAcc: string
- Returns:
- string ; The protein ID .
+ @return: The protein ID
+ @rtype: string
"""
statement = """
@@ -167,25 +174,28 @@ class Mapping(Db) :
return self.query(statement)[0][0]
#get_protAcc
- def get_NM_info(self, mrnaAcc, version=None) :
+ def get_NM_info(self, mrnaAcc, version = None) :
"""
- Retrieve various data for an NM number.
+ Retrieve various data for an NM number.
- Arguments:
- mrnaAcc ; The ID of an mRNA.
+ SQL tables from dbNames:
+ - map ; Accumulated mapping info.
- SQL tables from dbNames:
- map ; Accumulated mapping info.
+ @arg mrnaAcc: The ID of an mRNA
+ @type mrnaAcc: string
+ @arg version: version number of the accession number (not used)
+ @type version: integer
- Returns:
- list:
- exonStarts ; List of exon start sites.
- exonEnds ; List of exon end sites.
- cdsStart ; Position of the start codon.
- cdsEnd ; Position of the end codon.
- strand ; The orientation of the gene (+ = forward,
- - = reverse).
+ @return:
+ - exonStarts ; List of exon start sites.
+ - exonEnds ; List of exon end sites.
+ - cdsStart ; Position of the start codon.
+ - cdsEnd ; Position of the end codon.
+ - strand ; Orientation of the gene (+ = forward,
+ - = reverse)
+ @rtype: list
"""
+
statement = """
SELECT exonStarts, exonEnds, cdsStart, cdsEnd, strand
FROM map
@@ -197,16 +207,16 @@ class Mapping(Db) :
def get_NM_version(self, mrnaAcc) :
"""
- Get the version number of an accession number.
+ Get the version number of an accession number.
- Arguments:
- mrnaAcc ; The ID of an mRNA.
+ SQL tables from dbNames:
+ - map ; Accumulated mapping info.
- SQL tables from dbNames:
- map ; Accumulated mapping info.
+ @arg mrnaAcc: The ID of an mRNA
+ @type mrnaAcc: string
- Returns:
- integer ; The version number.
+ @return: The version number
+ @rtype: integer
"""
statement = """
@@ -220,18 +230,19 @@ class Mapping(Db) :
def getAllFields(self, mrnaAcc, version):
"""
- Get all Fields of an accession number and version number.
- If the version number is None, use the "newest" version number
+ Get all Fields of an accession number and version number.
+ If the version number is None, use the "newest" version number.
- Arguments:
- mrnaAcc ; The ID of an mRNA.
- version ; The version number
+ SQL tables from dbNames:
+ - map ; Accumulated mapping info.
- SQL tables from dbNames:
- map ; Accumulated mapping info.
+ @arg mrnaAcc: The ID of an mRNA
+ @type mrnaAcc: string
+ @arg version: The version number
+ @type version: integer
- Returns:
- integer ; The version number.
+ @return: The version number
+ @rtype: integer
"""
q = """
@@ -260,26 +271,29 @@ class Mapping(Db) :
def get_Transcripts(self, chrom, p1, p2, overlap) :
"""
- Get a list of transcripts, given a chromosome and a range. If
- all transcripts that are hit should be returned, set overlap to 1,
- if only the transcripts that completely reside within a range
- should be returned, set overlap to 0.
-
- Arguments:
- chrom ; The chromosome (coded as "chr1", ..., "chrY").
- p1 ; The position relative to the start of the chromosome.
- p2 ; The position relative to the start of the chromosome.
- overlap ; Specify the behaviour of the selection:
- 0 ; Return only the transcripts that completely fall
- in the range [p1, p2].
- 1 ; Return all hit transcripts.
-
- SQL tables from dbNames:
- map ; Accumulated mapping info.
+ Get a list of transcripts, given a chromosome and a range. If
+ all transcripts that are hit should be returned, set overlap to 1,
+ if only the transcripts that completely reside within a range
+ should be returned, set overlap to 0.
- Returns:
- list ; All accession numbers that are hit according to the
- overlap criterium.
+ SQL tables from dbNames:
+ - map ; Accumulated mapping info.
+
+ @arg chrom: The chromosome (coded as "chr1", ..., "chrY")
+ @type chrom: string
+ @arg p1: The position relative to the start of the chromosome
+ @type p1: integer
+ @arg p2: The position relative to the start of the chromosome
+ @type p2: integer
+ @arg overlap: Specify the behaviour of the selection:
+ - 0 ; Return only the transcripts that completely fall in the
+ range [p1, p2]
+ - 1 ; Return all hit transcripts
+ @type overlap: boolean
+
+ @return: All accession numbers that are hit according to the overlap
+ criterium
+ @rtype: list
"""
q = """
select acc,
@@ -342,16 +356,16 @@ class Mapping(Db) :
def get_GeneName(self, mrnaAcc) :
"""
- Get the name of a gene, given a transcript identifier (NM number).
+ Get the name of a gene, given a transcript identifier (NM number).
- Arguments:
- mrnaAcc ; The ID of an mRNA.
+ SQL tables from dbNames:
+ - map ; Accumulated mapping info.
- SQL tables from dbNames:
- map ; Accumulated mapping info.
+ @arg mrnaAcc: The ID of an mRNA
+ @type mrnaAcc: string
- Returns:
- string ; The gene name.
+ @return: The gene name
+ @rtype: string
"""
statement = """
@@ -368,17 +382,17 @@ class Mapping(Db) :
def isChrom(self, name) :
"""
- Check if the given name is a valid chromosome name.
+ Check if the given name is a valid chromosome name.
- Arguments:
- name ; The name to be tested.
+ SQL tables from dbNames:
+ - map ; Accumulated mapping info.
- SQL tables from dbNames:
- map ; Accumulated mapping info.
+ @arg name: The name to be tested
+ @type name: string
- Returns:
- boolean ; True if the name is found to be a chromosome name,
- False otherwise.
+ @return: True if the name is found to be a chromosome name, False
+ otherwise
+ @rtype: boolean
"""
statement = """
@@ -394,16 +408,16 @@ class Mapping(Db) :
def chromName(self, accNo) :
"""
- Get the name of a chromosome, given an accession number.
+ Get the name of a chromosome, given an accession number.
- Arguments:
- accNo ; The accession number of a chromosome.
+ SQL tables from dbNames:
+ - ChrName ; Assembly release notes.
- SQL tables from dbNames:
- ChrName ; Assembly release notes.
+ @arg accNo: The accession number of a chromosome
+ @type accNo: string
- Returns:
- string ; The name of a chromosome.
+ @return: The name of a chromosome
+ @rtype: string
"""
statement = """
@@ -420,16 +434,16 @@ class Mapping(Db) :
def chromAcc(self, name) :
"""
- Get the accession number of a chromosome, given a name.
+ Get the accession number of a chromosome, given a name.
- Arguments:
- name ; The name of a chromosome.
+ SQL tables from dbNames:
+ - ChrName ; Assembly release notes.
- SQL tables from dbNames:
- ChrName ; Assembly release notes.
+ @arg name: The name of a chromosome
+ @type name: string
- Returns:
- string ; The accession number of a chromosome.
+ @return: The accession number of a chromosome
+ @rtype: string
"""
statement = """
@@ -446,17 +460,16 @@ class Mapping(Db) :
def get_chromName(self, acc) :
"""
- Get the chromosome name, given a transcript identifier (NM number).
+ Get the chromosome name, given a transcript identifier (NM number).
- Arguments:
- acc ; The NM accession number (version NOT included)
+ SQL tables from dbNames:
+ - map ; Accumulated mapping info.
- SQL tables from dbNames:
- map ; .
-
- Returns:
- string ; The chromosome name (e.g. chr1)
+ @arg acc: The NM accession number (version NOT included)
+ @type acc: string
+ @return: The chromosome name (e.g. chr1)
+ @rtype: string
"""
statement = """
@@ -474,37 +487,38 @@ class Mapping(Db) :
class Remote(Db) :
"""
- Database functions for retrieving updates for the mapping databases.
+ Database functions for retrieving updates for the mapping databases.
- Special methods:
- __init__(config) ; Initialise the class.
+ Special methods:
+ - __init__(config) ; Initialise the class.
- Public methods:
- get_Update() ; Retrieve new mapping info from the UCSC.
+ Public methods:
+ - get_Update() ; Retrieve new mapping info from the UCSC.
- Inherited methods from Db:
- query(statement) ; General query function.
+ Inherited methods from Db:
+ - query(statement) ; General query function.
- SQL tables from dbNames:
- gbStatus ; acc -> version mapping (NM to NM + version),
- type, modDate
- refGene ; name -> geneName mapping (NM to gene name),
- txStart, txEnd, cdsStart, cdsEnd, exonStarts,
- exonEnds, chrom, strand.
- refLink ; mrnaAcc -> protAcc mapping (NM to NP).
+ SQL tables from dbNames:
+ - gbStatus ; acc -> version mapping (NM to NM + version),
+ type, modDate
+ - refGene ; name -> geneName mapping (NM to gene name),
+ txStart, txEnd, cdsStart, cdsEnd, exonStarts,
+ exonEnds, chrom, strand.
+ - refLink ; mrnaAcc -> protAcc mapping (NM to NP).
"""
def __init__(self, build, config) :
"""
- Initialise the Db parent class. Use the remote database for a
- certain build.
+ Initialise the Db parent class. Use the remote database for a
+ certain build.
- Arguments:
- build ; The version of the mapping database.
- config ; Configuration variables.
+ Private variables (altered):
+ - __config ; Configuration variables.
- Private variables (altered):
- __config ; Configuration variables.
+ @arg build: The version of the mapping database
+ @type build: string
+ @arg config: Configuration variables
+ @type config: class instance
"""
self.__config = config
@@ -513,22 +527,22 @@ class Remote(Db) :
def get_Update(self) :
"""
- Retrieve all mapping updates from the UCSC within a certain time
- window (defined in the configuration file) and gather the results
- into one mapping table.
+ Retrieve all mapping updates from the UCSC within a certain time
+ window (defined in the configuration file) and gather the results
+ into one mapping table.
- The results will be written to a temporary file (also defined in
- the configuration file) to be imported in the local database with
- the load_Update() function.
+ The results will be written to a temporary file (also defined in
+ the configuration file) to be imported in the local database with
+ the load_Update() function.
- SQL tables from dbNames:
- gbStatus ; acc -> version mapping (NM to NM + version),
- type, modDate
- refGene ; name -> geneName mapping (NM to gene name),
- txStart, txEnd, cdsStart, cdsEnd, exonStarts,
- exonEnds, chrom, strand.
- refLink ; mrnaAcc -> protAcc mapping (NM to NP).
+ SQL tables from dbNames:
+ - gbStatus ; acc -> version mapping (NM to NM + version),
+ type, modDate
+ - refGene ; name -> geneName mapping (NM to gene name),
+ txStart, txEnd, cdsStart, cdsEnd, exonStarts,
+ exonEnds, chrom, strand.
+ - refLink ; mrnaAcc -> protAcc mapping (NM to NP).
"""
statement = """
@@ -557,44 +571,45 @@ class Remote(Db) :
class Update(Db) :
"""
- Database functions for updating the mapping databases.
-
- Public methods:
- load_Update() ; Load new mapping info into the local database.
- count_Updates() ; Count the number of entries in the new
- mapping info table.
- backup_cdsUpdates() ; Make a backup of updates that overwrite the
- old mapping info.
- count_cdsUpdates() ; Count the number of updates that overwrite
- the old mapping info.
- merge_cdsUpdates() ; Merge the backup of old mapping info with the
- other old info.
- merge_Update() ; Merge the new mapping info from the UCSC with
- what we already have.
-
- Inherited methods from Db:
- query(statement) ; General query function.
-
- SQL tables from dbNames:
- map ; Accumulated mapping info.
- map_temp ; Newly found data.
- map_new ; Merge of map_temp and map.
- map_cdsBackup_temp ; Entries that were updated without an increment
- of the version number.
- map_cdsBackup ; Merge of map_cdsBackup_temp and itself.
+ Database functions for updating the mapping databases.
+
+ Public methods:
+ - load_Update() ; Load new mapping info into the local database.
+ - count_Updates() ; Count the number of entries in the new
+ mapping info table.
+ - backup_cdsUpdates() ; Make a backup of updates that overwrite the
+ old mapping info.
+ - count_cdsUpdates() ; Count the number of updates that overwrite
+ the old mapping info.
+ - merge_cdsUpdates() ; Merge the backup of old mapping info with the
+ other old info.
+ - merge_Update() ; Merge the new mapping info from the UCSC with
+ what we already have.
+
+ Inherited methods from Db:
+ - query(statement) ; General query function.
+
+ SQL tables from dbNames:
+ - map ; Accumulated mapping info.
+ - map_temp ; Newly found data.
+ - map_new ; Merge of map_temp and map.
+ - map_cdsBackup_temp ; Entries that were updated without an increment
+ of the version number.
+ - map_cdsBackup ; Merge of map_cdsBackup_temp and itself.
"""
def __init__(self, build, config) :
"""
- Initialise the Db parent class. Use the remote database for a
- certain build.
+ Initialise the Db parent class. Use the remote database for a
+ certain build.
- Arguments:
- build ; The version of the mapping database.
- config ; Configuration variables.
+ Private variables (altered):
+ - __config ; Configuration variables.
- Private variables (altered):
- __config ; Configuration variables.
+ @arg build: The version of the mapping database
+ @type build: string
+ @arg config: Configuration variables
+ @type config: class instance
"""
self.__config = config
@@ -603,15 +618,15 @@ class Update(Db) :
def load_Update(self) :
"""
- Load the updates from the temporary file (defined in the
- configuration file) created by the get_Update() function and import
- it in the local database.
+ Load the updates from the temporary file (defined in the
+ configuration file) created by the get_Update() function and import
+ it in the local database.
- SQL tables from dbNames (altered):
- map_temp ; Created and loaded with data from TempFile.
+ SQL tables from dbNames (altered):
+ - map_temp ; Created and loaded with data from TempFile.
- SQL tables from dbNames:
- map ; Accumulated mapping info.
+ SQL tables from dbNames:
+ - map ; Accumulated mapping info.
"""
# The statements in this function may be combined when MYSQL_BUG is
@@ -633,15 +648,14 @@ class Update(Db) :
def count_Updates(self) :
"""
- Count the number of updates. This function will only work if it
- is preceeded by the load_Update() function. Otherwise the map_temp
- table may not exist. This function can not be used after the
- merge_Update() function has been executed, since it drops the
- map_temp table.
+ Count the number of updates. This function will only work if it
+ is preceeded by the load_Update() function. Otherwise the map_temp
+ table may not exist. This function can not be used after the
+ merge_Update() function has been executed, since it drops the
+ map_temp table.
- Returns:
- int ; The number of entries in the table of updated mapping
- info.
+ @return: The number of entries in the table of updated mapping info
+ @rtype: integer
"""
statement = """
@@ -654,19 +668,19 @@ class Update(Db) :
def backup_cdsUpdates(self) :
"""
- Copy all mapping entries where there was an update, but no
- increment in the version number, to a backup table. Note that
- we use acc, version, txStart as the primary key because members
- of a gene family are mapped multiple times.
+ Copy all mapping entries where there was an update, but no
+ increment in the version number, to a backup table. Note that
+ we use acc, version, txStart as the primary key because members
+ of a gene family are mapped multiple times.
- SQL tables from dbNames (altered):
- map_cdsBackup_temp ; Created and filled with entries that
- were updated without an increment of the
- version number.
+ SQL tables from dbNames (altered):
+ - map_cdsBackup_temp ; Created and filled with entries that
+ were updated without an increment of the
+ version number.
- SQL tables from dbNames:
- map ; Accumulated mapping info.
- map_temp ; Freshly downloaded mapping info.
+ SQL tables from dbNames:
+ - map ; Accumulated mapping info.
+ - map_temp ; Freshly downloaded mapping info.
"""
statement = """
@@ -687,18 +701,18 @@ class Update(Db) :
def count_cdsUpdates(self) :
"""
- Count the number of mapping entries that have changed without an
- increment in the version number. This function can only be called
- after backup_cdsUpdates() has been executed and before
- merge_cdsUpdates has been executed.
+ Count the number of mapping entries that have changed without an
+ increment in the version number. This function can only be called
+ after backup_cdsUpdates() has been executed and before
+ merge_cdsUpdates has been executed.
- SQL tables from dbNames:
- map_cdsBackup_temp ; Entries that wre updated without an
- increment of the version number.
+ SQL tables from dbNames:
+ - map_cdsBackup_temp ; Entries that wre updated without an
+ increment of the version number.
- Returns:
- int ; The number of mapping entries that have changed without
- an increment in the version number.
+ @return: The number of mapping entries that have changed without an
+ increment in the version number
+ @rtype: integer
"""
statement = """
@@ -711,14 +725,14 @@ class Update(Db) :
def merge_cdsUpdates(self) :
"""
- Merge the mapping entries that have changed without an increment in
- the version number with a table that contains backups of these
- entries.
+ Merge the mapping entries that have changed without an increment in
+ the version number with a table that contains backups of these
+ entries.
- SQL tables from dbNames (altered):
- map_cdsBackup ; Extended with the entries in
- map_cdsBackup_temp.
- map_cdsBackup_temp ; Dropped.
+ SQL tables from dbNames (altered):
+ - map_cdsBackup ; Extended with the entries in
+ map_cdsBackup_temp.
+ - map_cdsBackup_temp ; Dropped.
"""
# The statements in this function may be combined when MYSQL_BUG is
@@ -739,13 +753,13 @@ class Update(Db) :
def merge_Update(self) :
"""
- Merge the new mapping data with the old ones.
+ Merge the new mapping data with the old ones.
- SQL tables from dbNames (altered):
- map_new ; Created and filled with the merge of map_temp and
- map. Dropped after use.
- map_temp ; Merged with map to form map_new. Dropped after use.
- map ; Overwritten with the merged info in map_new.
+ SQL tables from dbNames (altered):
+ - map_new ; Created and filled with the merge of map_temp and map.
+ Dropped after use.
+ - map_temp ; Merged with map to form map_new. Dropped after use.
+ - map ; Overwritten with the merged info in map_new.
"""
# The statements in this function may be combined when MYSQL_BUG is
@@ -791,46 +805,38 @@ class Update(Db) :
class Cache(Db) :
"""
- Database functions for cache administration.
-
- Special methods:
- __init__(config) ; Initialise the class.
-
- Public methods:
- insertGB(accNo, GI, ; Insert info about a GenBank record.
- fileHash,
- ChrAccVer,
- ChrStart,
- ChrStop,
- orientation,
- url)
- updateHash(accNo, ; Update the hash of an accession number.
- fileHash)
- getGBFromLoc(ChrAccVer, ; Get the accession number from slicing
- ChrStart, information.
- ChrStop,
- orientation)
- getGBFromHash(fileHash) ; Get the accession number from its hash.
- getGBFromGI(GI) ; Get the accession number from its GI
- number.
- getLoc(accNo) ; Get the slicing information of an
- accession number.
- getHash(accNo) ; Get the hash of a GenBank record.
- getUrl(accNo) ; Get the URL of an accession number.
-
- Inherited methods from Db:
- query(statement) ; General query function.
-
- SQL tables from internalDb:
- GBInfo ; Information about cached and uploaded GenBank files.
+ Database functions for cache administration.
+
+ Special methods:
+ - __init__(config) ; Initialise the class.
+
+ Public methods:
+ - insertGB(accNo, GI, fileHash, ChrAccVer, ChrStart, ChrStop,
+ orientation, url) ; Insert info about a GenBank record.
+ - updateHash(accNo, fileHash) ; Update the hash of an accession number.
+ - getGBFromLoc(ChrAccVer, ChrStart, ChrStop, orientation) ; Get the
+ accession number from slicing information.
+ - getGBFromHash(fileHash) ; Get the accession number from its hash.
+ - getGBFromGI(GI) ; Get the accession number from its GI
+ number.
+ - getLoc(accNo) ; Get the slicing information of an
+ accession number.
+ - getHash(accNo) ; Get the hash of a GenBank record.
+ - getUrl(accNo) ; Get the URL of an accession number.
+
+ Inherited methods from Db:
+ - query(statement) ; General query function.
+
+ SQL tables from internalDb:
+ - GBInfo ; Information about cached and uploaded GenBank files.
"""
def __init__(self, config) :
"""
- Initialise the Db parent class. Use the internalDb.
+ Initialise the Db parent class. Use the internalDb.
- Arguments:
- config ; Configuration variables.
+ @arg config: Configuration variables
+ @type config: class instance
"""
Db.__init__(self, config.internalDb, config.LocalMySQLuser,
@@ -840,35 +846,41 @@ class Cache(Db) :
def insertGB(self, accNo, GI, fileHash, ChrAccVer, ChrStart,
ChrStop, orientation, url) :
"""
- Insert information about a GenBank record in the internal database.
+ Insert information about a GenBank record in the internal database.
- The accNo and fileHash arguments are mandatory.
+ The accNo and fileHash arguments are mandatory.
- If the record is a normal RefSeq, then the GI number should be
- provided.
- - If the record is a chromosome slice, then the ChrAccVer,
- ChrStart, ChrStop and orientation variables should be specified.
- - If the record is downloaded from the internet, the url should
- be provided.
- - If all fields except the mandatory ones are empty, the record
- is assumed to be uploaded.
-
- Arguments:
- accNo ; The name associated with this record.
- GI ; The GI number (if available).
- fileHash ; The hash of the content of the record.
- ChrAccVer ; The accession number of the chromosome (if
- available).
- ChrStart ; The start of the record in chromosomal
- coordinates (if available).
- ChrStop ; The end of the record in chromosomal coordinates
- (if available).
- orientation ; The orientation of the record relative to the
- chromosome (if available) (1 = forward,
- 2 = reverse complement).
- url ; The originating URL (if available).
-
- SQL tables from internalDb (altered):
- GBInfo ; Information about cached and uploaded GenBank files.
+ provided.
+ - If the record is a chromosome slice, then the ChrAccVer, ChrStart,
+ ChrStop and orientation variables should be specified.
+ - If the record is downloaded from the internet, the url should be
+ provided.
+ - If all fields except the mandatory ones are empty, the record is
+ assumed to be uploaded.
+
+ SQL tables from internalDb (altered):
+ - GBInfo ; Information about cached and uploaded GenBank files.
+
+ @arg accNo: The name associated with this record
+ @type accNo: string
+ @arg GI: The GI number (if available)
+ @type GI: string
+ @arg fileHash: The hash of the content of the record
+ @type fileHash: string
+ @arg ChrAccVer: The accession number of the chromosome (if available)
+ @type ChrAccVer: string
+ @arg ChrStart: The start of the record in chromosomal
+ coordinates (if available)
+ @type ChrStart: integer
+ @arg ChrStop: The end of the record in chromosomal coordinates
+ (if available)
+ @type ChrStop: integer
+ @arg orientation: The orientation of the record relative to the
+ chromosome (if available) (1 = forward,
+ 2 = reverse complement)
+ @type orientation: integer
+ @arg url: The originating URL (if available)
+ @type url: string
"""
statement = """
@@ -882,8 +894,18 @@ class Cache(Db) :
def insertLRG(self, accNo, fileHash, url):
"""
- Insert information about a LRG record in the internal database
+ Insert information about a LRG record in the internal database.
+
+ See insertGB() for more information.
+
+ @arg accNo: The name associated with this record
+ @type accNo: string
+ @arg fileHash: The hash of the content of the record
+ @type fileHash: string
+ @arg url: The originating URL (if available)
+ @type url: string
"""
+
statement = """
INSERT INTO GBInfo
VALUES (%s, %s, %s, %s, %s, %s, %s, %s);
@@ -895,14 +917,15 @@ class Cache(Db) :
def updateHash(self, accNo, fileHash) :
"""
- Update the hash of an accession number.
+ Update the hash of an accession number.
- Arguments:
- accNo ; The accession number of a GenBank record.
- fileHash ; The hash of a GenBank record.
+ SQL tables from internalDb (altered):
+ - GBInfo ; Information about cached and uploaded GenBank files.
- SQL tables from internalDb (altered):
- GBInfo ; Information about cached and uploaded GenBank files.
+ @arg accNo: The accession number of a GenBank record
+ @type accNo: string
+ @arg fileHash: The hash of a GenBank record
+ @type fileHash: string
"""
statement = """
@@ -916,22 +939,25 @@ class Cache(Db) :
def getGBFromLoc(self, ChrAccVer, ChrStart, ChrStop, orientation) :
"""
- Get the accession number from a chromosomic location, used
- to make a slice, typically this only affects UD-numbers.
+ Get the accession number from a chromosomic location, used
+ to make a slice, typically this only affects UD-numbers.
- Arguments:
- ChrAccVer ; The accession number of the chromosome.
- ChrStart ; Start position of the slice.
- ChrStop ; End position of the slice.
- orientation ; Orientation of the slice:
- 1 ; Forward.
- 2 ; Reverse complement.
+ SQL tables from internalDb:
+ - GBInfo ; Information about cached and uploaded GenBank files.
- SQL tables from internalDb:
- GBInfo ; Information about cached and uploaded GenBank files.
+ @arg ChrAccVer: The accession number of the chromosome
+ @type ChrAccVer: string
+ @arg ChrStart: Start position of the slice
+ @type ChrStart: integer
+ @arg ChrStop: End position of the slice
+ @type ChrStop: integer
+ @arg orientation: Orientation of the slice:
+ 1. Forward
+ 2. Reverse complement
+ @type orientation: integer
- Returns:
- string ; The accession number.
+ @return: The accession number
+ @rtype: string
"""
statement = """
@@ -951,16 +977,16 @@ class Cache(Db) :
def getGBFromHash(self, fileHash) :
"""
- Get the accession number from its hash.
+ Get the accession number from its hash.
- Arguments:
- fileHash ; The hash of a GenBank record.
+ SQL tables from internalDb:
+ - GBInfo ; Information about cached and uploaded GenBank files.
- SQL tables from internalDb:
- GBInfo ; Information about cached and uploaded GenBank files.
+ @arg fileHash: The hash of a GenBank record
+ @type fileHash: string
- Returns:
- string ; The accession number.
+ @return: The accession number
+ @rtype: string
"""
statement = """
@@ -977,17 +1003,17 @@ class Cache(Db) :
def getGBFromGI(self, GI) :
"""
- Get the accession number from its GI number, typically this only
- affects RefSeq sequences.
+ Get the accession number from its GI number, typically this only
+ affects RefSeq sequences.
- Arguments:
- GI ; The GI number of a GenBank record.
+ SQL tables from internalDb:
+ - GBInfo ; Information about cached and uploaded GenBank files.
- SQL tables from internalDb:
- GBInfo ; Information about cached and uploaded GenBank files.
+ @arg GI: The GI number of a GenBank record
+ @type GI: string
- Returns:
- string ; The accession number.
+ @return: The accession number
+ @rtype: string
"""
statement = """
@@ -1004,22 +1030,22 @@ class Cache(Db) :
def getLoc(self, accNo) :
"""
- Get the slicing information of an accession number, typically this
- only affects UD numbers.
+ Get the slicing information of an accession number, typically this
+ only affects UD numbers.
- Arguments:
- accNo ; The accession number of a genbank record.
+ SQL tables from internalDb:
+ - GBInfo ; Information about cached and uploaded GenBank files.
- SQL tables from internalDb:
- GBInfo ; Information about cached and uploaded GenBank files.
+ @arg accNo: The accession number of a genbank record
+ @type accNo: string
- Returns:
- list ; The slicing information:
- ChrAccVer ; Accession number of the chromosome.
- ChrStart ; Start position of the slice.
- ChrStop ; End position of the slice.
- orientation ; Orientation of the slice (1 = forward,
- 2 = reverse complement).
+ @return: The slicing information:
+ - ChrAccVer ; Accession number of the chromosome
+ - ChrStart ; Start position of the slice
+ - ChrStop ; End position of the slice
+ - orientation ; Orientation of the slice (1 = forward,
+ 2 = reverse complement)
+ @rtype: list
"""
statement = """
@@ -1036,16 +1062,16 @@ class Cache(Db) :
def getHash(self, accNo) :
"""
- Get the hash of a GenBank record identified by an accession number.
+ Get the hash of a GenBank record identified by an accession number.
- Arguments:
- accNo ; The accession number of a genbank record.
+ SQL tables from internalDb:
+ - GBInfo ; Information about cached and uploaded GenBank files.
- SQL tables from internalDb:
- GBInfo ; Information about cached and uploaded GenBank files.
+ @arg accNo: The accession number of a genbank record
+ @type accNo: string
- Returns:
- string ; The hash of the GenBank record.
+ @return: The hash of the GenBank record
+ @rtype: string
"""
statement = """
@@ -1062,17 +1088,17 @@ class Cache(Db) :
def getUrl(self, accNo) :
"""
- Get the URL of an accession number, typically this only affects
- uploaded UD numbers.
+ Get the URL of an accession number, typically this only affects
+ uploaded UD numbers.
- Arguments:
- accNo ; The accession number of a genbank record.
+ SQL tables from internalDb:
+ - GBInfo ; Information about cached and uploaded GenBank files.
- SQL tables from internalDb:
- GBInfo ; Information about cached and uploaded GenBank files.
+ @arg accNo: The accession number of a genbank record
+ @type accNo: string
- Returns:
- string ; The URL of the GenBank record.
+ @return: The URL of the GenBank record
+ @rtype: string
"""
statement = """
@@ -1089,13 +1115,16 @@ class Cache(Db) :
def getGI(self, accNo) :
"""
- Get the GI number that is connected to the accession number.
+ Get the GI number that is connected to the accession number.
- Arguments:
- accNo ; The accession number.
+ SQL tables from internalDb:
+ - GBInfo ; Information about cached and uploaded GenBank files.
- SQL tables from internalDb:
- GBInfo ; Information about cached and uploaded GenBank files.
+ @arg accNo: The accession number
+ @type accNo: string
+
+ @return: GI number
+ @rtype: string
"""
statement = """
@@ -1112,6 +1141,17 @@ class Cache(Db) :
def getProtAcc(self, mrnaAcc) :
"""
+ Gets the protein accession number for the given mRNA accession
+ number.
+
+ SQL tables from internalDb:
+ - Link ; mRNA and associated protein IDs.
+
+ @arg mrnaAcc: The ID of an mRNA
+ @type mrnaAcc: string
+
+ @return: The protein accession number
+ @rtype: string
"""
statement = """
@@ -1128,6 +1168,16 @@ class Cache(Db) :
def getmrnaAcc(self, protAcc) :
"""
+ Gets the mRNA accession number for a given protein accession number.
+
+ SQL tables from internalDb:
+ - Link ; mRNA and associated protein IDs.
+
+ @arg protAcc: The protein ID
+ @type protAcc: string
+
+ @return: The mRNA accession number
+ @rtype: string
"""
statement = """
@@ -1145,6 +1195,16 @@ class Cache(Db) :
def insertLink(self, mrnaAcc, protAcc) :
"""
+ Inserts the given mRNA and protein accession numbers into the Link
+ table.
+
+ SQL tables from internalDb:
+ - Link ; mRNA and associated protein IDs.
+
+ @arg protAcc: The protein ID
+ @type protAcc: string
+ @arg mrnaAcc: The ID of an mRNA
+ @type mrnaAcc: string
"""
statement = """
@@ -1158,40 +1218,37 @@ class Cache(Db) :
class Batch(Db) :
"""
- Database functions for the batch checker.
-
- Special methods:
- __init__(config) ; Initialise the class.
-
- Public methods:
- isJobListEmpty() ; See if there are active jobs.
- addJob(outputFilter, ; Add a job and give it a unique ID.
- email,
- fromHost)
- getJobs() ; Get a list of active jobs.
- removeJob(jobID) ; Remove a job and return information about
- the job submitter.
- addToQueue(jobID, ; Add a request belonging to a certain job to
- accNo, the queue.
- gene,
- variant)
- getFromQueue(jobID) ; Get a request belonging to a certain job
- from the queue.
-
- Inherited methods from Db:
- query(statement) ; General query function.
-
- SQL tables from internalDb:
- BatchJob ; Job information.
- BatchQueue ; Requests.
+ Database functions for the batch checker.
+
+ Special methods:
+ - __init__(config) ; Initialise the class.
+
+ Public methods:
+ - isJobListEmpty() ; See if there are active jobs.
+ - addJob(outputFilter, email, fromHost); Add a job and give it a unique
+ ID.
+ - getJobs() ; Get a list of active jobs.
+ - removeJob(jobID) ; Remove a job and return information about
+ the job submitter.
+ - addToQueue(jobID, accNo, gene, variant) ; Add a request belonging to a
+ certain job to the queue.
+ - getFromQueue(jobID) ; Get a request belonging to a certain job
+ from the queue.
+
+ Inherited methods from Db:
+ - query(statement) ; General query function.
+
+ SQL tables from internalDb:
+ - BatchJob ; Job information.
+ - BatchQueue ; Requests.
"""
def __init__(self, config) :
"""
- Initialise the Db parent class. Use the internalDb.
+ Initialise the Db parent class. Use the internalDb.
- Arguments:
- config ; Configuration variables.
+ @arg config: Configuration variables
+ @type config: class instance
"""
Db.__init__(self, config.internalDb, config.LocalMySQLuser,
@@ -1200,13 +1257,13 @@ class Batch(Db) :
def isJobListEmpty(self) :
"""
- See if there are active jobs.
+ See if there are active jobs.
- SQL tables from internalDb:
- BatchJob ; Job information.
+ SQL tables from internalDb:
+ - BatchJob ; Job information.
- Returns:
- boolean ; False if there are active jobs, True otherwise.
+ @return: False if there are active jobs, True otherwise
+ @rtype: boolean
"""
statement = """
@@ -1221,16 +1278,16 @@ class Batch(Db) :
def entriesLeftForJob(self, jobID):
"""
- Count the number of entries of a job that are still to be processed
+ Count the number of entries of a job that are still to be processed
- Arguments:
- jobID ; The JobID of interest
+ SQL tables from internalDB:
+ - BatchQueue ; Queue information
- SQL tables from internalDB:
- BatchQueue ; Queue information
+ @arg jobID: The JobID of interest
+ @type jobID: string
- Returns:
- int ; The number of entries
+ @return: The number of entries
+ @rtype: integer
"""
statement = """
SELECT COUNT(*)
@@ -1244,18 +1301,20 @@ class Batch(Db) :
def addJob(self, outputFilter, email, fromHost, jobType, Arg1) :
"""
- Add a job and give it a unique ID.
+ Add a job and give it a unique ID.
- Arguments:
- outputFilter ; Output settings for all requests in this job.
- email ; Contact information of the submitter.
- jobType ; The type of batch job
+ SQL tables from internalDb (altered):
+ - BatchJob ; Job information.
- SQL tables from internalDb (altered):
- BatchJob ; Job information.
+ @arg outputFilter: Output settings for all requests in this job
+ @type outputFilter: string
+ @arg email: Contact information of the submitter
+ @type email: string
+ @arg jobType: The type of batch job
+ @type jobType: string
- Returns:
- int ; A job ID.
+ @return: A job ID
+ @rtype: integer
"""
M = Misc.Misc()
@@ -1272,13 +1331,13 @@ class Batch(Db) :
def getJobs(self) :
"""
- Get a list of active jobs.
+ Get a list of active jobs.
- SQL tables from internalDb:
- BatchJob ; Job information.
+ SQL tables from internalDb:
+ - BatchJob ; Job information.
- Returns:
- list ; List of tuples (job ID, job Type).
+ @return: List of tuples (job ID, job Type)
+ @rtype: list
"""
statement = """
@@ -1294,14 +1353,14 @@ class Batch(Db) :
Remove a job (because the queue for this job is empty) and return
information needed to alert the job submitter.
- Arguments:
- jobID ; Identifier of a job.
-
SQL tables from internalDb (altered):
- BatchJob ; Job information.
+ - BatchJob ; Job information.
- Returns:
- triple ; Data for the job submitter.
+ @arg jobID: Identifier of a job
+ @type jobID: string
+
+ @return: Data for the job submitter
+ @rtype: triple
"""
# First retrieve all information about this job.
@@ -1325,14 +1384,15 @@ class Batch(Db) :
def addToQueue(self, jobID, inputl, flag):
"""
- Add a request belonging to a certain job to the queue.
+ Add a request belonging to a certain job to the queue.
- Arguments:
- jobID ; Identifier of a job.
- inputl ; The input line of an entry
+ SQL tables from internalDb (altered):
+ - BatchQueue ; Requests.
- SQL tables from internalDb (altered):
- BatchQueue ; Requests.
+ @arg jobID: Identifier of a job
+ @type jobID: string
+ @arg inputl: The input line of an entry
+ @type inputl: string
"""
# The first value (QueueID) will be auto increased by MySQL.
@@ -1346,23 +1406,27 @@ class Batch(Db) :
def updateBatchDb(self, jobID, old, new, flag, whereNot):
"""
- Update the Entries of a BatchJob. This is used to alter
- batch entries that would otherwise take a long time to process.
- e.g. a batch job with a lot of the same accession numbers without
- version numbers would take a long time because mutalyzer would
- fetch the file from the NCBI for each entry. A database update
- over all entries with the same accession number speeds up the
- job considerably.
-
- Arguments:
- jobID ; Identifier of a job.
- old ; String to be replaced
- new ; String to replace old with
- flag ; The reason of subsitution
- whereNot; A negative selector to prevent false positives
-
- SQL tables from internalDb (altered):
- BatchQueue ; Requests.
+ Update the Entries of a BatchJob. This is used to alter
+ batch entries that would otherwise take a long time to process.
+ e.g. a batch job with a lot of the same accession numbers without
+ version numbers would take a long time because mutalyzer would
+ fetch the file from the NCBI for each entry. A database update
+ over all entries with the same accession number speeds up the
+ job considerably.
+
+ SQL tables from internalDb (altered):
+ - BatchQueue ; Requests.
+
+ @arg jobID: Identifier of a job
+ @type jobID: string
+ @arg old: String to be replaced
+ @type old: string
+ @arg new: String to replace old with
+ @type new: string
+ @arg flag: The reason of subsitution
+ @type flag: string
+ @arg whereNot: A negative selector to prevent false positives
+ @type whereNot: string
"""
#update whereNot to escape parenthesis
whereNot = whereNot.replace("(","[(]").replace(")","[)]")
@@ -1378,16 +1442,18 @@ class Batch(Db) :
def skipBatchDb(self, jobID, where, flag):
"""
- Flag batch entries to be skipped. This is used if it is certain
- that an entry will cause an error, or that its output is ambiguous.
+ Flag batch entries to be skipped. This is used if it is certain
+ that an entry will cause an error, or that its output is ambiguous.
- Arguments:
- jobID ; Identifier of a job
- where ; Look for occurencus of this string
- flag ; The reason of skipping
+ SQL tables from internalDB (alterd):
+ - BatchQueue ; Requests
- SQL tables from internalDB (alterd):
- BatchQueue ; Requests
+ @arg jobID: Identifier of a job
+ @type jobID: string
+ @arg where: Look for occurencus of this string
+ @type where: string
+ @arg flag: The reason of skipping
+ @type flag: string
"""
#update where to escape parenthesis
where = where.replace("(","[(]").replace(")","[)]")
@@ -1404,21 +1470,21 @@ class Batch(Db) :
def getFromQueue(self, jobID) :
"""
- Get a request belonging to a certain job from the queue. If a
- request is found, remove it from the queue and return it. Otherwise
- return nothing.
+ Get a request belonging to a certain job from the queue. If a
+ request is found, remove it from the queue and return it. Otherwise
+ return nothing.
- Arguments:
- jobID ; Identifier of a job.
+ SQL tables from internalDb (altered):
+ - BatchQueue ; Requests.
- SQL tables from internalDb (altered):
- BatchQueue ; Requests.
+ @arg jobID: Identifier of a job
+ @type jobID: string
- Returns:
- triple:
- accNo ; The accession number of a request.
- gene ; The gene and transcript variant information.
- variant ; The variant.
+ @return:
+ - accNo ; The accession number of a request
+ - gene ; The gene and transcript variant information
+ - variant ; The variant
+ @rtype: triple
"""
statement = """
@@ -1431,7 +1497,7 @@ class Batch(Db) :
results = self.query(statement)
if results :
- queueID, inputl,flags = results[0]
+ queueID, inputl, flags = results[0]
else :
return None, None
diff --git a/src/Modules/File.py b/src/Modules/File.py
index 3cbfabf25f171a433272a31a4318030a4139f46b..2b9f9c2c1c6ec37caa036c05031ccebc23ed71c3 100644
--- a/src/Modules/File.py
+++ b/src/Modules/File.py
@@ -1,13 +1,21 @@
#!/usr/bin/python
-#TODO: Check ODS, XLS compatibility
-
"""
- Module for parsing CSV files and spreadsheets.
-
- Public classes:
- File ; Parse CSV files and spreadsheets.
+Module for parsing CSV files and spreadsheets.
+
+@todo: Check ODS, XLS compatibility
+@requires: magic
+@requires: csv
+@requires: xlrd
+@requires: zipfile
+@requires: xml.dom.minidom
+@requires: os
+@requires: types
+@requires: Modules.Misc
"""
+# Public classes:
+# - File ; Parse CSV files and spreadsheets.
+
import magic # open(), MAGIC_MIME, MAGIC_NONE
import csv # Sniffer(), reader(), Error
@@ -21,55 +29,60 @@ from Modules import Misc
class File() :
"""
- Parse CSV files and spreadsheets.
-
- Private variables:
- __config ; Configuration variables.
- __output ; The Output object.
-
- Special methods:
- __init__(config, output) ; Initialse the class.
-
- Private methods:
- __tempFileWrapper(func, ; Call func() with a filename.
- handle)
- __getMimeType(handle) ; Get the mime type of a stream.
- __parseCsvFile(handle) ; Parse a CSV file.
- __parseXlsFile(handle) ; Parse an Excel file.
- __parseOdsFile(handle) ; Parse an OpenDocument Spreadsheet file.
- __checkBatchFormat(job) ; Check a batch job and sanitize it.
-
- Public methods:
- parseFileRaw(handle) ; Parse a stream with the appropriate parser.
- parseBatchFile(handle) ; Parse a stream with the appropriate parser
- and sanitize the output.
+ Parse CSV files and spreadsheets.
+
+ Private variables:
+ - __config ; Configuration variables.
+ - __output ; The Output object.
+
+ Special methods:
+ - __init__(config, output) ; Initialise the class.
+
+ Private methods:
+ - __tempFileWrapper(func, handle) ; Call func() with a filename.
+ - __parseCsvFile(handle) ; Parse a CSV file.
+ - __parseXlsFile(handle) ; Parse an Excel file.
+ - __parseOdsFile(handle) ; Parse an OpenDocument Spreadsheet file.
+ - __checkBatchFormat(job) ; Check a batch job and sanitize it.
+
+ Public methods:
+ - getMimeType(handle) ; Get the mime type of a stream.
+ - parseFileRaw(handle) ; Parse a stream with the appropriate parser.
+ - parseBatchFile(handle) ; Parse a stream with the appropriate parser
+ and sanitize the output.
"""
def __init__(self, config, output) :
"""
- Initialise the class.
-
- Private variables (altered):
- __config ; Initialised with configuration variables.
- __output ; Set to the Output object.
+ Initialise the class.
+
+ Private variables (altered):
+ - __config ; Initialised with configuration variables.
+ - __output ; Set to the Output object.
+
+ @arg config: Configuration variables
+ @type config: class instance
+ @arg output: Output object
+ @type output: class instance
"""
self.__config = config
- self.__output = output
+ self.__output = output #: The Output object
#__init__
def __tempFileWrapper(self, func, handle) :
"""
- Make a temporary file, put the content of a stream in it and pass
- the filename to a general function. Return whatever this function
- returns.
+ Make a temporary file, put the content of a stream in it and pass
+ the filename to a general function. Return whatever this function
+ returns.
- Arguments:
- func ; A general function that needs a file name as argument.
- handle ; A stream.
+ @arg func: general function that needs a file name as argument
+ @type func: function
+ @arg handle: A stream
+ @type handle: stream
- Returns:
- unknown ; The output of func().
+ @return: unknown; the output of func().
+ @rtype: ?
"""
# Generate an unique filename in the tempDir directory.
@@ -92,50 +105,19 @@ class File() :
return ret
#__tempFileWrapper
- def getMimeType(self, handle) :
- """
- Get the mime type of a stream by inspecting a fixed number of bytes.
- The stream is rewinded after use.
-
- Arguments:
- handle ; A handle to a stream.
-
- Private variables:
- __config ; The bufSize configuration variables.
-
- Returns:
- string ; The mime type of a file.
- """
-
- handle.seek(0)
- buf = handle.read(self.__config.bufSize)
-
- MagicInstance = magic.open(magic.MAGIC_MIME)
- MagicInstance.load()
- mimeType = MagicInstance.buffer(buf).split(';')[0]
- MagicInstance.close()
- MagicInstance = magic.open(magic.MAGIC_NONE)
- MagicInstance.load()
- description = MagicInstance.buffer(buf)
- del MagicInstance
- handle.seek(0)
-
- return mimeType, description
- #getMimeType
-
def __parseCsvFile(self, handle) :
"""
- Parse a CSV file.
- The stream is not rewinded after use.
+ Parse a CSV file.
+ The stream is not rewinded after use.
- Arguments:
- handle ; A handle to a stream.
+ Private variables:
+ - __config ; The bufSize configuration variables.
- Private variables:
- __config ; The bufSize configuration variables.
+ @arg handle: A handle to a stream
+ @type handle: stream
- Returns:
- list ; A list of lists.
+ @return: list of lists
+ @rtype: list
"""
handle.seek(0)
@@ -164,14 +146,14 @@ class File() :
def __parseXlsFile(self, handle) :
"""
- Parse an Excel file.
- The stream is not rewinded after use.
+ Parse an Excel file.
+ The stream is not rewinded after use.
- Arguments:
- handle ; A handle to a stream.
+ @arg handle: A handle to a stream
+ @type handle: stream
- Returns:
- list ; A list of lists.
+ @return: A list of lists
+ @rtype: list
"""
workBook = self.__tempFileWrapper(xlrd.open_workbook, handle)
@@ -196,15 +178,14 @@ class File() :
def __parseOdsFile(self, handle) :
"""
- Parse an OpenDocument Spreadsheet file.
- The stream is not rewinded after use.
-
- Arguments:
- handle ; A handle to a stream.
+ Parse an OpenDocument Spreadsheet file.
+ The stream is not rewinded after use.
- Returns:
- list ; A list of lists.
+ @arg handle: A handle to a stream
+ @type handle: stream
+ @return: A list of lists
+ @rtype: list
"""
#zipFile = self.__tempFileWrapper(zipfile.ZipFile, handle)
@@ -229,20 +210,22 @@ class File() :
def __checkBatchFormat(self, job) :
"""
- Check if a job is of the correct format.
- - Each row should consist of three elements.
- - The first and the last element should be non-empty.
- - The first line should be the header defined in the config file.
+ Check if a job is of the correct format.
+ - Each row should consist of three elements.
+ - The first and the last element should be non-empty.
+ - The first line should be the header defined in the config file.
- Arguments:
- job ; list of lists.
+ Private variables:
+ - __config ; The header configuration variable.
+
+ @todo: Add more new style old style logic
+ @todo: if not inputl: try to make something out of it
- Private variables:
- __config ; The header configuration variable.
+ @arg job: list of lists
+ @type job: list
- Returns:
- list ; A sanitised list of lists (without a header or empty
- lines).
+ @return: A sanitised list of lists (without a header or empty lines)
+ @rtype: list
"""
#store original line numbers line 1 = job[0]
jobl = [(l+1, row) for l, row in enumerate(job)]
@@ -339,16 +322,48 @@ class File() :
return None
#__checkBatchFormat
+ def getMimeType(self, handle) :
+ """
+ Get the mime type of a stream by inspecting a fixed number of bytes.
+ The stream is rewinded after use.
+
+ Private variables:
+ - __config: The bufSize configuration variables.
+
+ @arg handle: A handle to a stream
+ @type handle: stream
+
+ @return: The mime type of a file
+ @rtype: string
+ """
+
+ handle.seek(0)
+ buf = handle.read(self.__config.bufSize) #: The bufSize configuration variables.
+
+
+ MagicInstance = magic.open(magic.MAGIC_MIME)
+ MagicInstance.load()
+ mimeType = MagicInstance.buffer(buf).split(';')[0]
+ MagicInstance.close()
+ MagicInstance = magic.open(magic.MAGIC_NONE)
+ MagicInstance.load()
+ description = MagicInstance.buffer(buf)
+ del MagicInstance
+ handle.seek(0)
+
+ return mimeType, description
+ #getMimeType
+
def parseFileRaw(self, handle) :
"""
- Check which format a stream has and parse it with the appropriate
- parser if the stream is recognised.
+ Check which format a stream has and parse it with the appropriate
+ parser if the stream is recognised.
- Arguments:
- handle ; A handle to a stream.
+ @arg handle: A handle to a stream
+ @type handle: stream
- Returns:
- list ; A list of lists, None if an error occured.
+ @return: A list of lists, None if an error occured
+ @rtype: list
"""
mimeType = self.getMimeType(handle)
@@ -365,15 +380,15 @@ class File() :
def parseBatchFile(self, handle) :
"""
- Check which format a stream has and parse it with the appropriate
- parser if the stream is recognised.
+ Check which format a stream has and parse it with the appropriate
+ parser if the stream is recognised.
- Arguments:
- handle ; A handle to a stream.
+ @arg handle: A handle to a stream
+ @type handle: stream
- Returns:
- list ; A sanitised list of lists (without a header or empty
- lines), or None if an error occured.
+ @return: A sanitised list of lists (without a header or empty lines),
+ or None if an error occured
+ @rtype: list
"""
job = self.parseFileRaw(handle)
@@ -384,8 +399,20 @@ class File() :
#File
def makeList(l, maxlen=10):
+ """
+ Converts a list of lines to a string to be used in output messages for
+ incompatible fields.
+
+ @arg l: list of lines
+ @type l: list
+ @arg maxlen: maximum length of the string you want to return
+ @type maxlen: integer
+ @return: a list converted to a string with comma's and spaces
+ @rtype: string
+ """
ret = ", ".join(str(i) for i in l[:maxlen])
if len(l)>maxlen:
return ret+", ..."
else:
return ret
+#makeList
\ No newline at end of file
diff --git a/src/Modules/GBparser.py b/src/Modules/GBparser.py
index 8751df4fd5e97d9991034e8c1f5f179a5a399fa7..75f82e00535363f0b9a85eb728fc3c0a4fbb7853 100644
--- a/src/Modules/GBparser.py
+++ b/src/Modules/GBparser.py
@@ -1,19 +1,48 @@
-from Bio import SeqIO, Entrez # read()
-import bz2 # BZ2Compressor(), BZ2File()
-from GenRecord import PList, Locus, Gene, Record, GenRecord
-import Db
+#!/usr/bin/python
"""
- Module contains one public function createGBRecord which returns a
- mutalyzer GenRecord.Record populated with data from a GenBank file.
+Module contains one public function createGBRecord which returns a
+mutalyzer GenRecord. Record populated with data from a GenBank file.
+
+@requires: bz2
+@requires: Db
+@requires: Bio.SeqIO
+@requires: Bio.Entrez
+@requires: GenRecord.PList
+@requires: GenRecord.Locus
+@requires: GenRecord.Gene
+@requires: GenRecord.Record
+@requires: GenRecord.GenRecord
"""
+import bz2 # BZ2Compressor(), BZ2File()
+import Db
+
+from Bio import SeqIO, Entrez # read()
+from GenRecord import PList, Locus, Gene, Record, GenRecord
+
class tempGene() :
"""
+ Container class for a given gene name.
+
+ Special methods:
+ - __init__(name) ; Initialise the class.
+
+ Public variables:
+ - rnaList ; List of splice sites.
+ - cdsList ; CDS list (including internal splice sites).
"""
def __init__(self, name) :
"""
+ Initialise the class for a given gene name.
+
+ Public variables:
+ - rnaList ; List of splice sites.
+ - cdsList ; CDS list (including internal splice sites).
+
+ @arg name: Gene name
+ @type name: string
"""
self.name = name
@@ -24,10 +53,20 @@ class tempGene() :
class GBparser() :
"""
+ @todo: documentation
"""
def __init__(self) :
"""
+ Initialise the class
+
+ Public variables:
+ - config ; Config object.
+
+ Private variables:
+ - __database ; Db.Cache object
+
+ @requires: Config
"""
import Config
@@ -38,13 +77,13 @@ class GBparser() :
def __location2pos(self, location) :
"""
- Convert a location object to a tuple of integers.
+ Convert a location object to a tuple of integers.
- Arguments:
- location ; A location object (see the BioPython documentation).
+ @arg location: A location object (see the BioPython documentation)
+ @type location: location object
- Returns:
- List ; A tuple of integers.
+ @return: A tuple of integers
+ @rtype: list
"""
ret = []
@@ -62,14 +101,13 @@ class GBparser() :
def __locationList2posList(self, locationList) :
"""
- Convert a list of locations to a list of integers.
+ Convert a list of locations to a list of integers.
- Arguments:
- locationList ; A list of locations
- (see the BioPython documentation).
+ @arg locationList: A list of locations (see the BioPython documentation)
+ @type locationList: list (location objects)
- Returns:
- List ; A list (of even length) of integers.
+ @return: A list (of even length) of integers
+ @rtype: list (integers)
"""
ret = []
@@ -96,18 +134,17 @@ class GBparser() :
def __transcriptToProtein(self, transcriptAcc) :
"""
- Try to find the protein linked to a transcript id.
+ Try to find the protein linked to a transcript id.
- First look in our database, if a link can not be found, try to
- retrieve it via the NCBI. Store the result in our database.
+ First look in our database, if a link can not be found, try to
+ retrieve it via the NCBI. Store the result in our database.
- Arguments:
- transcriptAcc ; Accession number of the transcript for which we
- want to find the protein.
-
- Returns:
- string ; Accession number of a protein or None if nothing can
- be found.
+ @arg transcriptAcc: Accession number of the transcript for which we
+ want to find the protein
+ @type transcriptAcc: string
+
+ @return: Accession number of a protein or None if nothing can be found
+ @rtype: string
"""
proteinAcc = self.__database.getProtAcc(transcriptAcc)
@@ -142,19 +179,19 @@ class GBparser() :
def __findMismatch(self, productList, direction) :
"""
- Find the index of the first or last word that distinguishes one
- sentence from an other.
-
- If direction equals 1, search for the first word.
- If direction equals -1, search for the last word.
-
- Arguments:
- productList ; A list of sentences.
- direction ; The direction in which to search.
-
- Returns:
- integer ; The index of the word where sentences start to
- differ.
+ Find the index of the first or last word that distinguishes one
+ sentence from an other.
+
+ If direction equals 1, search for the first word.
+ If direction equals -1, search for the last word.
+
+ @arg productList: A list of sentences
+ @type productList: list of strings
+ @arg direction: The direction in which to search
+ @type direction: integer (1 or -1)
+
+ @return: The index of the word where sentences start to differ
+ @rtype: integer
"""
i = 0
@@ -174,13 +211,13 @@ class GBparser() :
def __tagByDict(self, locus, key) :
"""
- Transfer a variable in the qualifiers dictionary to the locus
- object. If the variable does not exist, set it to the empty string.
+ Transfer a variable in the qualifiers dictionary to the locus
+ object. If the variable does not exist, set it to the empty string.
- Arguments:
- locus ; The locus object on which the transfer should be
- performed.
- key ; The name of the variable that should be transferred.
+ @arg locus: The locus object on which the transfer should be performed
+ @type locus: locus object
+ @arg key: The name of the variable that should be transferred
+ @type key: string
"""
if locus.qualifiers.has_key(key) :
@@ -191,14 +228,14 @@ class GBparser() :
def __tagLocus(self, locusList) :
"""
- Enrich a list of locus objects (mRNA or CDS) with information used
- for linking (locus_tag, proteinLink and productTag). Also
- transfer the variables transcript_id, protein_id, gene and product
- to each of the locus objects. If these variables do not exist, set
- them to the empty string.
-
- Arguments:
- locusList ; A list of locus objects.
+ Enrich a list of locus objects (mRNA or CDS) with information used
+ for linking (locus_tag, proteinLink and productTag). Also
+ transfer the variables transcript_id, protein_id, gene and product
+ to each of the locus objects. If these variables do not exist, set
+ them to the empty string.
+
+ @arg locusList: A list of locus objects
+ @type locusList: list
"""
productList = []
@@ -247,12 +284,13 @@ class GBparser() :
def __checkTags(self, locusList, tagName) :
"""
- Check whether all tags in a locus list are unique. Prune all the
- non unique tags.
+ Check whether all tags in a locus list are unique. Prune all the
+ non unique tags.
- Arguments:
- locusList ; A list of loci.
- tagName ; Name of the tag to be checked.
+ @arg locusList: A list of loci
+ @type locusList: list
+ @arg tagName: Name of the tag to be checked
+ @type tagName: string
"""
tags = []
@@ -275,17 +313,19 @@ class GBparser() :
def __matchByRange(self, mrna, cds) :
"""
- Match the mRNA list to the CDS list.
-
- Arguments:
- mrnaList ; List of splice sites.
- cdsList ; CDS list (including internal splice sites).
-
- Returns:
- integer ; -1 : False.
- 0 : Don't know.
- 1 : Maybe true.
- 2 : Probably true.
+ Match the mRNA list to the CDS list.
+
+ @arg mrna: List of splice sites
+ @type mrna: list
+ @arg cds: CDS list (including internal splice sites)
+ @type cds: list
+
+ @return:
+ - E{-}1 : False
+ - 0 : Don't know
+ - 1 : Maybe true
+ - 2 : Probably true
+ @rtype: integer
"""
if not cds or not mrna :
@@ -316,26 +356,29 @@ class GBparser() :
def link(self, rnaList, cdsList) :
"""
- Link mRNA loci to CDS loci (all belonging to one gene).
-
- First of all, the range of the CDS must be a sub range of that of
- the mRNA. If this is true, then we try to link both loci. The first
- method is by looking at the locus_tag, if this fails, we try to
- match the proteinLink tags, if this also fails, we try the
- productTag.
- If no link could be found, but there is only one possibility left,
- the loci are linked too.
- The method that was used to link the loci, is put in the linkmethod
- variable of the transcript locus. The link variable of the
- transcript locus is a pointer to the CDS locus. Furthermore, the
- linked variable of the CDS locus is set to indicate that this locus
- is no longer available for linking.
-
- Available link methods are: locus, protein, product and exhaustion.
-
- Arguments:
- rnaList ; A list of mRNA loci.
- cdsList ; A list of CDS loci.
+ Link mRNA loci to CDS loci (all belonging to one gene).
+
+ First of all, the range of the CDS must be a subrange of that of
+ the mRNA. If this is true, then we try to link both loci. The first
+ method is by looking at the locus_tag, if this fails, we try to
+ match the proteinLink tags, if this also fails, we try the
+ productTag.
+
+ If no link could be found, but there is only one possibility left,
+ the loci are linked too.
+
+ The method that was used to link the loci, is put in the linkmethod
+ variable of the transcript locus. The link variable of the
+ transcript locus is a pointer to the CDS locus. Furthermore, the
+ linked variable of the CDS locus is set to indicate that this locus
+ is no longer available for linking.
+
+ Available link methods are: locus, protein, product and exhaustion.
+
+ @arg rnaList: A list of mRNA loci
+ @type rnaList: list
+ @arg cdsList: A list of CDS loci
+ @type cdsList: list
"""
# Enrich the lists with as much information we can find.
@@ -407,11 +450,11 @@ class GBparser() :
"""
Create a GenRecord.Record from a GenBank file
- Arguments:
- filename ; The full path to the compresed GenBank file
+ @arg filename: The full path to the compressed GenBank file
+ @type filename: string
- Returns:
- record ; A GenRecord.Record instance
+ @return: A GenRecord.Record instance
+ @rtype: object (record)
"""
# first create an intermediate genbank record with BioPython
diff --git a/src/Modules/GenRecord.py b/src/Modules/GenRecord.py
index 9e942d3e838d97e0ef2f7e58990d3d5d35f555df..4dc7ff325c41182549da39bf5f56ea70242f590d 100644
--- a/src/Modules/GenRecord.py
+++ b/src/Modules/GenRecord.py
@@ -1,50 +1,55 @@
#!/usr/bin/python
+"""
+Module to convert a GenBank record to a nested dictionary consisting of
+a list of genes, which itself consists of a list of loci. This structure
+makes it possible to iterate over genes and transcripts without having to
+search for them each time.
+
+@requires: Crossmap
+@requires: Bio
+@requires: Db
+"""
+# Public classes:
+# - PList ; Store a general location and a list of splice sites.
+# - Locus ; Store data about the mRNA and CDS splice sites.
+# - Gene ; Store a list of Locus objects and the orientation.
+# - Record ; Store a geneList and other additional information.
+# - GenRecord ; Convert a GenBank record to a nested dictionary.
+
+
import Crossmap
import Bio
import Db
-"""
- Module to convert a GenBank record to a nested dictionary consisting of
- a list of genes, which itself consists of a list of loci. This structure
- makes it possible to iterate over genes and transcripts without having to
- search for them each time.
-
- Public classes:
- PList ; Store a general location and a list of splice sites.
- Locus ; Store data about the mRNA and CDS splice sites.
- Gene ; Store a list of Locus objects and the orientation.
- Record ; Store a geneList and other additional information.
- GenRecord ; Convert a GenBank record to a nested dictionary.
-"""
class PList(object) :
"""
- A position list object, to store a general location and a list of
- specific splice sites (if available).
+ A position list object, to store a general location and a list of
+ specific splice sites (if available).
- These objects are used to describe either a list of mRNA splice sites
- or a list of CDS splice sites. These splice sites are stored in the
- list element. The location element is a fallback in case the splice
- sites are not available.
+ These objects are used to describe either a list of mRNA splice sites
+ or a list of CDS splice sites. These splice sites are stored in the
+ list element. The location element is a fallback in case the splice
+ sites are not available.
- Special methods:
- __init__() ; Initialise the class.
+ Special methods:
+ - __init__() ; Initialise the class.
- Public variables:
- location ; A tuple of integers between which the object resides.
- list ; A list (with an even amount of entries) of splice sites.
+ Public variables:
+ - location ; A tuple of integers between which the object resides.
+ - list ; A list (with an even amount of entries) of splice sites.
"""
def __init__(self) :
"""
- Initialise the class.
+ Initialise the class.
- Public variables (altered):
- location ; A tuple of integers between which the object
- resides.
- list ; A list (with an even amount of entries) of splice
- sites.
+ Public variables (altered):
+ - location ; A tuple of integers between which the object
+ resides.
+ - POSITIONlist ; A list (with an even amount of entries) of splice
+ sites.
"""
self.location = []
@@ -54,28 +59,31 @@ class PList(object) :
class Locus(object) :
"""
- A Locus object, to store data about the mRNA and CDS splice sites.
+ A Locus object, to store data about the mRNA and CDS splice sites.
- Special methods:
- __init__() ; Initialise the class.
+ Special methods:
+ - __init__() ; Initialise the class.
- Public variables:
- mRNA ; A position list object.
- CDS ; A position list object.
- exon ; A position list object.
+ Public variables:
+ - mRNA ; A position list object.
+ - CDS ; A position list object.
+ - exon ; A position list object.
"""
def __init__(self, name) :
"""
- Initialise the class.
+ Initialise the class.
- Public variables (altered):
- mRNA ; A position list object.
- CDS ; A position list object.
- location ;
- exon ; A position list object.
- txTable ; The translation table.
- CM ; A Crossmap object.
+ Public variables (altered):
+ - mRNA ; A position list object.
+ - CDS ; A position list object.
+ - location ;
+ - exon ; A position list object.
+ - txTable ; The translation table.
+ - CM ; A Crossmap object.
+
+ @arg name: identifier of the locus
+ @type name: string
"""
self.name = name
@@ -103,6 +111,10 @@ class Locus(object) :
def addToDescription(self, rawVariant) :
"""
+ Expands the DNA description with a new raw variant.
+
+ @arg rawVariant: description of a single mutation
+ @type rawVariant: string
"""
if self.description :
@@ -114,25 +126,32 @@ class Locus(object) :
class Gene(object) :
"""
- A Gene object, to store a list of Locus objects and the orientation of
- the gene.
+ A Gene object, to store a list of Locus objects and the orientation of
+ the gene.
- Special methods:
- __init__() ; Initialise the class.
+ Special methods:
+ - __init__() ; Initialise the class.
- Public variables:
- orientation ; The orientation of the gene: 1 = forward,
- -1 = reverse.
- list ; A list of Locus objects.
+ Public variables:
+ - orientation; The orientation of the gene: 1 = forward, -1 = reverse.
+ - TRANSCRIPTSlist; A list of Locus objects.
"""
def __init__(self, name) :
"""
- Initialise the class.
+ Initialise the class.
- Public variables (altered):
- orientation ; The orientation of the gene.
- list ; A list of Locus objects.
+ Public variables (altered):
+ - name
+ - orientation ; The orientation of the gene.
+ - transcriptList ; A list of transcripts
+ - location ;
+ - longName ;
+ Private variables (altered):
+ - __locusTag ;
+
+ @arg name: gene name
+ @type name: string
"""
self.name = name
@@ -145,6 +164,10 @@ class Gene(object) :
def newLocusTag(self) :
"""
+ Generates a new Locus tag.
+
+ @return: Locus tag
+ @rtype: integer (3 digits, if < 100 preceeded with 0's)
"""
self.__locusTag = "%03i" % (int(self.__locusTag) + 1)
@@ -154,6 +177,13 @@ class Gene(object) :
def findLocus(self, name) :
"""
+ Find a transcript, given its name.
+
+ @arg name: transcript variant number
+ @type name: string
+
+ @return: transcript
+ @rtype: object
"""
for i in self.transcriptList :
@@ -164,6 +194,10 @@ class Gene(object) :
def listLoci(self) :
"""
+ Provides a list of transcript variant numbers
+
+ @return: list of transcript variant numbers
+ @rtype: list
"""
ret = []
@@ -174,50 +208,57 @@ class Gene(object) :
def findLink(self, protAcc) :
"""
+ Look in the list of transcripts for a given protein accession number.
+
+ @arg protAcc: protein accession number
+ @type protAcc: string
+
+ @return: transcript
+ @rtype: object
"""
for i in self.transcriptList :
if i.link == protAcc :
return i
return None
- #findCDS
+ #findLink
#Gene
class Record(object) :
"""
- A Record object, to store a geneList and other additional
- information.
-
- Special methods:
- __init__() ; Initialise the class.
-
- Public variables:
- geneList ; List of Gene objects.
- mol_type ; Variable to indicate the sequence type (DNA, RNA, ...)
- organelle ; Variable to indicate whether the sequence is from the
- nucleus or from an onganelle (if so, also from which
- one).
- source ; A fake gene that can be used when no gene information
- is present.
+ A Record object, to store a geneList and other additional
+ information.
+
+ Special methods:
+ - __init__() ; Initialise the class.
+
+ Public variables:
+ - geneList ; List of Gene objects.
+ - mol_type ; Variable to indicate the sequence type (DNA, RNA, ...)
+ - organelle ; Variable to indicate whether the sequence is from the
+ nucleus or from an organelle (if so, also from which
+ one).
+ - source ; A fake gene that can be used when no gene information
+ is present.
"""
def __init__(self) :
"""
- Initialise the class.
+ Initialise the class.
- Public variables (altered):
- geneList ; List of Gene objects.
- molType ; Variable to indicate the sequence type (DNA, RNA,
- ...)
- seq ; The reference sequence
- mapping ; The mapping of the reference sequence to the genome
- include a list of differences between the sequences
- organelle ; Variable to indicate whether the sequence is from
- the nucleus or from an onganelle (if so, also from
- which one).
- source ; A fake gene that can be used when no gene
- information is present.
+ Public variables (altered):
+ - geneList ; List of Gene objects.
+ - molType ; Variable to indicate the sequence type (DNA, RNA,
+ ...)
+ - seq ; The reference sequence
+ - mapping ; The mapping of the reference sequence to the genome
+ include a list of differences between the sequences
+ - organelle ; Variable to indicate whether the sequence is from
+ the nucleus or from an organelle (if so, also from
+ which one).
+ - source ; A fake gene that can be used when no gene
+ information is present.
"""
self.geneList = []
@@ -237,6 +278,13 @@ class Record(object) :
def findGene(self, name) :
"""
+ Returns a Gene object, given its name.
+
+ @arg name: Gene name
+ @type name: string
+
+ @return: Gene object
+ @rtype: object
"""
for i in self.geneList :
@@ -247,6 +295,11 @@ class Record(object) :
def listGenes(self) :
"""
+ List the names of all genes found in this record.
+
+ @return: Genes list
+ @rtype: list
+
"""
ret = []
@@ -257,6 +310,10 @@ class Record(object) :
def addToDescription(self, rawVariant) :
"""
+ Expands the DNA description with a new raw variant.
+
+ @arg rawVariant: description of a single mutation
+ @type rawVariant: string
"""
if self.description :
@@ -267,6 +324,14 @@ class Record(object) :
def toChromPos(self, i) :
"""
+ Converts a g. position (relative to the start of the record) to a
+ chromosomal g. position
+
+ @arg i: g. position (relative to the start of the record)
+ @type i: integer
+
+ @return: chromosomal g. position
+ @rtype: integer
"""
if self.orientation == 1 :
@@ -276,6 +341,7 @@ class Record(object) :
def addToChromDescription(self, rawVariant) :
"""
+ @todo document me
"""
if not self.chromOffset :
@@ -290,14 +356,23 @@ class Record(object) :
class GenRecord() :
"""
- Convert a GenBank record to a nested dictionary.
+ Convert a GenBank record to a nested dictionary.
- Public methods:
- checkRecord() ; Check and repair self.record
+ Public methods:
+ - checkRecord() ; Check and repair self.record.
"""
def __init__(self, output, config) :
"""
+ Initialise the class.
+
+ Public variable:
+ - record ; A record object
+
+ @arg output: an output object
+ @type output: object
+ @arg config: a config object
+ @type config: object
"""
self.__output = output
@@ -307,6 +382,15 @@ class GenRecord() :
def __checkExonList(self, exonList, CDSpos) :
"""
+ @todo document me
+
+ @arg exonList: list of splice sites
+ @type exonList: list (object)
+ @arg CDSpos: location of the CDS
+ @type CDSpos: object
+
+ @return:
+ @rtype: boolean
"""
if not exonList :
@@ -332,6 +416,16 @@ class GenRecord() :
def __constructCDS(self, mRNA, CDSpos) :
"""
+ Construct a list of coordinates that contains CDS start and stop and
+ the internal splice sites.
+
+ @arg mRNA: mRNA positions/coordinates list
+ @type mRNA: list (integer)
+ @arg CDSpos: coding DNA positions/coordinates
+ @type CDSpos: list (integer)
+
+ @return: CDS positions plus internal splice sites
+ @rtype: list (integer)
"""
i = 1
@@ -352,6 +446,17 @@ class GenRecord() :
def __maybeInvert(self, gene, string) :
"""
+ Return the reverse-complement of a DNA sequence if the gene is in
+ the reverse orientation.
+
+ @arg gene: Gene
+ @type gene: object
+ @arg string: DNA sequence
+ @type string: string
+
+ @return: reverse-complement (if applicable), otherwise return the
+ original.
+ @rtype: string
"""
if gene.orientation == -1 :
@@ -361,9 +466,11 @@ class GenRecord() :
def checkRecord(self) :
"""
- Check if the record in self.record is compatible with mutalyzer
-
- update the mRNA PList with the exon and CDS data
+ Check if the record in self.record is compatible with mutalyzer.
+ Update the mRNA PList with the exon and CDS data.
+
+ @todo: This function should really check the record for minimal
+ requirements
"""
#TODO: This function should really check
@@ -479,6 +586,21 @@ class GenRecord() :
def name(self, start_g, stop_g, varType, arg1, arg2, roll) :
"""
+ Generate variant descriptions for all genes, transcripts, etc.
+
+ @arg start_g: start position
+ @type start_g: integer
+ @arg stop_g: stop position
+ @type stop_g: integer
+ @arg varType: variant type
+ @type varType: string
+ @arg arg1: argument 1 of a raw variant
+ @type arg1: string
+ @arg arg2: argument 2 of a raw variant
+ @type arg2: string
+ @arg roll: ???
+ @type roll: tuple (integer, integer)
+
"""
forwardStart = start_g
@@ -558,6 +680,19 @@ class GenRecord() :
#name
def checkIntron(self, gene, transcript, position) :
+ """
+ Checks if a position is on or near a splice site
+
+ @arg gene: Gene
+ @type gene: object
+ @arg transcript: transcript
+ @type transcript: object
+ @arg position: g. position
+ @type position: integer
+
+ @return:
+ @todo: Also check a range properly.
+ """
# TODO Also check a range properly.
intronPos = abs(transcript.CM.g2x(position)[1])
if intronPos :
diff --git a/src/Modules/LRGparser.py b/src/Modules/LRGparser.py
index b607e87c1492b89b17aa07fa6638e2d04ca31e90..43fc5954a556e28dd47bb5e8a42907021fd2ae0a 100644
--- a/src/Modules/LRGparser.py
+++ b/src/Modules/LRGparser.py
@@ -1,21 +1,27 @@
+#!/usr/bin/python
+
"""
- Module contains one public function createLrgRecord which returns a
- mutalyzer GenRecord.Record populated with data from a LRG file.
-
- A LRG file is an XML formatted file and consists of a fixed and
- updatable section. The fixed section contains a DNA sequence
- and for that sequence a number of transcripts.
-
- The updatable region could contain all sorts of annotation for the
- sequence and transcripts. It can also contain additional (partial)
- transcripts and mapping information.
-
- This module is based on the result of the minidom xml parser.
- NOTE:
- A strong alternative to the minidom parser would be ElementTree
- http://docs.python.org/library/xml.etree.elementtree.html
- which is added in python2.5
- Its main strengths are speed and readability [pythonesque]
+Module contains one public function createLrgRecord which returns a
+mutalyzer GenRecord.Record populated with data from a LRG file.
+
+A LRG file is an XML formatted file and consists of a fixed and
+updatable section. The fixed section contains a DNA sequence
+and for that sequence a number of transcripts.
+
+The updatable region could contain all sorts of annotation for the
+sequence and transcripts. It can also contain additional (partial)
+transcripts and mapping information.
+
+This module is based on the result of the minidom xml parser.
+
+NOTE: A strong alternative to the minidom parser would be ElementTree which is
+added in python2.5. Its main strengths are speed and readability [pythonesque].
+(http://docs.python.org/library/xml.etree.elementtree.html)
+
+@requires: xml.dom.minidom
+@requires: xml.parsers.expat.ExpatError
+@requires: Bio.Seq.Seq
+@requires: Bio.Alphabet.IUPAC
"""
from Bio.Seq import Seq
@@ -28,8 +34,15 @@ __all__ = ["createLrgRecord"] # Only import createLrgRecord from this module
def __debugParsedData(title, data):
"""
- Output additional data to stdout. Used for debugging the
- intermediate format used while parsing a LRG file.
+ Output additional data to stdout. Used for debugging the
+ intermediate format used while parsing a LRG file.
+
+ @requires: pprint
+
+ @arg title:
+ @type title: string
+ @arg data: minidom object
+ @type data: object
"""
import pprint #Only imported when the debug flag is set
print "#"*79+"\nDEBUG: Start of "+title+"\n"+"#"*79
@@ -39,15 +52,15 @@ def __debugParsedData(title, data):
def _getContent(data, refname):
"""
- Return string-content of an XML textnode.
+ Return string-content of an XML textnode.
- Arguments:
- data ; a minidom object
- refname ; the name of a member of the minidom object
+ @arg data: a minidom object
+ @type data: object
+ @arg refname: the name of a member of the minidom object
+ @type refname: string
- Returns:
- String ; The UTF-8 content of the textnode
- or an emtpy string
+ @return: The UTF-8 content of the textnode or an emtpy string
+ @rtype: string
"""
temp = data.getElementsByTagName(refname)
if temp:
@@ -58,15 +71,15 @@ def _getContent(data, refname):
def _attr2dict(attr):
"""
- Create a dictionary from the attributes of an XML node
+ Create a dictionary from the attributes of an XML node
- Arguments:
- attr ; a minidom node
+ @arg attr: a minidom node
+ @type attr: object
- Returns:
- Dict ; A dictionary with pairing of node-attribute names
- and values. Integer string values are converted to
- integers. String values are converted to UTF-8
+ @return: A dictionary with pairing of node-attribute names and values.
+ Integer string values are converted to integers. String values are converted
+ to UTF-8
+ @rtype: dictionary
"""
ret = {}
for key, value in attr.items():
@@ -77,13 +90,13 @@ def _attr2dict(attr):
def createLrgRecord(data):
"""
- Create a GenRecord.Record of a LRG <xml> formatted string
+ Create a GenRecord.Record of a LRG <xml> formatted string.
- Input:
- data ; Content of LRG file [String]
+ @arg data: Content of LRG file
+ @type data: string
- Output
- record ; GenRecord.Record instance
+ @return: GenRecord.Record instance
+ @rtype: object
"""
# Initiate the GenRecord.Record
record = GenRecord.Record()
@@ -185,14 +198,14 @@ def createLrgRecord(data):
def genesFromUpdatable(updParsed):
"""
- populate GenRecord.Gene instances with updatable LRG node data
+ Populate GenRecord.Gene instances with updatable LRG node data.
- Input:
- updParsed ; Intermediate nested dict of updatable section
+ @arg updParsed: Intermediate nested dict of updatable section
+ @type updParsed: dictionary
- Output
- genes ; List of GenRecord.Gene instances, populated with
- the content of the updatable section
+ @return: genes ; List of GenRecord.Gene instances, populated with the
+ content of the updatable section
+ @rtype: list
"""
genes = []
for geneSymbol, geneData in updParsed["NCBI"].items():
@@ -216,14 +229,14 @@ def genesFromUpdatable(updParsed):
def transcriptsFromParsed(parsedData):
"""
- populate GenRecord.Locus instances with updatable LRG node data
+ Populate GenRecord.Locus instances with updatable LRG node data
- Input:
- parsedData ; Dict of transcript data. See getFeaturesAnnotation
+ @arg parsedData: Dictionary of transcript data. See getFeaturesAnnotation
+ @type parsedData: dictionary
- Output
- transcripts ; List of GenRecord.Locus instances, populated with
- the content of the parsed Data
+ @return: transcripts ; List of GenRecord.Locus instances, populated with the
+ content of the parsed Data
+ @rtype: list
"""
transcripts = []
@@ -245,16 +258,18 @@ def transcriptsFromParsed(parsedData):
def _emptyTranscripts(data):
#TODO: This function can be moved to the GenRecord.checkRecord method
"""
- populate a GenRecord.Locus instance with minimal data to make the
- gene compatible with mutalyzer. Data abstracted from the gene.
-
- Input:
- data ; Data from the gene which is used to populate
- the create a minimal GenRecord.Locus instance.
-
- Output
- list ; List with a single bogus GenRecord.Locus instance,
- in which location and mRNA are copied from the gene.
+ Populate a GenRecord.Locus instance with minimal data to make the
+ gene compatible with mutalyzer. Data abstracted from the gene.
+
+ @todo: This function can be moved to the GenRecord.checkRecord method.
+
+ @arg data: Data from the gene which is used to populate the create a minimal
+ GenRecord.Locus instance
+ @type data: dictionary
+
+ @return: List with a single bogus GenRecord.Locus instance, in which
+ location and mRNA are copied from the gene
+ @rtype: list
"""
transcript = GenRecord.Locus('')
transcript.molType = 'n'
@@ -268,15 +283,16 @@ def _emptyTranscripts(data):
def _transcriptPopulator(trName, trData):
"""
- populate GenRecord.Locus instance with updatable LRG node data
-
- Input:
- trName ; Name of the transcript.
- trData ; Data associated with the transcript.
-
- Output
- transcript ; GenRecord.Locus instance, populated with
- the content of the parsed Data
+ Populate GenRecord.Locus instance with updatable LRG node data.
+
+ @arg trName: Name of the transcript
+ @type trName: string
+ @arg trData: Data associated with the transcript
+ @type trData: dictionary
+
+ @return: transcript ; GenRecord.Locus instance, populated with the content
+ of the parsed Data
+ @rtype: object
"""
transcript = GenRecord.Locus(trName)
transcript.transcriptProduct = trData.get("transLongName")
@@ -304,15 +320,16 @@ def _transcriptPopulator(trName, trData):
def getMapping(rawMapData):
"""
- Collect all necessary info to map the current LRG sequence to the
- genomic reference supplied by the file.
+ Collect all necessary info to map the current LRG sequence to the
+ genomic reference supplied by the file.
- Input:
- rawMapData ; A list of dictionaries with the raw mapping info
+ @arg rawMapData: A list of dictionaries with the raw mapping info
+ @type rawMapData: list
- Output
- dict ;
+ @return: dictionary with the mapping info
+ @rtype: dictionary
"""
+
mapp, span, diffs = rawMapData
ret = { "assembly": mapp.get("assembly"), # Assembly Reference
"chr_name": mapp.get("chr_name"), # Chromosome name
@@ -329,19 +346,18 @@ def getMapping(rawMapData):
def parseUpdatable(data):
"""
- Mediator function which transforms the minidom object to a nested dict
- and filters information needed to construct the GenRecord.Record.
+ Mediator function which transforms the minidom object to a nested dict
+ and filters information needed to construct the GenRecord.Record.
- NOTE: an xml node has attributes and elements, this function squashes
- this ambiguity and collects only the attributes and elements of
- interest
+ NOTE: an xml node has attributes and elements, this function squashes this
+ ambiguity and collects only the attributes and elements of interest
- Input:
- data ; The LRG file's updatable section node
+ @arg data: The LRG file's updatable section node
+ @type data: dictionary
- Output
- nested dict ; Contains the fields of interest of the LRG
- NCBI and Ensembl sections of the updatable node.
+ @return: Contains the fields of interest of the LRG NCBI and Ensembl
+ sections of the updatable node
+ @rtype: dictionary
"""
ret = {"LRG":{}, "NCBI":{}, "Ensembl":{}}
annotation_nodes = data.getElementsByTagName("annotation_set")
@@ -362,16 +378,16 @@ def parseUpdatable(data):
def getLrgAnnotation(data):
"""
- Retrieves three parts of the LRG annotation:
- - the mapping of this LRG file to a genomic reference
- - a diference list between the LRG sequence and the ref seq
- - the genename of the main gene annotated by this LRG file
+ Retrieves three parts of the LRG annotation:
+ - the mapping of this LRG file to a genomic reference
+ - a diference list between the LRG sequence and the ref seq
+ - the genename of the main gene annotated by this LRG file
- Input:
- data ; updatable section -> Annotations -> LRG node
+ @arg data: updatable section -> Annotations -> LRG node
+ @type data: dictionary
- Output
- dict ; Contains the mapping [+ opt. diffs] and the genename
+ @return: Contains the mapping [+ opt. diffs] and the genename
+ @rtype: dictionary
"""
ret = {"mapping": (), "genename":""}
# Get the mapping
@@ -396,38 +412,38 @@ def getLrgAnnotation(data):
def getFeaturesAnnotation(data):
"""
- Retrieves feature annotations from NCBI & Ensembl nodes.
- - List of genes
- - List of transcripts per gene
- - Potential Product of a transcript
-
- If a transcript can not be linked to a transcript from the fixed
- section it is stored in the noFixedId list.
-
- NOTE: an xml node has attributes and elements, this function squashes
- this ambiguity and collects only the attributes and elements of
- interest
- Input:
- data ; updatable section -> Annotations -> NCBI | Ensembl
-
- Output
- nested dict ; toplevel contains the genesymbols as keys e.g:
- COL1A1 :
- geneAttr : {}
- geneLongName : ""
- transcripts : {}
- geneAttr contains the start, end and strand info
- transcripts contains a list of transcripts that
- could not be linked to the fixed section AND
- it contains each linked transcript with the
- locustag as key e.g:
- 1 :
- transAttr : {}
- transLongName : ""
- proteinAttr : {}
- proteinLongName : ""
- transAttr & proteinAttr contain
- reference, start and end info
+ Retrieves feature annotations from NCBI & Ensembl nodes.
+ - List of genes
+ - List of transcripts per gene
+ - Potential Product of a transcript
+
+ If a transcript can not be linked to a transcript from the fixed section it
+ is stored in the noFixedId list.
+
+ NOTE: an xml node has attributes and elements, this function squashes this
+ ambiguity and collects only the attributes and elements of interest
+
+ @todo: check documentation
+
+ @arg data: updatable section -> Annotations -> NCBI | Ensembl
+ @type data: dictionary
+
+ @return: nested dict ; toplevel contains the genesymbols as keys e.g:
+ - COL1A1 :
+ - geneAttr : {}
+ - geneLongName : ""
+ - transcripts : {}
+ - geneAttr contains the start, end and strand info
+ - transcripts contains a list of transcripts that could not be linked to
+ the fixed section AND it contains each linked transcript with the
+ locustag as key e.g:
+ - 1 :
+ - transAttr : {}
+ - transLongName : ""
+ - proteinAttr : {}
+ - proteinLongName : ""
+ - transAttr & proteinAttr contain reference, start and end info
+ @rtype: dictionary
"""
ret = {} # Get annotation per gene symbol {"COL1A1":{}}
#Check if features exists
diff --git a/src/Modules/Mapper.py b/src/Modules/Mapper.py
index 9b769d1030a7dadd77fad312e8d9b2783514c430..863f7dd06e8041fb2dabec301f285fc6df58329c 100644
--- a/src/Modules/Mapper.py
+++ b/src/Modules/Mapper.py
@@ -1,21 +1,33 @@
#!/usr/bin/python
"""
- Search for an NM number in the MySQL database, if the version number
- matches, get the start and end positions in a variant and translate these
- positions to g. notation if the variant is in c. notation and vice versa.
+Search for an NM number in the MySQL database, if the version number
+matches, get the start and end positions in a variant. Translate these
+positions to I{g.} notation if the variant is in I{c.} notation or vice versa.
- - If no end position is present, the start position is assumed to be the
- end position.
+ - If no end position is present, the start position is assumed to be the end
+ position.
- If the version number is not found in the database, an error message is
- generated and a suggestion for an other version is given.
+ generated and a suggestion for an other version is given.
- If the reference sequence is not found at all, an error is returned.
- - If no variant is present, the transcription start and end and CDS end
- in c. notation is returned.
+ - If no variant is present, the transcription start and end and CDS end in
+ I{c.} notation is returned.
- If the variant is not accepted by the nomenclature parser, a parse error
- will be printed.
-
+ will be printed.
+
+@requires: sys
+@requires: Modules.Config
+@requires: Modules.Db
+@requires: Modules.Crossmap
+@requires: Modules.Parser
+@requires: Modules.Output
+@requires: Modules.Serializers.SoapMessage
+@requires: Modules.Serializers.Mapping
+@requires: Modules.Serializers.Transcript
+@requires: Bio.Seq.reverse_complement
+@requires: collections.defaultdict
"""
+
import sys # argv
from Modules import Config # Config()
from Modules import Db # Db(), get_NM_version(), get_NM_info()
@@ -30,11 +42,13 @@ from collections import defaultdict
def _sl2il(l) :
"""
- Convert a list of strings to a list of integers.
+ Convert a list of strings to a list of integers.
- Arguments: l ; A list of strings.
+ @arg l: A list of strings
+ @type l: list
- Returns: list ; A list of integers.
+ @returns: A list of integers
+ @rtype: list
"""
return [int(s) for s in l]
@@ -42,18 +56,20 @@ def _sl2il(l) :
def _getcoords(C, Loc, Type) :
"""
- Return main, offset and g positions given either a position in
- c. or in g. notation.
-
- Arguments:
- C ; A crossmapper.
- Loc ; Either a location in g. or c. notation.
- Type ; The reference type.
- Returns:
- triple:
- 0 ; Main coordinate in c. notation.
- 1 ; Offset coordinate in c. notation.
- 2 ; Position in g. notation.
+ Return main, offset and g positions given either a position in
+ I{c.} or in I{g.} notation.
+
+ @arg C: A crossmapper
+ @type C: object
+ @arg Loc: A location in either I{g.} or I{c.} notation
+ @type Loc: object
+ @arg Type: The reference type
+ @type Type: string
+ @returns: triple:
+ 0. Main coordinate in I{c.} notation
+ 1. Offset coordinate in I{c.} notation
+ 2. Position in I{g.} notation
+ @rtype: triple (integer, integer, integer)
"""
if Type == 'c' :
@@ -69,11 +85,24 @@ def _getcoords(C, Loc, Type) :
return (main, offset, g)
#__getcoords
-class Converter(object):
+class Converter(object) :
"""
- Converter object docstring
+ Converter object docstring
"""
- def __init__(self, build, C, O):
+
+ def __init__(self, build, C, O) :
+ """
+ Initialise the class.
+
+ @arg build: the genome build version of the organism (e.g. hg19 for
+ human genome build version 19)
+ @type build: string
+ @arg C: crossmapper object
+ @type C: object
+ @arg O: output object
+ @type O: object
+ """
+
self.build = None
self.__output = O
self.__config = C
@@ -83,40 +112,79 @@ class Converter(object):
self.parseTree = None
self.crossmap = None
self.dbFields = {}
+ #__init__
+
+ def _changeBuild(self, build) :
+ """
+ @todo document me (figure out what is does)
+ Change the build if it different from the one previously set?????.
+
+ @arg build: the genome build version of the organism (e.g. hg19 for
+ human genome build version 19)
+ @type build: string
+ """
- def _changeBuild(self, build):
- if self.build != build:
+ if self.build != build :
self.crossmap = None
self.dbFields = {}
self.build = build
self.__database = Db.Mapping(build, C.Db)
+ #if
+ #_changeBuild
- def _reset(self):
+ def _reset(self) :
self.crossmap = None
self.dbFields = {}
+ #_reset
+
+ def _parseInput(self, variant) :
+ """
+ Parse a variant.
+
+ @arg variant: variant description
+ @type variant: string
+
+ @return: parsetree object
+ @rtype: object
+ """
- def _parseInput(self, variant):
P = Parser.Nomenclatureparser(self.__output)
parseTree = P.parse(variant)
- if not parseTree:
+ if not parseTree :
self.__output.addMessage(__file__, 4, "EPARSE",
"Could not parse the given variant")
return None
- if parseTree.SingleAlleleVarSet:
+ #if
+ if parseTree.SingleAlleleVarSet :
#Only simple mutations
self.__output.addMessage(__file__, 4, "EPARSE",
"Can not process multiple mutation variant")
return None
+ #if
if not parseTree.RefSeqAcc: #In case of LRG for example
self.__output.addMessage(__file__, 4, "EONLYGB",
"Currently we only support GenBank Records")
return None
+ #if
self.parseTree = parseTree
return parseTree
#_parseInput
- def _populateFields(self, Fields):
+ def _populateFields(self, Fields) :
#TODO: ADD Error Messages, unlikely that CDS info is missing
+ """
+ Create a Mutalyzer compatible exon list.
+
+ @todo: ADD Error Messages, unlikely that CDS info is missing.
+
+ @arg Fields: dictionary with exon start and end positions taken from the
+ MySQL database
+ @type Fields: dictionary
+
+ @return: Exon list
+ @rtype: list
+ """
+
Fields["exonStarts"] =\
_sl2il(Fields["exonStarts"].split(',')[:-1])
Fields["exonEnds"] =\
@@ -131,42 +199,66 @@ class Converter(object):
# Create Mutalyzer compatible exon list
Fields["exons"] = []
- for exon in zip(Fields["exonStarts"], Fields["exonEnds"]):
+ for exon in zip(Fields["exonStarts"], Fields["exonEnds"]) :
Fields["exons"].extend(exon)
self.dbFields = Fields
return Fields
+ #_populateFields
+
+ def _FieldsFromValues(self, values) :
+ """
+ Combines labels with the given values to a dictionary.
+ (zip returns a list of tuples, where the i-th tuple contains the i-th
+ element from each of the argument sequences or iterables.
+ dict(arg) creates a new data dictionary, with items taken from arg.)
+
+ @arg values: list of values take from the MySQL database
+ @type values: list
+
+ @return: dictionary with values taken from the MySQL database
+ @rtype: dictionary
+ """
- def _FieldsFromValues(self, values):
Fields = dict(zip(
("acc", "txStart", "txEnd", "cdsStart", "cdsEnd",
"exonStarts", "exonEnds", "geneName",
"chrom", "strand", "protAcc", "version"),
values))
return self._populateFields(Fields)
+ #_FieldsFromValues
+
+ def _FieldsFromDb(self, acc, version) :
+ """
+ Get data from database and populate dbFields dict.
+
+ @arg acc: NM_ accession number (without version)
+ @type acc: string
+ @arg version: version number
+ @type version: integer
+ """
- def _FieldsFromDb(self, acc, version):
- """Get data from database and populate dbFields dict"""
- if not version:
+ if not version :
version = 0
version = int(version)
versions = self.__database.get_NM_version(acc)
- if not versions:
+ if not versions :
self.__output.addMessage(__file__, 4, "EACCNOTINDB",
"The accession number: %s could not be "
"found in our database." % acc)
self.__output.addOutput("LOVDERR",
"Reference sequence not found.")
- return None #Excplicit return of None in case of error
- else:
- if version in versions:
+ return None #Explicit return of None in case of error
+ #if
+ else :
+ if version in versions :
Values = self.__database.getAllFields(acc, version)
return self._FieldsFromValues(Values)
-
- if not version:
+ #if
+ if not version :
self.__output.addMessage(__file__, 4, "ENOVERSION",
"Version number missing for %s" % acc)
- else:
+ else :
self.__output.addMessage(__file__, 4, "EACCNOTINDB",
"The accession number: %s version %s "
"could not be found in our database." %
@@ -186,18 +278,24 @@ class Converter(object):
# "Reference sequence version not found. "
# "Available: %s.%s" % (acc, sorted(versions)[-1]))
return None
+ #else
+ #_FieldsFromDb
def makeCrossmap(self) :
- ''' Build the crossmapper
+ """
+ Build the crossmapper.
+
+ @todo: ADD Error Messages
+
+ @return: Cross ; A Crossmap object
+ @rtype: object
+ """
- Returns:
- Cross ; A Crossmap object.
- '''
#TODO: ADD Error Messages
if not self.dbFields: return None
CDS = []
- if self.dbFields["cdsStart"] != self.dbFields["cdsEnd"]:
+ if self.dbFields["cdsStart"] != self.dbFields["cdsEnd"] :
#The counting from 0 conversion.
CDS = [self.dbFields["cdsStart"] + 1, self.dbFields["cdsEnd"]]
@@ -213,13 +311,14 @@ class Converter(object):
return self.crossmap
#makeCrossmap
- def _coreMapping(self):
- '''
- Build the Mapping ClassSerializer
+ def _coreMapping(self) :
+ """
+ Build the Mapping ClassSerializer.
+
+ @return: Mapping ; A ClassSerializer object
+ @rtype: object
+ """
- Returns:
- Mapping ; A ClassSerializer object.
- '''
Cross = self.makeCrossmap()
if not Cross :
return None
@@ -239,7 +338,7 @@ class Converter(object):
endmain, endoffset, end_g = \
_getcoords(Cross, mutation.EndLoc.PtLoc,
self.parseTree.RefType)
- else:
+ else :
end_g, endmain, endoffset = start_g, startmain, startoffset
# Assign these values to the Mapping ClassSerializer
@@ -253,32 +352,47 @@ class Converter(object):
V.mutationType = mutation.MutationType
return V
+ #_coreMapping
def giveInfo(self, accNo) :
- if '.' not in accNo:
+ """
+ Returns transcription start, transcription end and CDS stop, if
+ available.
+
+ @arg accNo: transcript (NM_) accession number (with or without version)
+ @type accNo: string
+
+ @return: transcription start, transcription end and CDS stop
+ @rtype: triple
+ """
+
+ if '.' not in accNo :
acc, ver = accNo, None
- else:
+ else :
acc, ver = accNo.split('.')
self._FieldsFromDb(acc, ver)
CM = self.makeCrossmap()
- if CM: return CM.info()
+ if CM :
+ return CM.info()
+ #giveInfo
- def mainTranscript(self, accNo):
+ def mainTranscript(self, accNo) :
"""
- One of the entry points (called by the HTML publisher).
+ One of the entry points (called by the HTML publisher).
- Arguments:
- acc ; The full NM accession number (including version).
+ @arg accNo: The full NM accession number (including version)
+ @type accNo: string
- Returns:
- T ; ClassSerializer object with the types trans_start,
- trans_stop and CDS_stop.
+ @return: T ; ClassSerializer object with the types trans_start,
+ trans_stop and CDS_stop
+ @rtype: object
"""
+
# Initiate ClassSerializer object
info = self.giveInfo(accNo)
T = Transcript()
- if info:
+ if info :
T.trans_start = info[0]
T.trans_stop = info[1]
T.CDS_stop = info[2]
@@ -287,10 +401,19 @@ class Converter(object):
def mainMapping(self, accNo, mutation) :
"""
- One of the entry points (called by the HTML publisher).
+ One of the entry points (called by the HTML publisher).
+
+ @arg accNo: transcript (NM_) accession number (with version?)
+ @type accNo: string
+ @arg mutation: the 'mutation' (e.g. c.123C>T)
+ @type mutation: string
+
+ @return: ClassSerializer object
+ @rtype: object
"""
+
variant = "%s:%s" % (accNo, mutation)
- if self._parseInput(variant):
+ if self._parseInput(variant) :
acc = self.parseTree.RefSeqAcc
version = self.parseTree.Version
self._FieldsFromDb(acc, version)
@@ -298,59 +421,69 @@ class Converter(object):
mapping = self._coreMapping()
soaperrors = self.__output.getSoapMessages()
- if mapping is None: # Something went wrong
+ if mapping is None : # Something went wrong
mapping = Mapping()
mapping.errorcode = len(soaperrors)
- else:
+ else :
mapping.errorcode = 0
mapping.messages = soaperrors
return mapping
-
#main_Mapping
def c2chrom(self, variant) :
"""
- Converts a complete HGVS c. notation into a chromosomal notation
-
- Arguments:
- variant ; The variant in HGVS c.notation.
+ Converts a complete HGVS I{c.} notation into a chromosomal notation.
- Returns:
- var_in_g ; The variant in HGVS g. notation (string).
+ @arg variant: The variant in HGVS I{c.} notation
+ @type variant: string
+ @return: var_in_g ; The variant in HGVS I{g.} notation
+ @rtype: string
"""
- if self._parseInput(variant):
+
+ if self._parseInput(variant) :
acc = self.parseTree.RefSeqAcc
version = self.parseTree.Version
self._FieldsFromDb(acc, version)
+ #if
M = self._coreMapping()
- if M is None: return None
+ if M is None :
+ return None
# construct the variant description
chromAcc = self.__database.chromAcc(self.dbFields["chrom"])
f_change = self._constructChange(False)
r_change = self._constructChange(True)
- if self.dbFields["strand"] == "+":
+ if self.dbFields["strand"] == "+" :
change = f_change
- else:
+ else :
change = r_change
- if M.start_g != M.end_g:
+ if M.start_g != M.end_g :
if self.dbFields["strand"] == '+' :
var_in_g = "g.%s_%s%s" % (M.start_g, M.end_g, change)
else :
var_in_g = "g.%s_%s%s" % (M.end_g, M.start_g, change)
+ #if
else :
var_in_g = "g.%s%s" % (M.start_g, change)
return "%s:%s" % (chromAcc, var_in_g)
- #cTog
+ #c2chrom
+
+ def correctChrVariant(self, variant) :
+ """
+ @arg variant:
+ @type variant: string
+
+ @return: variant ;
+ @rtype: string
+ """
- def correctChrVariant(self, variant):
#Pre split check
- if ':' not in variant:
+ if ':' not in variant :
self.__output.addMessage(__file__, 4, "EPARSE",
"The variant needs a colon")
return None
@@ -358,49 +491,63 @@ class Converter(object):
#Remove whitespace
variant = variant.replace(" ","")
- if variant.startswith("chr"):
+ if variant.startswith("chr") :
preco, postco = variant.split(":")
chrom = self.__database.chromAcc(preco)
- if chrom is None:
+ if chrom is None :
self.__output.addMessage(__file__, 4, "ENOTINDB",
"Chromosome %s could not be found in our database" %
preco)
return None
- else:
+ #if
+ else :
variant = "%s:%s" % (chrom, postco)
+ #if
return variant
+ #correctChrVariant
- def chrom2c(self, variant, rt):
- if not self._parseInput(variant):
+ def chrom2c(self, variant, rt) :
+ """
+ @arg variant: a variant description
+ @type variant: string
+ @arg rt: the return type
+ @type rt: string
+
+ @return: HGVS_notatations ;
+ @rtype: dictionary or list
+ """
+
+ if not self._parseInput(variant) :
return None
acc = self.parseTree.RefSeqAcc
version = self.parseTree.Version
chrom = self.__database.chromName("%s.%s" % (acc, version))
- if not chrom:
+ if not chrom :
self.__output.addMessage(__file__, 4, "ENOTINDB",
"Accession number: %s could not be found in our database" %
acc)
return None
+ #if
f_change = self._constructChange(False)
r_change = self._constructChange(True)
#FIXME This should be a proper conversion.
loc = int(self.parseTree.RawVar.StartLoc.PtLoc.Main)
- if self.parseTree.RawVar.EndLoc:
+ if self.parseTree.RawVar.EndLoc :
loc2 = int(self.parseTree.RawVar.EndLoc.PtLoc.Main)
- else:
+ else :
loc2 = loc
transcripts = self.__database.get_Transcripts(\
chrom, loc-5000, loc2+5000, 1)
HGVS_notatations = defaultdict(list)
NM_list = []
- for transcript in transcripts:
+ for transcript in transcripts :
self._reset()
self._FieldsFromValues(transcript)
M = self._coreMapping()
- if M is None:
+ if M is None :
#balen
continue
# construct the variant description
@@ -410,22 +557,22 @@ class Converter(object):
startp = self.crossmap.tuple2string((M.startmain, M.startoffset))
endp = self.crossmap.tuple2string((M.endmain, M.endoffset))
- if strand:
+ if strand :
change = f_change
- else:
+ else :
change = r_change
startp, endp = endp, startp
#Check if n or c type
info = self.crossmap.info()
- if info[0] == '1' and info[1] == info[2]:
+ if info[0] == '1' and info[1] == info[2] :
mtype = 'n'
- else:
+ else :
mtype = 'c'
- if M.start_g != M.end_g:
+ if M.start_g != M.end_g :
loca = "%s_%s" % (startp, endp)
- else:
+ else :
loca = "%s" % startp
variant = "%s:%c.%s%s" % (accNo, mtype, loca, change)
@@ -437,25 +584,35 @@ class Converter(object):
return HGVS_notatations
#chrom2c
- def _constructChange(self, revc=False):
+ def _constructChange(self, revc = False) :
+ """
+ @todo document me
+
+ @arg revc:
+ @type revc:
+
+ @return:
+ @rtype: string
+ """
+
p = self.parseTree
- if not p or p.SingleAlleleVarSet:
+ if not p or p.SingleAlleleVarSet :
return None
var = p.RawVar
- if revc:
+ if revc :
arg1 = reverse_complement(var.Arg1 or "") #imported from Bio.Seq
arg2 = reverse_complement(var.Arg2 or "")
- else:
+ #if
+ else :
arg1 = var.Arg1
arg2 = var.Arg2
+ #else
- if var.MutationType == "subst":
+ if var.MutationType == "subst" :
change = "%s>%s" % (arg1, arg2)
- else:
+ else :
change = "%s%s" % (var.MutationType, arg1 or arg2 or "")
return change
#_constructChange
-
-
-
+#Converter
diff --git a/src/Modules/Misc.py b/src/Modules/Misc.py
index 8f76dfc0b61cada60cebb9727a2a83c2451e3975..69ab2cb4044222848809e626ff448918d1db9e75 100644
--- a/src/Modules/Misc.py
+++ b/src/Modules/Misc.py
@@ -1,16 +1,23 @@
#!/usr/bin/python
"""
+@todo: documentation
"""
import time
class Misc() :
"""
+ @todo: documentation
"""
def ID(self) :
"""
+ Generates an ID using time()
+ @todo: documentation
+
+ @return:
+ @rtype:
"""
IDsPerSec = 100
diff --git a/src/Modules/Mutator.py b/src/Modules/Mutator.py
index 313c74b8863010d19e02b96d06c5fac1143c5ccd..6fb16c14840f0301a77967ee3bd3624602dc8a54 100644
--- a/src/Modules/Mutator.py
+++ b/src/Modules/Mutator.py
@@ -1,98 +1,104 @@
#!/usr/bin/python
-from Bio import Restriction
-from Bio.Seq import Seq
-from Bio.Alphabet.IUPAC import IUPACAmbiguousDNA
-from Bio.Seq import reverse_complement # reverse_complement()
-
"""
- Module for mutating a string.
+Module for mutating a string.
- Mutations are described in the original coordinates. These coordinates are
- transfered to the mutated coordinates with the aid of an internal shift
- list, which keeps track of the sizes of changes. Using the original
- coordinates greatly simplifies combined mutations in a variant. A
- visualisation of each raw variant within a combined variant is made and
- effects on restriction sites are also analysed.
+Mutations are described in the original coordinates. These coordinates are
+transfered to the mutated coordinates with the aid of an internal shift
+list, which keeps track of the sizes of changes. Using the original
+coordinates greatly simplifies combined mutations in a variant. A
+visualisation of each raw variant within a combined variant is made and
+effects on restriction sites are also analysed.
- The original as well as the mutated string are stored here.
+The original as well as the mutated string are stored here.
- Public classes:
- Mutator ; Mutate a string and register all shift points.
+@requires: Bio.Restriction
+@requires: Bio.Seq.Seq
+@requires: Bio.Alphabet.IUPAC.IUPACAmbiguousDNA
+@requires: Bio.Seq.reverse_complement
"""
+# Public classes:
+# - Mutator ; Mutate a string and register all shift points.
-class Mutator() :
- """
- Mutate a string and register all shift points. For each mutation a
- visualisation is made (on genomic level) and the addition or deletion
- of restriction sites is detected. Output for each raw variant is stored
- in the output object as 'visualisation', 'deletedRestrictionSites' and
- 'addedRestrictionSites' respectively.
-
- Private variables:
- __config ; Configuration variables of this class:
- __output ; The output object.
- __shift ; A sorted list of tuples (position, shiftsize)
- where the modifications in length are stored.
- Each first element of the tuples in this list
- is unique, each second element is non-zero.
- __restrictionBatch ;
+from Bio import Restriction
+from Bio.Seq import Seq
+from Bio.Alphabet.IUPAC import IUPACAmbiguousDNA
+from Bio.Seq import reverse_complement # reverse_complement()
- Public variables:
- orig ; The original string.
- mutated ; The mutated string.
-
- Special methods:
- __init__(orig) ; Initialise the class with the original string.
-
- Private methods:
- __sortins(tuple) ; Insert a tuple in a sorted list, after
- insertion the list stays sorted.
- __makeRestrictionSet()
- __mutate(pos1, pos2, ins) ; A general mutation function that does a
- delins on interbase coordinates of the
- original string.
-
- Public methods:
- shiftpos(position) ; Calculate the position in the mutated
- string given the position in the
- original string.
- newSplice(sites) ; Generate a list of new splice sites.
- delM(pos1, pos2) ; Delete a range from non-interbase
- position pos1 to pos2.
- insM(pos, ins) ; Insert a string at interbase position
- pos.
- delimsM(pos1, pos2, ins) ; Delete a range from non-interbase
- position pos1 to pos2 and insert ins.
- subM(pos, nuc) ; Substitute a nucleotite at non-interbase
- position pos for nuc.
- invM(pos1, pos2) ; Invert a range from non-interbase
- position pos1 to pos2.
- dupM(pos1, pos2) ; Duplicate a range from non-interbase
- position pos1 to pos2.
+class Mutator() :
+ """
+ Mutate a string and register all shift points. For each mutation a
+ visualisation is made (on genomic level) and the addition or deletion
+ of restriction sites is detected. Output for each raw variant is stored
+ in the output object as 'visualisation', 'deletedRestrictionSites' and
+ 'addedRestrictionSites' respectively.
+
+ Private variables:
+ - __config ; Configuration variables of this class.
+ - __output ; The output object.
+ - __shift ; A sorted list of tuples (position, shiftsize)
+ where the modifications in length are stored.
+ Each first element of the tuples in this list
+ is unique, each second element is non-zero.
+ - __restrictionBatch ;
+
+ Public variables:
+ - orig ; The original string.
+ - mutated ; The mutated string.
+
+ Special methods:
+ - __init__(orig) ; Initialise the class with the original string.
+
+ Private methods:
+ - __sortins(tuple) ; Insert a tuple in a sorted list, after
+ insertion the list stays sorted.
+ - __makeRestrictionSet()
+ - __mutate(pos1, pos2, ins) ; A general mutation function that does a
+ delins on interbase coordinates of the
+ original string.
+
+ Public methods:
+ - shiftpos(position) ; Calculate the position in the mutated
+ string given the position in the
+ original string.
+ - newSplice(sites) ; Generate a list of new splice sites.
+ - delM(pos1, pos2) ; Delete a range from non-interbase
+ position pos1 to pos2.
+ - insM(pos, ins) ; Insert a string at interbase position
+ pos.
+ - delimsM(pos1, pos2, ins) ; Delete a range from non-interbase
+ position pos1 to pos2 and insert ins.
+ - subM(pos, nuc) ; Substitute a nucleotite at non-interbase
+ position pos for nuc.
+ - invM(pos1, pos2) ; Invert a range from non-interbase
+ position pos1 to pos2.
+ - dupM(pos1, pos2) ; Duplicate a range from non-interbase
+ position pos1 to pos2.
"""
def __init__(self, orig, config, output) :
"""
- Initialise the class with the original string.
-
- Arguments:
- orig ; The original string before mutation.
- config ; Configuration variables.
- output ; The output object.
-
- Private variables (altered):
- __config ; Initialised with the configuration
- variables.
- __output ; Initialised with the output object.
- __shift ; Initialised to the empty list.
- __restrictionBatch ; Initialised to a default set of
- restriction enzymes.
-
- Public variables (altered):
- orig ; Initialised to the parameter orig.
- mutated ; Initialised to the parameter orig.
+ Initialise the class with the original string.
+
+ Private variables (altered):
+ - __config ; Initialised with the configuration
+ variables.
+ - __output ; Initialised with the output object.
+ - __shift ; Initialised to the empty list.
+ - __restrictionBatch ; Initialised to a default set of
+ restriction enzymes.
+
+ Public variables (altered):
+ - orig ; Initialised to the parameter orig.
+ - mutated ; Initialised to the parameter orig.
+
+ @arg orig: The original string before mutation
+ @type orig: string
+ @arg config: Configuration variables
+ @type config: object
+ @arg output: The output object
+ @type output: object
"""
self.__config = config
@@ -106,20 +112,21 @@ class Mutator() :
def __sortins(self, tuple) :
"""
- Insert a tuple in a sorted list, the list is sorted on the first
- element of the tuples. After insertion the list stays sorted.
- If a tuple is inserted where tuple[0] already exists, this entry
- is altered.
- If an altered entry has zero as its second element, the entry is
- removed.
-
- Arguments:
- tuple ; An ordered pair where tuple[0] denotes a position and
- tuple[1] denotes the change in shift at this position.
-
- Private variables (altered):
- __shift ; A tuple can be added, removed or altered.
+ Insert a tuple in a sorted list, the list is sorted on the first
+ element of the tuples. After insertion the list stays sorted.
+ If a tuple is inserted where tuple[0] already exists, this entry
+ is altered.
+ If an altered entry has zero as its second element, the entry is
+ removed.
+
+ Private variables (altered):
+ - __shift ; A tuple can be added, removed or altered.
+
+ @arg tuple: An ordered pair where tuple[0] denotes a position and
+ tuple[1] denotes the change in shift at this position
+ @type tuple: tuple (integer)
"""
+
if not tuple[1] : # Only non-zero shift sizes are relevant.
return
@@ -143,17 +150,17 @@ class Mutator() :
def __makeRestrictionList(self, seq) :
"""
- Return a set of restriction enzymes that can bind in a certain
- sequence.
+ Return a set of restriction enzymes that can bind in a certain
+ sequence.
- Arguments:
- seq ; The sequence to be analysed.
+ Private variables:
+ - __restrictionBatch ; A RestrictionBatch object.
- Returns:
- list ; A list of restriction enzymes.
+ @arg seq: The sequence to be analysed
+ @type seq: string
- Private variables:
- __restrictionBatch ; A RestrictionBatch object.
+ @return: A list of restriction enzymes
+ @rtype: list
"""
restrictionAnalysis = Restriction.Analysis(self.__restrictionBatch, seq)
@@ -169,8 +176,18 @@ class Mutator() :
#__makeRestrictionSet
def __restrictionDiff(self, list1, list2) :
- #TODO documentation
"""
+ Compare two lists, and count those elements which are only present
+ in list1.
+
+ @arg list1: some list
+ @type list1: list
+ @arg list2: some (other) list
+ @type list2: list
+
+ @return: the elements only present in list 1, together with the number
+ of occurrences, if more than once present
+ @rtype: list
"""
tempList = list(list1)
@@ -193,26 +210,31 @@ class Mutator() :
def __mutate(self, pos1, pos2, ins) :
"""
- A general mutation function that does a delins on interbase
- coordinates of the original string. The change in length (if any)
- is stored by calling the __sortins() function.
- The coordinates are those of the original string, so we use the
- __shifsize() function to map them to the mutated string, on which
- we perform the alteration.
-
- Arguments:
- pos1 ; The first interbase position of the deletion.
- pos2 ; The second interbase position of the deletion.
- ins ; The insertion.
-
- Private variables:
- __config ; The variables maxvissize, flanksize and flankclipsize
- are used in the visualisation.
- __output ; Visualisation information is added.
-
- Public variables (altered):
- mutated ; This string will reflect the result of the given
- delins.
+ A general mutation function that does a delins on interbase
+ coordinates of the original string. The change in length (if any)
+ is stored by calling the __sortins() function.
+ The coordinates are those of the original string, so we use the
+ __shifsize() function to map them to the mutated string, on which
+ we perform the alteration.
+
+ Private variables:
+ - __config ; The variables maxvissize, flanksize and flankclipsize
+ are used in the visualisation.
+ - __output ; Visualisation information is added.
+
+ Public variables (altered):
+ - mutated ; This string will reflect the result of the given
+ delins.
+
+ @arg pos1: The first interbase position of the deletion
+ @type pos1: integer
+ @arg pos2: The second interbase position of the deletion
+ @type pos2: integer
+ @arg ins: The insertion
+ @type ins: string
+
+ @return: visualisation
+ @rtype: string
"""
#
@@ -276,6 +298,14 @@ class Mutator() :
def visualiseLargeString(self, string) :
"""
+ If the length of a sequence is larger than a certain maxvissize, the
+ string is clipped; otherwise the string is just returned.
+
+ @arg string: DNA sequence
+ @type string: string
+
+ @return: either the original sequence, or an abbreviation of it
+ @rtype: string
"""
if len(string) > self.__config.maxvissize :
@@ -287,18 +317,18 @@ class Mutator() :
def shiftpos(self, position) :
"""
- Calculate the position in the mutated string, given a position in
- the original string.
+ Calculate the position in the mutated string, given a position in
+ the original string.
- Arguments:
- position ; The position in the original string for which we
- want the shift size.
+ Private variables:
+ - __shift ; Used to calculate the shift.
- Private variables:
- __shift ; Used to calculate the shift.
+ @arg position: The position in the original string for which we want the
+ shift size
+ @type position: integer
- Returns:
- integer ; The position in the mutated string.
+ @return: The position in the mutated string
+ @rtype: integer
"""
ret = position
@@ -314,13 +344,13 @@ class Mutator() :
def newSplice(self, sites) :
"""
- Generate a list of new splice sites.
+ Generate a list of new splice sites.
- Arguments:
- sites ; A list of old splice sites.
+ @arg sites: A list of old splice sites
+ @type sites: list
- Returns:
- list ; A list of new splice sites.
+ @return: A list of new splice sites
+ @rtype: list
"""
ret = []
@@ -341,14 +371,15 @@ class Mutator() :
def delM(self, pos1, pos2) :
"""
- Delete a range from non-interbase position pos1 to pos2.
+ Delete a range from non-interbase position pos1 to pos2.
- Arguments:
- pos1 ; The first nucleotide of the range to be deleted.
- pos2 ; The last nucleotide of the range to be deleted.
+ Private variables:
+ - __output ; Visualisation information is added.
- Private variables:
- __output ; Visualisation information is added.
+ @arg pos1: The first nucleotide of the range to be deleted
+ @type pos1: integer
+ @arg pos2: The last nucleotide of the range to be deleted
+ @type pos2: integer
"""
if pos1 == pos2 :
@@ -362,15 +393,15 @@ class Mutator() :
def insM(self, pos, ins) :
"""
- Insert a string at interbase position pos.
+ Insert a string at interbase position pos.
- Arguments:
- pos ; The interbase position where the insertion should take
- place.
- ins ; The insertion, a string.
+ Private variables:
+ - __output ; Visualisation information is added.
- Private variables:
- __output ; Visualisation information is added.
+ @arg pos: The interbase position where the insertion should take place
+ @type pos: integer
+ @arg ins: The insertion
+ @type ins: string
"""
visualisation = ["insertion between %i and %i" % (pos, pos + 1)]
@@ -380,13 +411,15 @@ class Mutator() :
def delinsM(self, pos1, pos2, ins) :
"""
- Delete a range from non-interbase position pos1 to pos2 and insert
- ins.
-
- Arguments:
- pos1 ; The first nucleotide of the range to be deleted.
- pos2 ; The last nucleotide of the range to be deleted.
- ins ; The insertion, a string.
+ Delete a range from non-interbase position pos1 to pos2 and insert
+ ins.
+
+ @arg pos1: The first nucleotide of the range to be deleted
+ @type pos1: integer
+ @arg pos2: The last nucleotide of the range to be deleted.
+ @type pos2: integer
+ @arg ins: The insertion
+ @type ins: string
"""
visualisation = ["delins from %i to %i" % (pos1, pos2)]
@@ -396,14 +429,15 @@ class Mutator() :
def subM(self, pos, nuc) :
"""
- Substitute a nucleotite at non-interbase position pos for nuc.
+ Substitute a nucleotide at non-interbase position pos for nuc.
- Arguments:
- pos ; The position where the substitution should take place.
- nuc ; The new nucleotide.
+ Private variables:
+ - __output ; Visualisation information is added.
- Private variables:
- __output ; Visualisation information is added.
+ @arg pos: The position where the substitution should take place
+ @type pos: integer
+ @arg nuc: The new nucleotide
+ @type nuc: string
"""
visualisation = ["substitution at %i" % pos]
@@ -413,14 +447,15 @@ class Mutator() :
def invM(self, pos1, pos2) :
"""
- Invert a range from non-interbase position pos1 to pos2.
+ Invert a range from non-interbase position pos1 to pos2.
- Arguments:
- pos1 ; The first nucleotide of the range to be inverted.
- pos2 ; The last nucleotide of the range to be inverted.
+ Public variables:
+ - orig ; The original string.
- Public variables:
- orig ; The original string.
+ @arg pos1: The first nucleotide of the range to be inverted
+ @type pos1: integer
+ @arg pos2: The last nucleotide of the range to be inverted
+ @type pos2: integer
"""
visualisation = ["inversion between %i and %i" % (pos1, pos2)]
@@ -431,14 +466,15 @@ class Mutator() :
def dupM(self, pos1, pos2) :
"""
- Duplicate a range from non-interbase position pos1 to pos2.
+ Duplicate a range from non-interbase position pos1 to pos2.
- Arguments:
- pos1 ; The first nucleotide of the range to be duplicated.
- pos2 ; The last nucleotide of the range to be duplicated.
+ Public variables:
+ - orig ; The original string.
- Public variables:
- orig ; The original string.
+ @arg pos1: The first nucleotide of the range to be duplicated
+ @type pos1: integer
+ @arg pos2: The last nucleotide of the range to be duplicated
+ @type pos2: integer
"""
visualisation = ["duplication from %i to %i" % (pos1, pos2)]
diff --git a/src/Modules/Output.py b/src/Modules/Output.py
index 5aa37432904a351a9bccad42b8c50d9b71bff073..a5ebf0b5aba1ed32ae67933799ddd26f80b83483 100644
--- a/src/Modules/Output.py
+++ b/src/Modules/Output.py
@@ -1,123 +1,86 @@
#!/usr/bin/python
"""
- Module for storing output and messages.
- Output is stored as a named list that can be expanded.
- Messages can be retrieved at a later time to provide flexibility. Message
- levels are defined to increase or decrease the amount of logging and ouput.
- The position of the log file, as well as the levels are defined in the
- configuration file.
-
- Message levels:
- -1 : Log ; Specifically log a message.
- 0 : Debug ; Debug information.
- 1 : Info ; Info.
- 2 : Warning ; Regular warnings.
- 3 : Error ; Serious errors that can be compensated for.
- 4 : Fatal ; Errors that are not recoverable.
- 5 : Off ; Can be used as a log/output level to turn off output.
-
- Public classes:
- Message ; Container class for message variables.
- Output ; Output interface for errors, warnings and logging.
+Module for storing output and messages.
+Output is stored as a named list that can be expanded.
+Messages can be retrieved at a later time to provide flexibility. Message
+levels are defined to increase or decrease the amount of logging and ouput.
+The position of the log file, as well as the levels are defined in the
+configuration file.
+
+Message levels:
+ - E{-}1 : Log ; Specifically log a message.
+ - 0 : Debug ; Debug information.
+ - 1 : Info ; Info.
+ - 2 : Warning ; Regular warnings.
+ - 3 : Error ; Serious errors that can be compensated for.
+ - 4 : Fatal ; Errors that are not recoverable.
+ - 5 : Off ; Can be used as a log/output level to turn off output.
+
+@requires: time
"""
+# Public classes:
+# - Message ; Container class for message variables.
+# - Output ; Output interface for errors, warnings and logging.
-import time # strftime()
-
-class Message() :
- """
- Container class for message variables.
-
- Special methods:
- __init__(origin, level, code, description) ; Make a message object.
-
- Public variables:
- origin ; Name of the module creating this object.
- level ; Importance of the message.
- code ; The error code of the message.
- description ; A description of the message.
- """
- def __init__(self, origin, level, code, description) :
- """
- Make a new message object.
-
- Arguments:
- origin ; Name of the module creating this object.
- level ; Importance of the message.
- code ; The error code of the message.
- description ; A description of the message.
-
- Public variables (altered):
- origin ; Name of the module creating this object.
- level ; Importance of the message.
- code ; The error code of the message.
- description ; A description of the message.
- """
-
- self.origin = origin
- self.level = level
- self.code = code
- self.description = description
- #__init__
-#Message
+import time # strftime()
class Output() :
"""
- Provide an output interface for errors, warnings and logging purposes.
-
- Private variables:
- __config ; Configuration variables.
- __outputdata ; The output dictionary.
- __messages ; The messages list.
- __instance ; The name of the module that made this object.
- __loghandle ; The handle of the log file.
- __errors ; The number of errors that have been processed.
- __warnings ; The number of warnings that have been processed.
-
- Special methods:
- __init__(instance, config) ; Initialise the class with variables
- from the config file and the calling
- module.
- __del__() ; Close the logfile and clean up.
-
- Private methods:
- __niceName(filename) ; Strip the path and the extention from a
- filename.
- __levelToName(level) ; Convert a log level to a readable string.
-
- Public methods:
- addMessage(filename, ; Add a message to the message list.
- level,
- code,
- description)
- getMessages() ; Print all messages that exceed the
- configured output level.
- addOutput(name, data) ; Add output to the output dictionary.
- getOutput(name) ; Retrieve data from the output dictionary.
- Summary() ; Print a summary of the number of errors
- and warnings.
+ Provide an output interface for errors, warnings and logging purposes.
+
+ Private variables:
+ - __config ; Configuration variables.
+ - __outputdata ; The output dictionary.
+ - __messages ; The messages list.
+ - __instance ; The name of the module that made this object.
+ - __loghandle ; The handle of the log file.
+ - __errors ; The number of errors that have been processed.
+ - __warnings ; The number of warnings that have been processed.
+
+ Special methods:
+ - __init__(instance, config) ; Initialise the class with variables
+ from the config file and the calling
+ module.
+ - __del__() ; Close the logfile and clean up.
+
+ Private methods:
+ - __niceName(filename) ; Strip the path and the extention from a
+ filename.
+ - __levelToName(level) ; Convert a log level to a readable string.
+
+ Public methods:
+ - addMessage(filename, level, code, description) ; Add a message to
+ the message list.
+ - getMessages() ; Print all messages that exceed the
+ configured output level.
+ - addOutput(name, data) ; Add output to the output dictionary.
+ - getOutput(name) ; Retrieve data from the output dictionary.
+ - Summary() ; Print a summary of the number of errors
+ and warnings.
"""
def __init__(self, instance, config) :
"""
- Initialise the class private variables with variables from the
- config file and the calling module.
-
- Arguments:
- instance ; The filename of the module that created this object.
- config ; The configuration object.
-
- Private variables (altered):
- __config ; Configuration variables.
- __outputdata ; The output dictionary.
- __messages ; The messages list.
- __instance ; Initialised with the name of the module that
- created this object.
- __loghandle ; Initialised as the handle of the log file
- defined in the configuration file.
- __errors ; Initialised to 0.
- __warnings ; Initialised to 0.
+ Initialise the class private variables with variables from the
+ config file and the calling module.
+
+ Private variables (altered):
+ - __config ; Configuration variables.
+ - __outputdata ; The output dictionary.
+ - __messages ; The messages list.
+ - __instance ; Initialised with the name of the module that
+ created this object.
+ - __loghandle ; Initialised as the handle of the log file
+ defined in the configuration file.
+ - __errors ; Initialised to 0.
+ - __warnings ; Initialised to 0.
+
+ @arg instance: The filename of the module that created this object
+ @type instance: string
+ @arg config: The configuration object
+ @type config: object
"""
self.__config = config
@@ -131,14 +94,14 @@ class Output() :
def __del__(self) :
"""
- Clean up the output dictionary, the messages list and close the log
- file.
-
- Private variables(altered):
- __loghandle ; The handle of the log file defined in the
- configuration file.
- __outputdata ; The output dictionary.
- __messages ; The messages list.
+ Clean up the output dictionary, the messages list and close the log
+ file.
+
+ Private variables(altered):
+ - __loghandle ; The handle of the log file defined in the
+ configuration file.
+ - __outputdata ; The output dictionary.
+ - __messages ; The messages list.
"""
self.__loghandle.close()
@@ -150,13 +113,13 @@ class Output() :
def __niceName(self, filename) :
"""
- Strip the path and the extention from a filename.
+ Strip the path and the extention from a filename.
- Arguments:
- filename ; A complete path plus extention.
+ @arg filename: A complete path plus extention
+ @type filename: string
- Returns:
- string ; The bare filename without a path and extention.
+ @return: The bare filename without a path and extention
+ @rtype: string
"""
return filename.split('/')[-1].split('.')[0]
@@ -164,13 +127,13 @@ class Output() :
def __levelToName(self, level) :
"""
- Convert a log level to a readable string.
+ Convert a log level to a readable string.
- Arguments:
- level ; A log level (an integer between -1 and 5).
+ @arg level: A log level (an integer between -1 and 5)
+ @type level: integer
- Returns:
- string ; A readable description of the log level.
+ @return: A readable description of the log level
+ @rtype: string
"""
if level == 0 :
@@ -188,27 +151,26 @@ class Output() :
def addMessage(self, filename, level, code, description) :
"""
- Add a message to the message list.
- If the level exceeds the configured loglevel or if the level is -1,
- then the message is also logged.
- If the severity equals 2, then the number of warnings is inreased,
- if it exceeds 2, then the number of errors is increased.
-
- Arguments:
- filename ; Name of the calling module.
- level ; Severity of the message.
- code ; Error code of the message.
- description ; Description of the message.
-
- Private variables:
- __messages ; The messages list.
- __instance ; Module that created the Output object.
- __config ; The variables loglevel and datestring are used.
- __loghandle ; Handle to the log file.
-
- Private variables (altered):
- __warnings ; Increased by one if the severity equals 2.
- __errors ; Increased by one if the severity exceeds 2.
+ Add a message to the message list.
+ If the level exceeds the configured loglevel or if the level is -1,
+ then the message is also logged.
+ If the severity equals 2, then the number of warnings is inreased,
+ if it exceeds 2, then the number of errors is increased.
+
+ Private variables:
+ - __messages ; The messages list.
+ - __instance ; Module that created the Output object.
+ - __config ; The variables loglevel and datestring are used.
+ - __loghandle ; Handle to the log file.
+
+ Private variables (altered):
+ - __warnings ; Increased by one if the severity equals 2.
+ - __errors ; Increased by one if the severity exceeds 2.
+
+ @arg filename: Name of the calling module
+ @arg level: Severity of the message
+ @arg code: Error code of the message
+ @arg description: Description of the message
"""
niceName = self.__niceName(filename)
@@ -234,14 +196,14 @@ class Output() :
def getMessages(self) :
"""
- Print all messages that exceed the configured output level.
+ Print all messages that exceed the configured output level.
- Private variables:
- __messages ; The messages list.
- __config ; The variable outputlevel is used.
+ Private variables:
+ - __messages ; The messages list.
+ - __config ; The variable outputlevel is used.
- Returns:
- list ; A list of messages.
+ @return: A list of messages
+ @rtype: list
"""
ret = []
@@ -256,14 +218,16 @@ class Output() :
def getSoapMessages(self):
"""
- Returns a list of SoapMessages for over the wire
+ Returns a list of SoapMessages for over the wire
+
+ Private variables:
+ - __messages ; The messages list.
+ - __config ; The variable outputlevel is used.
- Private variables:
- __messages ; The messages list.
- __config ; The variable outputlevel is used.
+ @requires: Modules.Serializers.SoapMessage
- Returns:
- list ;
+ @return: list of SoapMessages
+ @rtype: list
"""
#TODO: MOVE to top if works
@@ -283,17 +247,17 @@ class Output() :
def getBatchMessages(self, level):
"""
- Returns a list of Messages with an errorlevel >= level
- and removes additional lines from a parseerror
+ Returns a list of Messages with an errorlevel >= level
+ and removes additional lines from a parseerror
- Arguments:
- level ;
+ Private variables:
+ - __messages ; The messages list.
- Private variables:
- __messages ; The messages list.
+ @arg level: error level
+ @type level: integer
- Returns:
- list ;
+ @return: list of Messages
+ @rtype: list
"""
ret = []
@@ -312,16 +276,17 @@ class Output() :
def addOutput(self, name, data) :
"""
- If the output dictionary already has a node with the specified
- name, the list that this name points to is expanded with the data.
- Otherwise create a node and assign a list containing the data.
+ If the output dictionary already has a node with the specified
+ name, the list that this name points to is expanded with the data.
+ Otherwise create a node and assign a list containing the data.
- Arguments:
- name ; Name of a node in the output dictionary.
- data ; The data to be stored at this node.
+ Private variables:
+ - __outputData ; The output dictionary.
- Private variables:
- __outputData ; The output dictionary.
+ @arg name: Name of a node in the output dictionary
+ @type name: string
+ @arg data: The data to be stored at this node
+ @type data: object
"""
if self.__outputData.has_key(name) :
@@ -332,13 +297,16 @@ class Output() :
def getOutput(self, name) :
"""
- Return a list of data from the output dictionary.
+ Return a list of data from the output dictionary.
- Arguments:
- name ; Name of a node in the output dictionary.
+ Private variables:
+ - __outputData ; The output dictionary.
- Private variables:
- __outputData ; The output dictionary.
+ @arg name: Name of a node in the output dictionary
+ @type name: string
+
+ @return: output dictionary
+ @rtype: dictionary
"""
if self.__outputData.has_key(name) :
@@ -348,19 +316,18 @@ class Output() :
def getIndexedOutput(self, name, index) :
"""
- Return an element of a list, the list is called 'name' in de
- __outputData dictionary. If either the list or the element does not
- exist, return an empty list.
+ Return an element of a list, the list is called 'name' in de
+ __outputData dictionary. If either the list or the element does not
+ exist, return an empty list.
- Arguments:
- name ; Name of the list.
- index ; Index of the element to be retuned.
+ @arg name: Name of the list.
+ @arg index: Index of the element to be retuned.
- Private variables:
- __outputData ; The output dictionary.
+ Private variables:
+ - __outputData ; The output dictionary.
- Returns:
- list ; The requested element.
+ @return: The requested element
+ @rtype: list
"""
if self.__outputData.has_key(name) :
@@ -371,16 +338,16 @@ class Output() :
def getMessagesWithErrorCode(self, errorcode):
"""
- Retrieve all messages that have a specific error code.
+ Retrieve all messages that have a specific error code.
- Arguments:
- errorcode ; The error code to filter on.
+ Private variables:
+ - __messages ; The messages list.
- Private variables:
- __messages ; The messages list.
+ @arg errorcode: The error code to filter on
+ @type errorcode: string
- Returns:
- list ; A filtered list.
+ @return: A filtered list
+ @rtype: list
"""
ret = []
@@ -393,17 +360,18 @@ class Output() :
def Summary(self) :
"""
- Print a summary of the number of errors and warnings.
-
- Private variables:
- __errors ; The number of errors.
- __warnings ; The number of warnings.
+ Print a summary of the number of errors and warnings.
- Returns:
- triple:
- integer ; Number of errors.
- integer ; Number of warnings.
- string ; Summary.
+ Private variables:
+ - __errors ; The number of errors.
+ - __warnings ; The number of warnings.
+
+ @return:
+ triple:
+ - Number of errors
+ - Number of warnings
+ - Summary
+ @rtype: integer, integer, string
"""
e_s = 's'
@@ -418,6 +386,47 @@ class Output() :
#Summary
#Output
+class Message() :
+ """
+ Container class for message variables.
+
+ Special methods:
+ - __init__(origin, level, code, description) ; Make a message object.
+
+ Public variables:
+ - origin ; Name of the module creating this object.
+ - level ; Importance of the message.
+ - code ; The error code of the message.
+ - description ; A description of the message.
+ """
+
+ def __init__(self, origin, level, code, description) :
+ """
+ Make a new message object.
+
+ Public variables (altered):
+ - origin ; Name of the module creating this object.
+ - level ; Importance of the message.
+ - code ; The error code of the message.
+ - description ; A description of the message.
+
+ @arg origin: Name of the module creating this object
+ @type origin: string
+ @arg level: Importance of the message
+ @type level: integer
+ @arg code: The error code of the message
+ @type code: string
+ @arg description: A description of the message
+ @type description: string
+ """
+
+ self.origin = origin
+ self.level = level
+ self.code = code
+ self.description = description
+ #__init__
+#Message
+
#
# Unit test.
#
diff --git a/src/Modules/Parser.py b/src/Modules/Parser.py
index f397f74ff1fcfbcf94816a9523a827dbb4961c22..538076b366e4d69f369308780f10e07eb209743c 100644
--- a/src/Modules/Parser.py
+++ b/src/Modules/Parser.py
@@ -1,34 +1,36 @@
#!/usr/bin/python
"""
- Module for parting a variant described using the HGVS nomenclature.
+Module for parsing a variant described using the HGVS nomenclature.
- A context-free parser is defined here, the nomenclature rules are specified
- in BNF, which is used (with some minor modifications) as source of this
- module.
+A context-free parser is defined here, the nomenclature rules are specified
+in Backus-Naur Form (BNF), which is used (with some minor modifications) as source of this
+module.
- Public classes:
- Nomenclatureparser ; Parse an input string.
+@requires: pyparsing
"""
+# Public classes:
+# - Nomenclatureparser ; Parse an input string.
+
from pyparsing import *
class Nomenclatureparser() :
"""
- Parse an input string.
+ Parse an input string.
- Private variables:
- __output ; The output object.
+ Private variables:
+ - __output ; The output object.
- Public variables:
- All variables defined below, they are all context-free grammar
- rules.
+ Public variables:
+ - All variables defined below, they are all context-free grammar
+ rules.
- Special methods:
- __init__() ; Initialise the class and enable packrat parsing.
+ Special methods:
+ - __init__() ; Initialise the class and enable packrat parsing.
- Public methods:
- parse(input) ; Parse the input string and return a parse tree.
+ Public methods:
+ - parse(input) ; Parse the input string and return a parse tree.
"""
# New:
@@ -307,13 +309,13 @@ class Nomenclatureparser() :
def __init__(self, output) :
"""
- Initialise the class and enable packrat parsing.
+ Initialise the class and enable packrat parsing.
- Arguments:
- output ; The output object.
+ Private variables (altered):
+ - __output ; Set to the output object.
- Private variables (altered):
- __output ; Set to the output object.
+ @arg output: The output object
+ @type output: object
"""
self.__output = output
@@ -322,21 +324,21 @@ class Nomenclatureparser() :
def parse(self, variant) :
"""
- Parse the input string and return a parse tree if the parsing was
- successful. Otherwise print the parse error and the position in
- the input where the error occurred.
+ Parse the input string and return a parse tree if the parsing was
+ successful. Otherwise print the parse error and the position in
+ the input where the error occurred.
- Arguments:
- variant ; The input string that needs to be parsed.
+ Private variables:
+ - __output ; The output object.
- Private variables:
- __output ; The output object.
+ Public variables:
+ - Var ; The top-level rule of our parser.
- Public variables:
- Var ; The top-level rule of our parser.
+ @arg variant: The input string that needs to be parsed
+ @type variant: string
- Returns:
- Object ; The parse tree containing the parse results.
+ @return: The parse tree containing the parse results
+ @rtype: object
"""
try :
diff --git a/src/Modules/Retriever.py b/src/Modules/Retriever.py
index b7403dca9ef03da002cfbdf4fbb0b7d1081cf28f..7288b900b32d5bd9af9d709daa7baae8cb5b8cc4 100644
--- a/src/Modules/Retriever.py
+++ b/src/Modules/Retriever.py
@@ -1,15 +1,30 @@
#!/usr/bin/python
"""
- Module for retrieving files from either the cache or the NCBI.
-
- A hash of every retrieved file is stored in the internal database. If a
- requested file is not found, but its hash is, we use additional information
- to re-download the file.
-
- Public classes:
- Retriever ; Retrieve a record from either the cache or the NCBI.
+Module for retrieving files from either the cache or the NCBI.
+
+A hash of every retrieved file is stored in the internal database. If a
+requested file is not found, but its hash is, we use additional information
+to re-download the file.
+
+@requires: os
+@requires: bz2
+@requires: hashlib
+@requires: urllib2
+@requires: StringIO
+@requires: ftplib
+@requires: Bio.SeqIO
+@requires: Bio.Entrez
+@requires: Bio.Seq.UnknownSeq
+@requires: Modules.Misc
+@requires: Modules.LRGparser
+@requires: Modules.GBparser
+@requires: xml.dom.DOMException
+@requires: xml.dom.minidom
"""
+# Public classes:
+# - Retriever ; Retrieve a record from either the cache or the NCBI.
+
import os # path.isfile(), link() path.isdir(), path.mkdir(),
# walk(), path.getsize(), path.join(), stat(), remove()
@@ -30,58 +45,58 @@ import xml.dom.minidom
class Retriever(object) :
"""
- Retrieve a record from either the cache or the NCBI.
-
- Inherited variables from Db.Output.Config:
- email ; The email address which we give to the NCBI.
- cache ; The directory where the records are stored.
- cachesize ; Maximum size of the cache.
-
- Special methods:
- __init__(config, ; Use variables from the configuration file to
- output, initialise the class private variables.
- database)
-
-
- Private methods:
- _foldersize(folder) ; Return the size of a folder.
- _cleancache() ; Keep the cache at a maximum size.
- _nametofile(name) ; Convert a name to a filename.
- _write(raw_data, ; Write a record to a file.
- filename,
- extract)
- _calcHash(content) ; Calculate the md5sum of 'content'.
- _newUD() ; Generate a new UD number.
-
- Public methods:
- retrieveslice(accno, ; Retrieve a chromosome slice from the NCBI.
- start,
- stop,
- orientation)
- retrievegene(gene, ; Retrieve a gene from the NCBI.
- organism,
- upstream,
- downstream)
- downloadrecord(url) ; Download a GenBank file.
- uploadrecord(raw_data) ; Let someone upload a GenBank file.
- loadrecord(identifier) ; Load a record, store it in the
- cache, manage the cache and return
- the record.
-
- Inherited methods from Db.Output:
- WarningMsg(filename, message) ; Print a warning message.
- ErrorMsg(filename, message) ; Print an error message and log it.
- LogMsg(filename, message) ; Log a message.
+ Retrieve a record from either the cache or the NCBI.
+
+ Inherited variables from Db.Output.Config:
+ - email ; The email address which we give to the NCBI.
+ - cache ; The directory where the records are stored.
+ - cachesize ; Maximum size of the cache.
+
+ Special methods:
+ - __init__(config, output, database) ; Use variables from the
+ configuration file to initialise the class private variables.
+
+
+
+ Private methods:
+ - _foldersize(folder) ; Return the size of a folder.
+ - _cleancache() ; Keep the cache at a maximum size.
+ - _nametofile(name) ; Convert a name to a filename.
+ - _write(raw_data, filename, extract) ; Write a record to a file.
+ - _calcHash(content) ; Calculate the md5sum of 'content'.
+ - _newUD() ; Generate a new UD number.
+
+ Public methods:
+ - retrieveslice(accno, start, stop, orientation) ; Retrieve a chromosome
+ slice from the NCBI.
+ - retrievegene(gene, organism, upstream, downstream) ; Retrieve a gene
+ from the NCBI.
+ - downloadrecord(url) ; Download a GenBank file.
+ - uploadrecord(raw_data) ; Let someone upload a GenBank file.
+ - loadrecord(identifier) ; Load a record, store it in the cache, manage
+ the cache and return the record.
+
+ Inherited methods from Db.Output:
+ - WarningMsg(filename, message) ; Print a warning message.
+ - ErrorMsg(filename, message) ; Print an error message and log it.
+ - LogMsg(filename, message) ; Log a message.
"""
def __init__(self, config, output, database) :
"""
- Use variables from the configuration file for some simple
- settings. Make the cache directory if it does not exist yet.
+ Use variables from the configuration file for some simple
+ settings. Make the cache directory if it does not exist yet.
- Inherited variables from Db.Output.Config:
- email ; The email address which we give to the NCBI.
- cache ; The directory where the records are stored.
+ Inherited variables from Db.Output.Config:
+ - email ; The email address which we give to the NCBI.
+ - cache ; The directory where the records are stored.
+
+ @arg config:
+ @type config:
+ @arg output:
+ @type output:
+ @arg database:
+ @type database:
"""
self._config = config
@@ -95,13 +110,13 @@ class Retriever(object) :
def _foldersize(self, folder) :
"""
- Return the size of a folder in bytes.
-
- Arguments:
- folder ; Name of a directory.
+ Return the size of a folder in bytes.
- Returns:
- integer ; The size of the directory.
+ @arg folder: Name of a directory
+ @type folder: string
+
+ @return: The size of the directory
+ @rtype: integer
"""
folder_size = 0
@@ -114,15 +129,15 @@ class Retriever(object) :
def _cleancache(self) :
"""
- Keep removing files until the size of the cache is less than the
- maximum size.
- First, the cache checked for its size, if it exceeds the maximum
- size the ``oldest'' files are deleted. Note that accessing a file
- makes it ``new''.
+ Keep removing files until the size of the cache is less than the
+ maximum size.
+ First, the cache checked for its size, if it exceeds the maximum
+ size the ``oldest'' files are deleted. Note that accessing a file
+ makes it ``new''.
- Inherited variables from Db.Output.Config:
- cache ; Directory under scrutiny.
- cachesize ; Maximum size of the cache.
+ Inherited variables from Db.Output.Config:
+ - cache ; Directory under scrutiny.
+ - cachesize ; Maximum size of the cache.
"""
if self._foldersize(self._config.cache) < self._config.cachesize:
@@ -147,16 +162,16 @@ class Retriever(object) :
def _nametofile(self, name) :
"""
- Convert an accession number to a filename.
+ Convert an accession number to a filename.
- Arguments:
- name ; The accession number.
+ Inherited variables from Db.Output.Config:
+ - cache ; Name of the cache directory.
- Inherited variables from Db.Output.Config:
- cache ; Name of the cache directory.
+ @arg name: The accession number
+ @type name: string
- Returns:
- string ; A filename.
+ @return: A filename
+ @rtype: string
"""
return self._config.cache + '/' + name + "." + self.fileType + ".bz2"
@@ -164,14 +179,15 @@ class Retriever(object) :
def _write(self, raw_data, filename) :
"""
- Write raw data to a compressed file.
+ Write raw data to a compressed file.
- Arguments:
- raw_data ; The raw_data to be compressed and written
- filename ; The intended name of the outfile
+ @arg raw_data: The raw_data to be compressed and written
+ @type raw_data: string
+ @arg filename: The intended name of the outfile
+ @type filename: string
- Returns:
- outfile ; The full paht and name of the file written
+ @return: outfile ; The full path and name of the file written
+ @rtype: string
"""
# Compress the data to save disk space.
comp = bz2.BZ2Compressor()
@@ -189,13 +205,13 @@ class Retriever(object) :
def _calcHash(self, content) :
"""
- Calculate the md5sum of a piece of text.
+ Calculate the md5sum of a piece of text.
- Arguments:
- content ; Arbitrary text.
+ @arg content: Arbitrary text
+ @type content: string
- Returns:
- string ; The md5sum of 'content'.
+ @return: The md5sum of 'content'
+ @rtype: string
"""
hashfunc = hashlib.md5()
@@ -208,10 +224,10 @@ class Retriever(object) :
def _newUD(self) :
"""
- Make a new UD number based on the current time (seconds since 1970).
+ Make a new UD number based on the current time (seconds since 1970).
- Returns:
- string ; A new UD number.
+ @return: A new UD number
+ @rtype: string
"""
M = Misc.Misc()
@@ -223,13 +239,17 @@ class Retriever(object) :
def _updateDBmd5(self, raw_data, name, GI):
#TODO documentation
"""
- Arguments:
- raw_data ;
- name ;
- GI ;
+ @todo: documentation
+
+ @arg raw_data:
+ @type raw_data:
+ @arg name:
+ @type name:
+ @arg GI:
+ @type GI:
- Returns:
- string ;
+ @return: filename
+ @rtype: string
"""
currentmd5sum = self._database.getHash(name)
@@ -250,14 +270,14 @@ class Retriever(object) :
def snpConvert(self, rsId) :
"""
- Search an rsId in dbSNP and return all annotated HGVS notations of
- it.
+ Search an rsId in dbSNP and return all annotated HGVS notations of
+ it.
- Arguments:
- rsId ; The id of the SNP.
+ @arg rsId: The id of the SNP
+ @type rsId: string
- Returns:
- list ; A list of HGVS notations.
+ @return: A list of HGVS notations
+ @rtype: list
"""
# A simple input check.
@@ -295,28 +315,29 @@ class GenBankRetriever(Retriever):
def write(self, raw_data, filename, extract) :
"""
- Write raw data to a file. The data is parsed before writing, if a
- parse error occurs an error is returned and the function exits.
- If 'filename' is set and 'extract' is set to 0, then 'filename' is
- used for output.
- If 'extract' is set to 1, then the filename is constructed from the
- id of the GenBank record. Additionally the id and GI number are
- returned for further processing (putting them in the internal
- database).
-
- Arguments:
- raw_data ; The data.
- filename ; The intended name of the file.
- extract ; Flag that indicates whether to extract the record ID
- and GI number:
- 0 ; Do not extract, use 'filename'.
- 1 ; Extract.
-
- Returns:
- tuple ; Depending on the value of 'extract':
- 0 ; ('filename', None)
- 1 ; (id, GI)
-
+ Write raw data to a file. The data is parsed before writing, if a
+ parse error occurs an error is returned and the function exits.
+ If 'filename' is set and 'extract' is set to 0, then 'filename' is
+ used for output.
+ If 'extract' is set to 1, then the filename is constructed from the
+ id of the GenBank record. Additionally the id and GI number are
+ returned for further processing (putting them in the internal
+ database).
+
+ @arg raw_data: The data
+ @type raw_data: string
+ @arg filename: The intended name of the file.
+ @type filename: string
+ @arg extract: Flag that indicates whether to extract the record ID and
+ GI number:
+ - 0 ; Do not extract, use 'filename'
+ - 1 ; Extract
+ @type extract: integer
+
+ @return: tuple ; Depending on the value of 'extract':
+ - 0 ; ('filename', None)
+ - 1 ; (id, GI)
+ @rtype: tuple (string, string)
"""
if raw_data == "\nNothing has been found\n" :
@@ -394,30 +415,34 @@ class GenBankRetriever(Retriever):
def retrieveslice(self, accno, start, stop, orientation) :
"""
- Retrieve a slice of a chromosome.
- If the arguments are recognised (found in the internal database),
- we look if the associated file is still present and if so: return
- its UD number.
- If the arguments are recognised but no file was found, we download
- the new slice and update the hash (and log if the hash changes).
- If the arguments are not recognised, we download the new slice and
- make a new UD number.
- The content of the slice is placed in the cache with the UD number
- as filename.
-
- Arguments:
- accno ; The accession number of the chromosome.
- start ; Start position of the slice.
- stop ; End position of the slice.
- orientation ; Orientatiion of the slice:
- 1 ; Forward.
- 2 ; Reverse complement.
-
- Inherited variables from Db.Output.Config:
- maxDldSize ; Maximum size of the slice.
+ Retrieve a slice of a chromosome.
+ If the arguments are recognised (found in the internal database),
+ we look if the associated file is still present and if so: return
+ its UD number.
+ If the arguments are recognised but no file was found, we download
+ the new slice and update the hash (and log if the hash changes).
+ If the arguments are not recognised, we download the new slice and
+ make a new UD number.
+ The content of the slice is placed in the cache with the UD number
+ as filename.
- Returns:
- string ; An UD number.
+ Inherited variables from Db.Output.Config:
+ - maxDldSize ; Maximum size of the slice.
+
+ @arg accno: The accession number of the chromosome
+ @type accno: string
+ @arg start: Start position of the slice
+ @type start: integer
+ @arg stop: End position of the slice.
+ @type stop: integer
+ @arg orientation:
+ Orientation of the slice:
+ - 1 ; Forward
+ - 2 ; Reverse complement
+ @type orientation: integer
+
+ @return: An UD number
+ @rtype: string
"""
# Not a valid slice.
@@ -463,16 +488,20 @@ class GenBankRetriever(Retriever):
def retrievegene(self, gene, organism, upstream, downstream) :
"""
- Query the NCBI for the chromosomal location of a gene and make a
- slice if the gene can be found.
+ Query the NCBI for the chromosomal location of a gene and make a
+ slice if the gene can be found.
- Arguments:
- gene ; Name of the gene.
- organism ; The organism in which we search.
- upstream ; Number of upstream nucleotides for the slice.
- downstream ; Number of downstream nucleotides for the slice.
+ @arg gene: Name of the gene
+ @type gene: string
+ @arg organism: The organism in which we search.
+ @type organism: string
+ @arg upstream: Number of upstream nucleotides for the slice.
+ @type upstream: integer
+ @arg downstream: Number of downstream nucleotides for the slice.
+ @type downstream: integer
- Returns:
+ @return: slice
+ @rtype:
"""
# Search the NCBI for a specific gene in an organism.
@@ -532,16 +561,19 @@ class GenBankRetriever(Retriever):
def downloadrecord(self, url) :
"""
- Download a GenBank record from a URL.
- If the downloaded file is recognised by its hash, the old UD number
- is used.
+ Download a GenBank record from a URL.
+ If the downloaded file is recognised by its hash, the old UD number
+ is used.
- Arguments:
- url ; Location of a GenBank record.
+ Inherited variables from Db.Output.Config:
+ - maxDldSize ; Maximum size of the file.
+ - minDldSize ; Minimum size of the file.
- Inherited variables from Db.Output.Config:
- maxDldSize ; Maximum size of the file.
- minDldSize ; Minimum size of the file.
+ @arg url: Location of a GenBank record
+ @type url: string
+
+ @return: UD or None
+ @rtype: string
"""
handle = urllib2.urlopen(url)
@@ -580,12 +612,15 @@ class GenBankRetriever(Retriever):
def uploadrecord(self, raw_data) :
"""
- Write an uploaded record to a file.
- If the downloaded file is recognised by its hash, the old UD number
- is used.
+ Write an uploaded record to a file.
+ If the downloaded file is recognised by its hash, the old UD number
+ is used.
- Arguments:
- raw_data ; A GenBank record.
+ @arg raw_data: A GenBank record
+ @type raw_data: string
+
+ @return:
+ @rtype: string?????
"""
md5sum = self._calcHash(raw_data)
@@ -603,15 +638,15 @@ class GenBankRetriever(Retriever):
def loadrecord(self, identifier) :
"""
- Load a record and return it.
- If the filename associated with the accession number is not found
- in the cache, try to re-download it.
+ Load a record and return it.
+ If the filename associated with the accession number is not found
+ in the cache, try to re-download it.
- Arguments:
- identifier ; An accession number.
+ @arg identifier: An accession number
+ @type identifier: string
- Returns:
- record ; A GenBank.Record record
+ @return: A GenBank.Record record
+ @rtype: object
"""
if (identifier[0].isdigit()) : # This is a GI identifier.
name = self._database.getGBFromGI(identifier)
@@ -660,17 +695,25 @@ class GenBankRetriever(Retriever):
class LRGRetriever(Retriever):
"""
- Retrieve a LRG record from either the cache or the web.
+ Retrieve a LRG record from either the cache or the web.
- Public methods:
- loadrecord(identifier) ; Load a record, store it in the
- cache, manage the cache and return
- the record.
+ Public methods:
+ - loadrecord(identifier) ; Load a record, store it in the cache, manage
+ the cache and return the record.
"""
def __init__(self, config, output, database):
#TODO documentation
"""
+ Initialize the class.
+
+ @todo: documentation
+ @arg config:
+ @type config:
+ @arg output:
+ @type output:
+ @arg database:
+ @type database:
"""
# Recall init of parent
@@ -681,14 +724,14 @@ class LRGRetriever(Retriever):
def loadrecord(self, identifier):
"""
- Load and parse a LRG file based on the identifier
+ Load and parse a LRG file based on the identifier
- Arguments:
- identifier ; The name of the LRG file to read
+ @arg identifier: The name of the LRG file to read
+ @type identifier: string
- Returns:
- record ; GenRecord.Record of LRG file
- None ; in case of failure
+ @return: record ; GenRecord.Record of LRG file
+ None ; in case of failure
+ @rtype:
"""
# Make a filename based upon the identifier.
@@ -714,19 +757,18 @@ class LRGRetriever(Retriever):
def fetch(self, name):
"""
- Fetch the LRG file and store in the cache directory. First try to
- grab the file from the confirmed section, if this fails, get it
- from the pending section.
+ Fetch the LRG file and store in the cache directory. First try to
+ grab the file from the confirmed section, if this fails, get it
+ from the pending section.
- Arguments:
- name ; The name of the LRG file to fetch
+ Inherited variables from Config.Retriever
+ - lrgURL ; The base url from where LRG files are fetched
- Inherited variables from Config.Retriever
- lrgURL ; The base url from where LRG files are fetched
+ @arg name: The name of the LRG file to fetch
+ @type name: string
- Returns:
- path ; the full path to the file
- None ; in case of an error
+ @return: the full path to the file; None in case of an error
+ @rtype: string
"""
prefix = self._config.lrgURL
@@ -751,18 +793,19 @@ class LRGRetriever(Retriever):
def downloadrecord(self, url, name = None) :
"""
- Download an LRG record from an URL.
+ Download an LRG record from an URL.
- Arguments:
- url ; Location of the LRG record.
+ Inherited variables from Db.Output.Config:
+ - maxDldSize ; Maximum size of the file.
+ - minDldSize ; Minimum size of the file.
- Inherited variables from Db.Output.Config:
- maxDldSize ; Maximum size of the file.
- minDldSize ; Minimum size of the file.
+ @arg url: Location of the LRG record
+ @type url: string
- Returns:
- filename ; The full path to the file
- None ; in case of failure
+ @return:
+ - filename ; The full path to the file
+ - None ; in case of failure
+ @rtype: string
"""
lrgID = name or os.path.splitext(os.path.split(url)[1])[0]
@@ -812,17 +855,18 @@ class LRGRetriever(Retriever):
def write(self, raw_data, filename) :
"""
- Write raw LRG data to a file. The data is parsed before writing,
- if a parse error occurs None is returned.
-
- Arguments:
- raw_data ; The data.
- filename ; The intended name of the file.
+ Write raw LRG data to a file. The data is parsed before writing,
+ if a parse error occurs None is returned.
- Returns:
- filename ; The full path and name of the file written
- None ; In case of an error
+ @arg raw_data: The data
+ @type raw_data: string
+ @arg filename: The intended name of the file
+ @type filename: string
+ @return:
+ - filename ; The full path and name of the file written
+ - None ; In case of an error
+ @rtype: string
"""
# Dirty way to test if a file is valid,
# Parse the file to see if it's a real LRG file.
diff --git a/src/Modules/Scheduler.py b/src/Modules/Scheduler.py
index 6c5a6eaaff71a3d257d6a2409e6b350394208926..4aabc806681e8e6f21fb90714eb0252af49a22b7 100644
--- a/src/Modules/Scheduler.py
+++ b/src/Modules/Scheduler.py
@@ -1,13 +1,23 @@
#!/usr/bin/python
"""
- Module used to add and manage the Batch Jobs
-
- Public classes:
- Scheduler ; Manages the batch jobs and contains the methods for
- * Batch Name Checker
- * Batch Syntax Checker
- * Batch Position Converter
+Module used to add and manage the Batch Jobs.
+
+@requires: subprocess
+@requires: os
+@requires: smtplib
+@requires: email.mime.text.MIMEText
+@requires: Modules.Config
+@requires: Modules.Output
+@requires: Modules.Parser
+@requires: Modules.Mapper
+@requires: Mutalyzer
"""
+# Public classes:
+# - Scheduler ; Manages the batch jobs and contains the methods for
+# - Batch Name Checker
+# - Batch Syntax Checker
+# - Batch Position Converter
+
import subprocess # subprocess.Popen
import os # os.path.exists
import smtplib # smtplib.STMP
@@ -22,41 +32,41 @@ import Mutalyzer # Mutalyzer.process
__all__ = ["Scheduler"]
-def debug(f):
+def debug(f) :
"""
- Decorator for functions called from within the daemon. Can be used
- to debug errors that are hidden because the daemon's stdout and
- errout filehandlers are closed.
+ Decorator for functions called from within the daemon. Can be used
+ to debug errors that are hidden because the daemon's stdout and
+ errout filehandlers are closed.
- Usage: Place the decorator line above the function to investigate
+ Usage: Place the decorator line above the function to investigate
- >>> @debug
- >>> def process(self) :
- >>> pass # function code
+ >>> @debug
+ >>> def process(self) :
+ >>> pass # function code
"""
#NOTE: All debug functions & methods should be moved to a DEBUG module
- def _tempf(*args):
+ def _tempf(*args) :
"""
- The decorated function is replaced by this function. Which sets up
- the filehandle to write to and print out additional debug info.
+ The decorated function is replaced by this function. Which sets up
+ the filehandle to write to and print out additional debug info.
- The original function is called from within a try, except clause
- which catches [AND DOES NOT RERAISE] an exception occuring in the
- debugged function.
+ The original function is called from within a try, except clause
+ which catches [AND DOES NOT RERAISE] an exception occuring in the
+ debugged function.
- This can result in odd behaviour, therefor the decorators should
- be removed from any production version.
+ This can result in odd behaviour, therefor the decorators should
+ be removed from any production version.
"""
of = open("/tmp/daemon.out", "a+")
- try:
+ try :
of.write("\nFunction %s\n\targs: %s\n\t" % (`f`, `args`))
ret = f(*args) # Actual function call
of.write("Returns: %s" % `ret`)
return ret
#try
- except Exception, e:
+ except Exception, e :
import traceback
of.write("\nEXCEPTION:\n")
traceback.print_exc(file=of)
@@ -67,30 +77,32 @@ def debug(f):
class Scheduler() :
"""
- Manages the batch jobs and contains the methods for
- Batch Name Checker
- Batch Syntax Checker
- Batch Position Converter
-
- Special methods:
- __init__(config, database) ;
-
- Public methods:
- addJob(outputFilter, eMail, queue, fromHost, jobType, Arg1)
- ; Add a job to the database jobqueue and start the
- batchChecker daemon.
- process() ; Iterate over & process the jobs in the jobqueue
+ Special methods:
+ - __init__(config, database) ;
+
+ Public methods:
+ - addJob(outputFilter, eMail, queue, fromHost, jobType, Arg1) ; Add a
+ job to the database jobqueue and start the batchChecker daemon.
+ - process() ; Iterate over & process the jobs in the jobqueue.
+
+ @summary: Manages the batch jobs and contains the methods for
+ - Batch Name Checker
+ - Batch Syntax Checker
+ - Batch Position Converter
"""
def __init__(self, config, database) :
#TODO: documentation
"""
- Initialize the Scheduler, which requires a config object
- and a database connection.
-
- Arguments:
- config ;
- database ;
+ Initialize the Scheduler, which requires a config object
+ and a database connection.
+
+ @todo: documentation
+
+ @arg config: Config object
+ @type config: object
+ @arg database:
+ @type database:
"""
self.__config = config
@@ -99,15 +111,18 @@ class Scheduler() :
def __sendMail(self, mailTo, url) :
"""
- Send an e-mail containing an url to a batch job submitter.
-
- Arguments:
- mailTo ; The batch job submitter.
- url ; The url containing the results.
-
- Private variables:
- __config ; The variables mailMessage, mailSubject and mailFrom
- are used.
+ Send an e-mail containing an url to a batch job submitter.
+
+ Private variables:
+ - __config ; The variables mailMessage, mailSubject and mailFrom
+ are used.
+
+ @todo: Handle Connection errors in a try, except clause
+
+ @arg mailTo: The batch job submitter
+ @type mailTo: string
+ @arg url: The url containing the results
+ @type url: string
"""
#TODO: Handle Connection errors in a try, except clause
@@ -128,73 +143,93 @@ class Scheduler() :
smtpInstance.quit()
#__sendMail
- def __processFlags(self, O, flags):
+ def __processFlags(self, O, flags) :
"""
- Translate the flags to error & info messages.
+ Translate the flags to error & info messages.
- Arguments:
- O ; Output object of the current batchentry
- flags ; Flags of the current batchentry
+ Side-effect:
+ - Added messages to the Output object.
- Returns:
- skip ; True if the entry must be skipped
+ @arg O: Output object of the current batchentry
+ @arg flags: Flags of the current batchentry
- Side-effect:
- Added messages to the Output object
+ @return: skip ; True if the entry must be skipped
+ @rtype: boolean
"""
- if not flags: return
- if 'S' in flags: #This entry is going to be skipped
+
+ if not flags :
+ return False
+ if 'S' in flags : #This entry is going to be skipped
#Add a usefull message to the Output object
- if "S0" in flags:
+ if "S0" in flags :
message = "Entry could not be formatted correctly, check "\
"batch input file help for details"
- elif "S9" in flags:
+ elif "S9" in flags :
message = "Empty Line"
- else:
+ else :
message = "Skipping entry"
O.addMessage(__file__, 4, "EBSKIP", message)
return True #skip
#if
- if 'A' in flags: #This entry is altered before execution
+ if 'A' in flags : #This entry is altered before execution
O.addMessage(__file__, 3, "WEALTER", "Entry altered before "
"execution")
+ return False
#__processFlags
- def __alterBatchEntries(self, jobID, old, new, flag, nselector):
+ def __alterBatchEntries(self, jobID, old, new, flag, nselector) :
"""
- Alias for the database.updateBatchDb method.
-
- Replace within one JobID all entries matching old with new, if
- they do not match the negative selector.
-
- Example:
- NM_002001(FCER1A_v001):c.1A>C ; this would result in the
- continuous fetching of the
- reference because no version
- number is given.
- In this case the arguments would be:
- old ; NM_002001
- new ; NM_002001.2
- nselector ; NM_002001[[.period.]]
-
- The nselector is used to prevent the replacement of
- false positives. e.g. NM_002001.1(FCER1A_v001):c.1A>C should not
- be replaced. The double bracket notation is the MySQL escape char
- for a regular expression.
+ Alias for the database.updateBatchDb method.
+
+ Replace within one JobID all entries matching old with new, if
+ they do not match the negative selector.
+
+ Example:
+ NM_002001(FCER1A_v001):c.1A>C ; this would result in the continuous
+ fetching of the reference because no version number is given.
+ In this case the arguments would be:
+ - old ; NM_002001
+ - new ; NM_002001.2
+ - nselector ; NM_002001[[.period.]]
+
+ The nselector is used to prevent the replacement of
+ false positives. e.g. NM_002001.1(FCER1A_v001):c.1A>C should not
+ be replaced. The double bracket notation is the MySQL escape char
+ for a regular expression.
+
+ @arg jobID:
+ @type jobID:
+ @arg old:
+ @type old:
+ @arg new:
+ @type new:
+ @arg flag:
+ @type flag:
+ @arg nselector:
+ @type nselector:
"""
+
self.__database.updateBatchDb(jobID, old, new, flag, nselector)
#__alterBatchEntries
- def __skipBatchEntries(self, jobID, flag, selector):
+ def __skipBatchEntries(self, jobID, flag, selector) :
"""
- Alias for the database.skipBatchDb method.
-
- Skip all batch entries that match a certain selector.
+ Alias for the database.skipBatchDb method.
+
+ Skip all batch entries that match a certain selector.
+
+ @arg jobID:
+ @type jobID:
+ @arg flag:
+ @type flag:
+ @arg selector:
+ @type selector:
"""
+
self.__database.skipBatchDb(jobID, selector, flag)
#__skipBatchEntries
- def _updateDbFlags(self, O, jobID):
+ def _updateDbFlags(self, O, jobID) :
"""
Check and set the flags for other entries of jobID.
@@ -202,13 +237,14 @@ class Scheduler() :
If these are set, this means that identical entries need to be
skipped / altered.
- Arguments:
- O ; Output object of the current batchentry
- jobID ; ID of job, so that the altering is only done within
- one job.
-
Side-effect:
- Added flags to entries in the database
+ - Added flags to entries in the database
+
+ @arg O: Output object of the current batchentry
+ @type O: object
+ @arg jobID: ID of job, so that the altering is only done within one
+ job
+ @type jobID:
"""
flags = O.getOutput("BatchFlags")
@@ -225,8 +261,8 @@ class Scheduler() :
if not flags: return
#First check if we need to skip
- for flag, args in flags:
- if 'S' in flag:
+ for flag, args in flags :
+ if 'S' in flag :
selector = args # Strip argument
O.addMessage(__file__, 3, "WBSKIP",
"All further occurrences with '%s' will be "
@@ -236,8 +272,8 @@ class Scheduler() :
#if
#for
#If not skipflags, check if we need to alter
- for flag, args in flags:
- if 'A' in flag:
+ for flag, args in flags :
+ if 'A' in flag :
old, new, nselector = args #Strip arguments
O.addMessage(__file__, 3, "WBSUBST",
"All further occurrences of %s will be substituted "
@@ -249,51 +285,53 @@ class Scheduler() :
def process(self) :
"""
- Start the mutalyzer Batch Processing. This method retrieves
- all jobs from the database and processes them in a roundrobin
- fashion. If all jobs are done the process checks if new jobs are
- added during the last processing round.
-
- This method uses two database tables, BatchJob and BatchQueue.
-
- The jobList is an array of tuples with three elements
- jobID ; The ID of the job
- jobType ; The type of the job
- argument1 ; Currently only used for the ConversionChecker
- to send the build version.
-
- If the jobList is not empty, the method will iterate once over the
- list and fetch the first entry of a job from the database table
- BatchQueue. This request returns both the input for the batch and
- the flags for the job.
-
- #Flags
- A job can be flagged in two ways:
- A ; Altered - this means that the input is altered
- before execution. This could be the case if an
- entry uses an accession number without a version.
- If a version is retrieved from the NCBI, all
- further occurences of that accession will be
- replaced by the accession with version number.
- S ; Skipped - this means that this batchentry will be
- skipped by the batchprocess. This could be the
- case if the user made a mistake that could not be
- auto fixed and henceforth all occurences of the
- mistake will be skipped.
- A Flag consists of either an A or S followed by a digit, which
- refers to the reason of alteration / skip.
+ Start the mutalyzer Batch Processing. This method retrieves
+ all jobs from the database and processes them in a roundrobin
+ fashion. If all jobs are done the process checks if new jobs are
+ added during the last processing round.
+
+ This method uses two database tables, BatchJob and BatchQueue.
+
+ The jobList is an array of tuples with three elements
+ - jobID ; The ID of the job
+ - jobType ; The type of the job
+ - argument1 ; Currently only used for the ConversionChecker
+ to send the build version.
+
+ If the jobList is not empty, the method will iterate once over the
+ list and fetch the first entry of a job from the database table
+ BatchQueue. This request returns both the input for the batch and
+ the flags for the job.
+
+ #Flags
+ A job can be flagged in two ways:
+ - A ; Altered - this means that the input is altered
+ before execution. This could be the case if an
+ entry uses an accession number without a version.
+ If a version is retrieved from the NCBI, all
+ further occurences of that accession will be
+ replaced by the accession with version number.
+ - S ; Skipped - this means that this batchentry will be
+ skipped by the batchprocess. This could be the
+ case if the user made a mistake that could not be
+ auto fixed and henceforth all occurences of the
+ mistake will be skipped.
+
+ A Flag consists of either an A or S followed by a digit, which
+ refers to the reason of alteration / skip.
"""
+
jobList = self.__database.getJobs()
while jobList :
for i, jobType, arg1 in jobList :
inputl, flags = self.__database.getFromQueue(i)
- if not(inputl is None):
- if jobType == "NameChecker":
+ if not (inputl is None) :
+ if jobType == "NameChecker" :
self._processNameBatch(inputl, i, flags)
- elif jobType == "SyntaxChecker":
+ elif jobType == "SyntaxChecker" :
self._processSyntaxCheck(inputl, i, flags)
- elif jobType == "PositionConverter":
+ elif jobType == "PositionConverter" :
self._processConversion(inputl, i, arg1, flags)
else: #unknown jobType
pass #TODO: Scream burning water and remove from Queue
@@ -307,18 +345,20 @@ class Scheduler() :
#while
#process
- def _processNameBatch(self, cmd, i, flags):
+ def _processNameBatch(self, cmd, i, flags) :
"""
- Process an entry from the Name Batch, write the results
- to the job-file. If an Exception is raised, catch and continue.
-
- Arguments:
- cmd ; The NameChecker input
- i ; The JobID
- flags ; Flags of the current entry
-
- Side-effect:
- Output written to outputfile
+ Process an entry from the Name Batch, write the results
+ to the job-file. If an Exception is raised, catch and continue.
+
+ Side-effect:
+ - Output written to outputfile.
+
+ @arg cmd: The NameChecker input
+ @type cmd:
+ @arg i: The JobID
+ @type i:
+ @arg flags: Flags of the current entry
+ @type flags:
"""
C = Config.Config()
@@ -329,18 +369,18 @@ class Scheduler() :
#Read out the flags
skip = self.__processFlags(O, flags)
- if not skip:
+ if not skip :
#Run mutalyzer and get values from Output Object 'O'
- try:
+ try :
Mutalyzer.process(cmd, C, O)
- except Exception, e:
+ except Exception, e :
#Catch all exceptions related to the processing of cmd
O.addMessage(__file__, 4, "EBATCHU",
"Unexpected error occurred, dev-team notified")
import traceback
O.addMessage(__file__, 4, "DEBUG", `traceback.format_exc()`)
#except
- finally:
+ finally :
#check if we need to update the database
self._updateDbFlags(O, i)
#if
@@ -350,14 +390,14 @@ class Scheduler() :
outputline = "%s\t" % cmd
outputline += "%s\t" % "|".join(O.getBatchMessages(3))
- if batchOutput:
+ if batchOutput :
outputline += batchOutput[0]
outputline += "\n"
#Output
filename = "%s/Results_%s.txt" % (self.__config.resultsDir, i)
- if not os.path.exists(filename):
+ if not os.path.exists(filename) :
# If the file does not yet exist, create it with the correct
# header above it. The header is read from the config file as
# a list. We need a tab delimited string.
@@ -365,7 +405,7 @@ class Scheduler() :
handle = open(filename, 'a')
handle.write("%s\n" % "\t".join(header))
#if
- else:
+ else :
handle = open(filename, 'a')
handle.write(outputline)
@@ -374,18 +414,20 @@ class Scheduler() :
"Finished NameChecker batchvariant " + cmd)
#_processNameBatch
- def _processSyntaxCheck(self, cmd, i, flags):
+ def _processSyntaxCheck(self, cmd, i, flags) :
"""
- Process an entry from the Syntax Check, write the results
- to the job-file.
-
- Arguments:
- cmd ; The Syntax Checker input
- i ; The JobID
- flags ; Flags of the current entry
-
- Side-effect:
- Output written to outputfile
+ Process an entry from the Syntax Check, write the results
+ to the job-file.
+
+ Side-effect:
+ - Output written to outputfile
+
+ @arg cmd: The Syntax Checker input
+ @type cmd:
+ @arg i: The JobID
+ @type i:
+ @arg flags: Flags of the current entry
+ @type flags:
"""
C = Config.Config()
@@ -397,19 +439,19 @@ class Scheduler() :
skip = self.__processFlags(O, flags)
#Process
- if not skip:
+ if not skip :
parsetree = P.parse(cmd)
- else:
+ else :
parsetree = None
- if parsetree:
+ if parsetree :
result = "OK"
- else:
+ else :
result = "|".join(O.getBatchMessages(3))
#Output
filename = "%s/Results_%s.txt" % (self.__config.resultsDir, i)
- if not os.path.exists(filename):
+ if not os.path.exists(filename) :
# If the file does not yet exist, create it with the correct
# header above it. The header is read from the config file as
# a list. We need a tab delimited string.
@@ -417,7 +459,7 @@ class Scheduler() :
handle = open(filename, 'a')
handle.write("%s\n" % "\t".join(header))
#if
- else:
+ else :
handle = open(filename, 'a')
handle.write("%s\t%s\n" % (cmd, result))
@@ -426,21 +468,24 @@ class Scheduler() :
"Finished SyntaxChecker batchvariant " + cmd)
#_processSyntaxCheck
- def _processConversion(self, cmd, i, build, flags):
+ def _processConversion(self, cmd, i, build, flags) :
"""
- Process an entry from the Position Converter, write the results
- to the job-file. The Position Coverter is wrapped in a try except
- block which ensures that he Batch Process keeps running. Errors
- are caught and the user will be notified.
-
- Arguments:
- cmd ; The Syntax Checker input
- i ; The JobID
- build ; The build to use for the converter
- flags ; Flags of the current entry
-
- Side-effect:
- Output written to outputfile
+ Process an entry from the Position Converter, write the results
+ to the job-file. The Position Coverter is wrapped in a try except
+ block which ensures that he Batch Process keeps running. Errors
+ are caught and the user will be notified.
+
+ Side-effect:
+ - Output written to outputfile.
+
+ @arg cmd: The Syntax Checker input
+ @type cmd: string
+ @arg i: The JobID
+ @type i: integer
+ @arg build: The build to use for the converter
+ @type build: string
+ @arg flags: Flags of the current entry
+ @type flags:
"""
C = Config.Config()
@@ -454,8 +499,8 @@ class Scheduler() :
"Received PositionCoverter batchvariant " + cmd)
skip = self.__processFlags(O, flags)
- if not skip:
- try:
+ if not skip :
+ try :
#process
converter = Mapper.Converter(build, C, O)
@@ -463,13 +508,13 @@ class Scheduler() :
variant = converter.correctChrVariant(variant)
#TODO: Parse the variant and check for c or g. This is ugly
- if not(":c." in variant or ":g." in variant):
+ if not(":c." in variant or ":g." in variant) :
#Bad name
P = Parser.Nomenclatureparser(O)
parsetree = P.parse(variant)
#if
- if ":c." in variant:
+ if ":c." in variant :
# Do the c2chrom dance
variant = converter.c2chrom(variant)
# NOTE:
@@ -480,10 +525,10 @@ class Scheduler() :
# If the input is a genomic variant or if we converted a
# coding variant to a genomic variant we try to find all
# other affected coding variants.
- if variant and ":g." in variant:
+ if variant and ":g." in variant :
# Do the chrom2c dance
variants = converter.chrom2c(variant, "dict")
- if variants:
+ if variants :
gName = variant
# Due to the cyclic behavior of the Position Converter
# we know for a fact that if a correct chrom name is
@@ -492,7 +537,7 @@ class Scheduler() :
# variants from a nested lists and store them.
cNames = [cName for cName2 in variants.values() \
for cName in cName2]
- except Exception, e:
+ except Exception, e :
#Catch all exceptions related to the processing of cmd
O.addMessage(__file__, 4, "EBATCHU",
"Unexpected error occurred, dev-team notified")
@@ -503,7 +548,7 @@ class Scheduler() :
#Output
filename = "%s/Results_%s.txt" % (self.__config.resultsDir, i)
- if not os.path.exists(filename):
+ if not os.path.exists(filename) :
# If the file does not yet exist, create it with the correct
# header above it. The header is read from the config file as
# a list. We need a tab delimited string.
@@ -511,7 +556,7 @@ class Scheduler() :
handle = open(filename, 'a')
handle.write("%s\n" % "\t".join(header))
#if
- else:
+ else :
handle = open(filename, 'a')
handle.write("%s\t%s\t%s\t%s\n" % (cmd, error, gName, "\t".join(cNames)))
@@ -524,15 +569,25 @@ class Scheduler() :
def addJob(self, outputFilter, eMail, queue, fromHost, jobType, Arg1) :
"""
- Add a job to the Database and start the BatchChecker.
-
- Arguments:
- outputFilter ; Filter the output of Mutalyzer
- eMail ; e-mail address of batch supplier
- queue ; A list of jobs
- fromHost ; From where is the request made
- jobType ; The type of Batch Job that should be run
- Arg1 ; Batch Arguments, for now only build info
+ Add a job to the Database and start the BatchChecker.
+
+ @arg outputFilter: Filter the output of Mutalyzer
+ @type outputFilter:
+ @arg eMail: e-mail address of batch supplier
+ @type eMail: string
+ @arg queue: A list of jobs
+ @type queue: list
+ @arg fromHost: From where is the request made
+ @type fromHost:
+ @arg jobType: The type of Batch Job that should be run
+ @type jobType:
+ @arg Arg1: Batch Arguments, for now only build info
+ @type Arg1:
+
+ @return: jobID
+ @rtype:
+
+ @todo: outputFilter is not used
"""
#TODO: outputFilter is not used
@@ -550,12 +605,14 @@ class Scheduler() :
# output in terms of input line and outputline.
if inputl.startswith("~!"): #Dirty Escape
inputl = inputl[2:]
- if inputl:
+ if inputl :
flag = "S0" # Flag for wrong format
- else:
+ else :
flag = "S9" # Flag for empty line
inputl = " " #Database doesn't like an empty inputfield
- else:
+ #else
+ #if
+ else :
flag = None
self.__database.addToQueue(jobID, inputl, flag)
diff --git a/src/Modules/Serializers.py b/src/Modules/Serializers.py
index 57d3e68eb8f3d757e72c8869bbcd6c3c13f88046..954b2a1ebc0134b896ab9ba162ea13b6c3bd9d22 100644
--- a/src/Modules/Serializers.py
+++ b/src/Modules/Serializers.py
@@ -1,5 +1,16 @@
+#!/usr/bin/python
+
"""
- Collection of Serilizable Objects used by the webservice
+Collection of Serilizable Objects used by the webservice
+
+@requires: soaplib.serializers.primitive.String
+@requires: soaplib.serializers.primitive.Integer
+@requires: soaplib.serializers.primitive.Array
+@requires: soaplib.serializers.clazz.ClassSerializer
+@requires: ZSI.TC
+@requires: ZSI.fault.Fault
+
+@todo: documentation
"""
from soaplib.serializers.primitive import String, Integer, Array
from soaplib.serializers.clazz import ClassSerializer
@@ -8,11 +19,11 @@ from ZSI.fault import Fault
class SoapMessage(ClassSerializer):
"""
- Send info message over the soapline
+ Send info message over the soapline
- Attributes:
- errorcode ; The error code affiliated with the error message
- message ; The error message
+ Attributes:
+ - errorcode ; The error code affiliated with the error message
+ - message ; The error message
"""
class types():
@@ -27,21 +38,21 @@ class SoapMessage(ClassSerializer):
class Mapping(ClassSerializer) :
"""
- Extended ClassSerializer object with mixed types of attributes
-
- Attributes:
- startmain ; Define the type of startmain.
- startoffset ; Define the type of startoffset.
- endmain ; Define the type of endmain value.
- endoffset ; Define the type of endoffset value.
- start_g ; Define the type of start_g value.
- end_g ; Define the type of end_g value.
- mutationType ; Define the type of mutation type
+ Extended ClassSerializer object with mixed types of attributes
+
+ Attributes:
+ - startmain ; Define the type of startmain.
+ - startoffset ; Define the type of startoffset.
+ - endmain ; Define the type of endmain value.
+ - endoffset ; Define the type of endoffset value.
+ - start_g ; Define the type of start_g value.
+ - end_g ; Define the type of end_g value.
+ - mutationType ; Define the type of mutation type
"""
class types() :
"""
- Types are defined here for the soaplib module.
+ Types are defined here for the soaplib module.
"""
startmain = Integer
@@ -57,7 +68,7 @@ class Mapping(ClassSerializer) :
def __init__(self) :
"""
- Types are defined here for the TC module.
+ Types are defined here for the TC module.
"""
self.typecode = TC.Struct(Mapping, [
@@ -78,12 +89,12 @@ class Mapping(ClassSerializer) :
class Transcript(ClassSerializer) :
"""
- Extended ClassSerializer object with mixed types of attributes
+ Extended ClassSerializer object with mixed types of attributes
- Attributes:
- trans_start ; Define the type of trans_start
- trans_stop ; Define the type of trans_stop
- CDS_stop ; Define the type of CDS_stop
+ Attributes:
+ - trans_start ; Define the type of trans_start
+ - trans_stop ; Define the type of trans_stop
+ - CDS_stop ; Define the type of CDS_stop
"""
class types() :
diff --git a/src/Modules/Web.py b/src/Modules/Web.py
index 635a86d1e551b1b2a65bbb414bb9c1dc137baa77..d1ce5eb92513925fd2182feed1604f117c7abd7b 100644
--- a/src/Modules/Web.py
+++ b/src/Modules/Web.py
@@ -1,11 +1,19 @@
#!/usr/bin/python
"""
- Module that provides general functions used by the web interfaces.
-
- Public classes:
- Web ; General functions used by the web interfaces.
+Module that provides general functions used by the web interfaces.
+
+@requires: sys
+@requires: re
+@requires: urllib
+@requires: cStringIO.StringIO
+@requires: simpletal.simpleTALES
+@requires: simpletal.simpleTAL
+@requires: Config
"""
+# Public classes:
+# - Web ; General functions used by the web interfaces.
+
import sys # sys.stdout
import re # match
@@ -19,27 +27,27 @@ import Config
class Web() :
"""
- General functions used by the web interfaces.
+ General functions used by the web interfaces.
- Public variables:
- version ; This is the version that is displayed on the web pages,
- WSDL files, etc.
+ Public variables:
+ - version ; This is the version that is displayed on the web pages,
+ WSDL files, etc.
- Special methods:
- __init__() ; Initialise the class.
+ Special methods:
+ - __init__() ; Initialise the class.
- Public methods:
- run(func, *args) ; Run func(*args) and return stdout.
- tal(scheme, filename, args) ; Compile a TAL template to HTML or XML.
- read(path, req) ; Read a file and return the content.
+ Public methods:
+ - run(func, *args) ; Run func(*args) and return stdout.
+ - tal(scheme, filename, args) ; Compile a TAL template to HTML or XML.
+ - read(path, req) ; Read a file and return the content.
"""
def __init__(self) :
"""
- Initialise the class.
+ Initialise the class.
- Public variables (altered):
- version ; Here the displayed version is defined.
+ Public variables (altered):
+ - version ; Here the displayed version is defined.
"""
self.version = "2.0 β-5"
@@ -52,14 +60,15 @@ class Web() :
def run(self, func, *args) :
"""
- Run any function and return standard output as a string.
+ Run any function and return standard output as a string.
- Arguments:
- func ; The function that has to be called.
- *args ; The arguments of func.
+ @arg func: The function that has to be called
+ @type func: function
+ @arg args: arguments for the function to call
+ @type args: list
- Returns:
- string ; Everything that func(*args) writes to standard output.
+ @return: Everything that func(*args) writes to standard output
+ @rtype: string
"""
old_stdout = sys.stdout
@@ -74,17 +83,20 @@ class Web() :
def tal_old(self, scheme, filename, args) :
#TODO merge this function with 'tal' (below).
"""
- Compile a TAL template to HTML or XML.
-
- Arguments:
- scheme ; Either "HTML" or "XML", output will be in this
- format.
- filename ; The filename of the template.
- args ; A dictionary with variables (whose name correspond
- to the ones in the template) and their values.
-
- Returns:
- string ; An HTML or XML file.
+ Compile a TAL template to HTML or XML.
+
+ @todo: merge this function with 'tal'
+
+ @arg scheme: Either "HTML" or "XML", output will be in this format
+ @type scheme: string
+ @arg filename: The filename of the template
+ @type filename: string
+ @arg args: A dictionary with variables (whose name correspond to
+ the ones in the template) and their values
+ @type args: dictionary
+
+ @return: An HTML or XML file
+ @rtype: string
"""
from simpletal import simpleTALES # context(), addGlobal()
@@ -118,17 +130,18 @@ class Web() :
def tal(self, scheme, filename, args) :
"""
- Compile a TAL template to HTML or XML.
-
- Arguments:
- scheme ; Either "HTML" or "XML", output will be in this
- format.
- filename ; The filename of the template.
- args ; A dictionary with variables (whose name correspond
- to the ones in the template) and their values.
-
- Returns:
- string ; An HTML or XML file.
+ Compile a TAL template to HTML or XML.
+
+ @arg scheme: Either "HTML" or "XML", output will be in this format
+ @type scheme: string
+ @arg filename: The filename of the template
+ @type filename: string
+ @arg args: A dictionary with variables (whose name correspond to
+ the ones in the template) and their values
+ @type args: dictionary
+
+ @return: An HTML or XML file
+ @rtype: string
"""
context = simpleTALES.Context()
@@ -164,14 +177,15 @@ class Web() :
def read(self, path, req) :
"""
- Read a file and return its content.
+ Read a file and return its content.
- Arguments:
- path ; Path to the file.
- req ; HTTP request (used to extract the filename).
+ @arg path: Path to the file
+ @type path: string
+ @arg req: HTTP request (used to extract the filename)
+ @type req: string
- Returns:
- string ; The content of the file.
+ @return: The content of the file
+ @rtype: string
"""
handle = open(path + req.uri.split('/', 2)[2], "r")
@@ -184,6 +198,13 @@ class Web() :
def isEMail(self, eMail) :
#TODO documentation
"""
+ Check if argument is a valid email address.
+
+ @arg eMail: email address to check
+ @type eMail: string
+
+ @return: True or False
+ @rtype: boolean
"""
if re.match("^[a-zA-Z0-9._%-]+@[a-zA-Z0-9._%-]+.[a-zA-Z]{2,6}$",
@@ -195,6 +216,11 @@ class Web() :
def urlEncode(self, descriptions) :
#TODO documentation
"""
+ @arg descriptions:
+ @type descriptions: list
+
+ @return: urlEncode descriptions???????????????
+ @rtype: list
"""
newDescr = []
diff --git a/src/Modules/__init__.py b/src/Modules/__init__.py
index 10629c4230034104ab132399156ba023ce75add4..9465c89daf7379f84f782fb9124f933cbe65ac07 100644
--- a/src/Modules/__init__.py
+++ b/src/Modules/__init__.py
@@ -1,14 +1,16 @@
"""
- Public modules:
- Config ;
- Crossmap ;
- Db ;
- GenRecord ;
- Misc ;
- Mutator ;
- Output ;
- Parser ;
- Retriever ;
- Scheduler ;
- Web ;
+@organization: Leiden University Medical Center (LUMC)
+@copyright: 2010, Jeroen Laros, LUMC
"""
+# Public modules:
+# - Config ;
+# - Crossmap ;
+# - Db ;
+# - GenRecord ;
+# - Misc ;
+# - Mutator ;
+# - Output ;
+# - Parser ;
+# - Retriever ;
+# - Scheduler ;
+# - Web ;
diff --git a/src/Mutalyzer.py b/src/Mutalyzer.py
index 9c7477de186ffb12c976b3b428f15124df9539da..5036fe7ef03bc4203e248dfc8ab818f9c7749979 100644
--- a/src/Mutalyzer.py
+++ b/src/Mutalyzer.py
@@ -1,7 +1,29 @@
#!/usr/bin/python
"""
- The nomenclature checker.
+The nomenclature checker.
+
+@requires: sys
+@requires: math
+@requires: types
+@requires: Bio
+@requires: Bio.Seq
+@requires: Bio.Seq.Seq
+@requires: Bio.Alphabet.IUPAC
+@requires: Bio.SeqUtils.seq3
+@requires: Bio.Restriction
+@requires: Modules.Retriever
+@requires: Modules.GenRecord
+@requires: Modules.Crossmap
+@requires: Modules.Parser
+@requires: Modules.Db
+@requires: Modules.Mutator
+@requires: Modules.Output
+@requires: Modules.Config
+@requires: operator.itemgetter
+@requires: operator.attrgetter
+
+@todo: SET TO FALSE DEBUG FLAG
"""
import sys
@@ -31,14 +53,15 @@ DEBUG = False
def __formatRange(pos1, pos2) :
"""
- Simplify a range to one position when applicable.
+ Simplify a range to one position when applicable.
- Arguments:
- pos1 ; First coordinate of a range.
- pos2 ; Second coordinate of a range.
+ @arg pos1: First coordinate of a range
+ @type pos1: integer
+ @arg pos2: Second coordinate of a range
+ @type pos2: integer
- Returns:
- string ; pos1_pos2 in case of a real range, pos1 otherwise.
+ @return: pos1_pos2 in case of a real range, pos1 otherwise
+ @rtype: string
"""
if pos1 == pos2 :
@@ -48,13 +71,13 @@ def __formatRange(pos1, pos2) :
def __intronicPosition(Loc) :
"""
- Check whether a location is intronic.
+ Check whether a location is intronic.
- Arguments:
- Loc ; A location from the Parser module.
+ @arg Loc: A location from the Parser module
+ @type Loc:
- Returns:
- boolean ; True if the location is intronic, False otherwise.
+ @return: True if the location is intronic, False otherwise
+ @rtype: boolean
"""
if not Loc :
@@ -68,18 +91,20 @@ def __intronicPosition(Loc) :
def __checkIntronPosition(main, offset, transcript) :
"""
- Check whether a c. position is really in an intron: The main coordinate
- must be a splice site and the offset coordinate must have the correct
- sign.
-
- Arguments:
- main ; Main coordinate of the position.
- offset ; Offset coordinate of the position.
- transcript ; Transcript under scrutiny.
-
- Returns:
- boolean ; True if the combination (main, offset) is valid for this
- transcript. False otherwise.
+ Check whether a c. position is really in an intron: The main coordinate
+ must be a splice site and the offset coordinate must have the correct
+ sign.
+
+ @arg main: Main coordinate of the position
+ @type main: integer
+ @arg offset: Offset coordinate of the position
+ @type offset: integer
+ @arg transcript: Transcript under scrutiny
+ @type transcript: object
+
+ @return: True if the combination (main, offset) is valid for this
+ transcript, False otherwise
+ @rtype: boolean
"""
main_g = transcript.CM.x2g(main, 0)
@@ -105,22 +130,23 @@ def __checkIntronPosition(main, offset, transcript) :
def __roll(ref, start, stop) :
"""
- Determine the variability of a variant by looking at cyclic
- permutations. Not all cyclic permutations are tested at each time, it
- is sufficient to check ``aW'' if ``Wa'' matches (with ``a'' a letter,
- ``W'' a word) when rolling to the left for example.
-
- Arguments:
- ref ; A reference sequence.
- start ; Start position of the pattern in the reference sequence.
- stop ; End position of the pattern in the reference sequence.
-
- Returns:
- tuple:
- left ; Amount of positions that the pattern can be shifted to
- the left.
- right ; Amount of positions that the pattern can be shifted to
- the right.
+ Determine the variability of a variant by looking at cyclic
+ permutations. Not all cyclic permutations are tested at each time, it
+ is sufficient to check ``aW'' if ``Wa'' matches (with ``a'' a letter,
+ ``W'' a word) when rolling to the left for example.
+
+ @arg ref: A reference sequence
+ @type ref: string
+ @arg start: Start position of the pattern in the reference sequence
+ @type start: integer
+ @arg stop: End position of the pattern in the reference sequence.
+ @type stop: integer
+
+ @return: tuple:
+ - left ; Amount of positions that the pattern can be shifted to the left
+ - right ; Amount of positions that the pattern can be shifted to the
+ right
+ @rtype: tuple (integer, integer)
"""
pattern = ref[start - 1:stop] # Extract the pattern.
@@ -147,16 +173,16 @@ def __roll(ref, start, stop) :
def __palinsnoop(string) :
"""
- Check a sequence for a reverse-complement-palindromic prefix (and
- suffix). If one is detected, return the length of this prefix. If the
- string equals its reverse complement, return -1.
+ Check a sequence for a reverse-complement-palindromic prefix (and
+ suffix). If one is detected, return the length of this prefix. If the
+ string equals its reverse complement, return -1.
- Arguments:
- string ; A nucleotide sequence.
+ @arg string: A nucleotide sequence
+ @type string: string
- Returns:
- integer ; The number of elements that are palindromic or -1 if the
- string is a ``palindrome''.
+ @return: The number of elements that are palindromic or -1 if the string is
+ a "palindrome".
+ @rtype: string
"""
revcomp = Bio.Seq.reverse_complement(string)
@@ -170,6 +196,7 @@ def __palinsnoop(string) :
def __bprint(s, O, where) :
# FIXME obsoleted function (replaced by __bprint2()), but still used.
"""
+ @todo: FIXME obsoleted function (replaced by __bprint2()), but still used.
"""
if not s :
@@ -194,21 +221,25 @@ def __bprint(s, O, where) :
def __insertTag(s, pos1, pos2, tag1, tag2) :
"""
- Insert two tags (tag1 and tag2) in string s at positions pos1 and pos2
- respectively if the positions are within the length of s. If not,
- either insert one tag or do nothing. If pos1 equals pos2, don't do
- anything either.
-
- Arguments:
- s ; A sequence.
- pos1 ; Position of tag1.
- pos2 ; Position of tag2.
- tag1 ; Content of tag1.
- tag2 ; Content of tag2.
-
- Returns:
- string ; The original sequence, or a sequence with eiter tag1,
- tag2 or both tags inserted.
+ Insert two tags (tag1 and tag2) in string s at positions pos1 and pos2
+ respectively if the positions are within the length of s. If not,
+ either insert one tag or do nothing. If pos1 equals pos2, don't do
+ anything either.
+
+ @arg s: A sequence
+ @type s:
+ @arg pos1: Position of tag1
+ @type pos1:
+ @arg pos2: Position of tag2
+ @type pos2:
+ @arg tag1: Content of tag1
+ @type tag1:
+ @arg tag2: Content of tag2
+ @type tag2:
+
+ @return: The original sequence, or a sequence with eiter tag1, tag2 or both
+ tags inserted.
+ @rtype: string
"""
output = s
@@ -227,15 +258,19 @@ def __insertTag(s, pos1, pos2, tag1, tag2) :
def __bprint2(s, pos1, pos2, O, where) :
"""
- Make a fancy representation of a protein and put it in the Output
- object under the name ``where''.
-
- Arguments:
- s ; A protein sequence.
- pos1 ; First position to highlight.
- pos2 ; Last position to highlight.
- O ; The Output object.
- where ; Location in the Output object to store the representation.
+ Make a fancy representation of a protein and put it in the Output
+ object under the name "where".
+
+ @arg s: A protein sequence
+ @type s: string
+ @arg pos1: First position to highlight
+ @type pos1:
+ @arg pos2: Last position to highlight
+ @type pos2:
+ @arg O: The Output object
+ @type O: object
+ @arg where: Location in the Output object to store the representation
+ @type where:
"""
if not s :
@@ -269,14 +304,14 @@ def __bprint2(s, pos1, pos2, O, where) :
def __PtLoc2main(Loc) :
"""
- Convert the main coordinate in a location (from the Parser) to an
- integer.
+ Convert the main coordinate in a location (from the Parser) to an
+ integer.
- Arguments:
- Loc ; A location.
+ @arg Loc: A location
+ @type Loc: object
- Returns:
- integer ; Integer representation of the main coordinate.
+ @return: Integer representation of the main coordinate
+ @rtype: integer
"""
main = int(Loc.Main)
@@ -288,14 +323,14 @@ def __PtLoc2main(Loc) :
def __PtLoc2offset(Loc) :
"""
- Convert the offset coordinate in a location (from the Parser) to an
- integer.
+ Convert the offset coordinate in a location (from the Parser) to an
+ integer.
- Arguments:
- Loc ; A location.
+ @arg Loc: A location.
+ @type Loc: object
- Returns;
- integer ; Integer representation of the offset coordinate.
+ @return: Integer representation of the offset coordinate
+ @rtype: integer
"""
if Loc.Offset :
@@ -312,16 +347,17 @@ def __PtLoc2offset(Loc) :
def __splice(string, splice_sites) :
"""
- Construct the transcript or the coding sequence from a record and
- a list of splice sites.
+ Construct the transcript or the coding sequence from a record and
+ a list of splice sites.
- Arguments:
- record ; A GenBank record (see the BioPython documentation).
- splice_sites ; A list of even length of integers.
+ @arg string: a DNA sequence
+ @type string: string
+ @arg splice_sites: A list of even length of integers.
+ @type splice_sites: list
- Returns:
- String ; The concatenation of slices from the sequence that is
- present in the GenBank record.
+ @return: The concatenation of slices from the sequence that is present in
+ the GenBank record
+ @rtype: string
"""
transcript = ""
@@ -335,6 +371,7 @@ def __splice(string, splice_sites) :
def __nsplice(string, splice_sites, CDS, orientation) :
#FIXME document this.
"""
+ @todo: documentation
"""
transcript = ""
@@ -364,14 +401,14 @@ def __nsplice(string, splice_sites, CDS, orientation) :
def __cdsLen(splice_sites) :
"""
- Calculate the length of a CDS.
+ Calculate the length of a CDS.
- Arguments:
- splice_sites ; The coordinates of the CDS including internal splice
- sites.
+ @arg splice_sites: The coordinates of the CDS including internal splice
+ sites.
+ @type splice_sites: list
- Returns:
- integer ; Length of the CDS.
+ @return: Length of the CDS
+ @rtype: integer
"""
l = 0
@@ -383,13 +420,13 @@ def __cdsLen(splice_sites) :
def __checkDNA(arg) :
"""
- Check whether a string is a DNA string.
+ Check whether a string is a DNA string.
- Arguments:
- arg ; Any string.
+ @arg arg: Any string
+ @type arg: string
- Returns:
- boolean ; True if the string is a DNA string, False otherwise.
+ @return: True if the string is a DNA string, False otherwise
+ @rtype: boolean
"""
for i in str(arg) :
@@ -400,18 +437,22 @@ def __checkDNA(arg) :
def __checkOptArg(ref, p1, p2, arg, O) :
"""
- Do several checks for the optional argument of a variant.
-
-
- Arguments:
- ref ; The reference sequence.
- p1 ; Start position of the variant.
- p2 ; End position of the variant.
- arg ; The optional argument.
- O ; The Output object.
-
- Returns:
- boolean ; True if the optional argument is correct, False otherwise.
+ Do several checks for the optional argument of a variant.
+
+
+ @arg ref: The reference sequence
+ @type ref: string
+ @arg p1: Start position of the variant
+ @type p1: integer
+ @arg p2: End position of the variant
+ @type p2: integer
+ @arg arg: The optional argument
+ @type arg:
+ @arg O: The Output object
+ @type O: object
+
+ @return: True if the optional argument is correct, False otherwise.
+ @rtype: boolean
"""
if arg : # The argument is optional, if it is not present, it is correct.
@@ -446,14 +487,15 @@ def __checkOptArg(ref, p1, p2, arg, O) :
def __lcp(str1, str2) :
"""
- Calculate the length of the longest common prefix of two strings.
+ Calculate the length of the longest common prefix of two strings.
- Arguments:
- str1 ; The first string.
- str2 ; The second string.
+ @arg str1: The first string
+ @type str1: string
+ @arg str2: The second string
+ @type str2: string
- Returns:
- integer ; The length of the longest common prefix of str1 and str2.
+ @return: The length of the longest common prefix of str1 and str2
+ @rtype: integer
"""
pos = 0
@@ -468,14 +510,15 @@ def __lcp(str1, str2) :
def __lcs(str1, str2) :
"""
- Calculate the length of the longest common suffix of two strings.
+ Calculate the length of the longest common suffix of two strings.
- Arguments:
- str1 ; The first string.
- str2 ; The second string.
+ @arg str1: The first string
+ @type str1: string
+ @arg str2: The second string
+ @type str2: string
- Returns:
- integer ; The length of the longest common suffix of str1 and str2.
+ @return: The length of the longest common suffix of str1 and str2
+ @rtype: integer
"""
t1 = str1[::-1] # Invert str1.
@@ -487,20 +530,21 @@ def __lcs(str1, str2) :
def findInFrameDescription(str1, str2) :
"""
- Give a description of an inframe difference of two proteins. Also give
- the position at which the proteins start to differ and the positions at
- which they are the same again.
-
- Arguments:
- str1 ; The original protein.
- str2 ; The mutated protein.
-
- Retuns:
- vector:
- string ; Protein description of the change.
- integer ; Start position of the change.
- integer ; End position of the change in the first protein.
- integer ; End position of the change in the second protein.
+ Give a description of an inframe difference of two proteins. Also give
+ the position at which the proteins start to differ and the positions at
+ which they are the same again.
+
+ @arg str1: The original protein
+ @type str1: string
+ @arg str2: The mutated protein
+ @type str2: string
+
+ @return: vector:
+ - string ; Protein description of the change
+ - integer ; Start position of the change
+ - integer ; End position of the change in the first protein
+ - integer ; End position of the change in the second protein
+ @rtype: string
"""
# Nothing happened.
@@ -562,22 +606,23 @@ def findInFrameDescription(str1, str2) :
def findFrameShift(str1, str2) :
"""
- Give the description of an out of frame difference between two
- proteins. Give a description of an inframe difference of two proteins.
- Also give the position at which the proteins start to differ and the
- end positions (to be compatible with the findInFrameDescription()
- function).
-
- Arguments:
- str1 ; The original protein.
- str2 ; The mutated protein.
-
- Retuns:
- vector:
- string ; Protein description of the change.
- integer ; Start position of the change.
- integer ; End position of the first protein.
- integer ; End position of the second protein.
+ Give the description of an out of frame difference between two
+ proteins. Give a description of an inframe difference of two proteins.
+ Also give the position at which the proteins start to differ and the
+ end positions (to be compatible with the findInFrameDescription()
+ function).
+
+ @arg str1: The original protein
+ @type str1: string
+ @arg str2: The mutated protein
+ @type str2: string
+
+ @return: vector:
+ - string ; Protein description of the change.
+ - integer ; Start position of the change.
+ - integer ; End position of the first protein.
+ - integer ; End position of the second protein.
+ @rtype: string
"""
lcp = __lcp(str1, str2)
@@ -593,20 +638,22 @@ def findFrameShift(str1, str2) :
def __toProtDescr(CDSStop, orig, trans) :
"""
- Wrapper function for the findInFrameDescription() and findFrameShift()
- functions. It uses the value CDSStop to decide which one to call.
-
- Arguments:
- CDSStop ; Position of the stop codon in c. notation (CDS length).
- orig ; The original protein.
- trans ; The mutated protein.
-
- Retuns:
- vector:
- string ; Protein description of the change.
- integer ; Start position of the change.
- integer ; End position of the change in the first protein.
- integer ; End position of the change in the second protein.
+ Wrapper function for the findInFrameDescription() and findFrameShift()
+ functions. It uses the value CDSStop to decide which one to call.
+
+ @arg CDSStop: Position of the stop codon in c. notation (CDS length)
+ @type CDSStop: integer
+ @arg orig: The original protein
+ @type orig: string
+ @arg trans: The mutated protein
+ @type trans: string
+
+ @return: vector:
+ - string ; Protein description of the change.
+ - integer ; Start position of the change.
+ - integer ; End position of the change in the first protein.
+ - integer ; End position of the change in the second protein.
+ @rtype: tuple (string, integer, integer, integer)
"""
if CDSStop % 3 :
@@ -620,16 +667,16 @@ def __toProtDescr(CDSStop, orig, trans) :
def __trim2(str1, str2) :
"""
- Given two strings, trim the lcp and the lcs.
+ Given two strings, trim the lcp and the lcs.
- Arguments:
- str1 ; A string.
- str2 ; An other string.
+ @arg str1: A string
+ @type str1: string
+ @arg str2: An other string
+ @type str2: string
- Returns:
- tuple:
- string ; Trimmed version of str1.
- string ; Trimmed version of str2.
+ @return: tuple:
+ - string: Trimmed version of str1.
+ - string: Trimmed version of str2.
"""
lcp = __lcp(str1, str2)
@@ -640,17 +687,18 @@ def __trim2(str1, str2) :
def __rangeToC(M, g1, g2) :
# FIXME apparently obsolete.
"""
- Convert a genomic range to a CDS oriented range.
-
- Arguments:
- M ;
- g1 ;
- g2 ;
-
- Returns:
- tuple:
- string ;
- string ;
+ Convert a genomic range to a CDS oriented range.
+
+ @arg M:
+ @type M:
+ @arg g1:
+ @type g1:
+ @arg g2:
+ @type g2:
+
+ @return: tuple (string, string)
+ @rtype: tuple
+ @todo: FIXME apparently obsolete.
"""
if M.orientation == -1 :
@@ -661,10 +709,14 @@ def __rangeToC(M, g1, g2) :
def _createBatchOutput(O):
#TODO More documentation.
"""
- Format the results to a batch output.
+ Format the results to a batch output.
- Filter the mutalyzer output
+ Filter the mutalyzer output
+
+ @arg O:
+ @type O:
+ @todo: More documentation.
"""
goi, toi = O.getOutput("geneSymbol")[-1] # Two strings [can be empty]
tList = [] # Temporary List
@@ -750,13 +802,18 @@ def checkSubstitution(start_g, Arg1, Arg2, MUU, GenRecordInstance, O) :
Do a semantic check for substitutions, do the actual substitution
and give it a name.
- Arguments:
- start_g ; Genomic location of the substitution.
- Arg1 ; Nucleotide in the reference sequence.
- Arg2 ; Nucleotide in the mutated sequence.
- MUU ; A Mutator object.
- GenRecordInstance ; A GenRecord object.
- O ; The Output object.
+ @arg start_g: Genomic location of the substitution
+ @type start_g: integer
+ @arg Arg1: Nucleotide in the reference sequence.
+ @type Arg1: string
+ @arg Arg2: Nucleotide in the mutated sequence.
+ @type Arg2: string
+ @arg MUU: A Mutator object.
+ @type MUU: object
+ @arg GenRecordInstance: A GenRecord object.
+ @type GenRecordInstance: object
+ @arg O: The Output object.
+ @type O: object
"""
if not __checkDNA(Arg2) : # It must be DNA.
@@ -775,16 +832,21 @@ def checkSubstitution(start_g, Arg1, Arg2, MUU, GenRecordInstance, O) :
def checkDeletionDuplication(start_g, end_g, mutationType, MUU,
GenRecordInstance, O) :
"""
- Do a semantic check for a deletion or duplication, do the actual
- deletion/duplication and give it a name.
-
- Arguments:
- start_g ; Genomic start position of the del/dup.
- end_g ; Genomic end position of the del/dup.
- mutationType ; The type (del or dup).
- MUU ; A Mutator object.
- GenRecordInstance ; A GenRecord object.
- O ; The Output object.
+ Do a semantic check for a deletion or duplication, do the actual
+ deletion/duplication and give it a name.
+
+ @arg start_g : Genomic start position of the del/dup
+ @type start_g: integer
+ @arg end_g: Genomic end position of the del/dup
+ @type end_g: integer
+ @arg mutationType: The type (del or dup)
+ @type mutationType: string
+ @arg MUU: A Mutator object
+ @type MUU: object
+ @arg GenRecordInstance: A GenRecord object
+ @type GenRecordInstance: object
+ @arg O: The Output object
+ @type O: object
"""
roll = __roll(MUU.orig, start_g, end_g)
@@ -826,6 +888,7 @@ def checkDeletionDuplication(start_g, end_g, mutationType, MUU,
def checkInversion(start_g, end_g, MUU, GenRecordInstance, O) :
"""
+ @todo: documentation
"""
snoop = __palinsnoop(MUU.orig[start_g - 1:end_g])
@@ -866,6 +929,7 @@ def checkInversion(start_g, end_g, MUU, GenRecordInstance, O) :
def checkInsertion(start_g, end_g, Arg1, MUU, GenRecordInstance, O) :
"""
+ @todo: documentation
"""
if start_g + 1 != end_g :
@@ -927,6 +991,7 @@ def checkInsertion(start_g, end_g, Arg1, MUU, GenRecordInstance, O) :
def __ivs2g(location, transcript) :
"""
+ @todo: documentation
"""
ivsNumber = int(location.IVSNumber)
@@ -943,6 +1008,7 @@ def __ivs2g(location, transcript) :
def __ex2g(location, transcript) :
"""
+ @todo: documentation
"""
numberOfExons = transcript.CM.numberOfExons()
@@ -965,6 +1031,7 @@ def __ex2g(location, transcript) :
def __normal2g(RawVar, transcript) :
"""
+ @todo: documentation
"""
if not RawVar.StartLoc.PtLoc.Main.isdigit() :
@@ -1014,6 +1081,7 @@ def __normal2g(RawVar, transcript) :
def __rv(MUU, RawVar, GenRecordInstance, parts, O, transcript) :
"""
+ @todo: documentation
"""
# FIXME check this
@@ -1166,6 +1234,9 @@ def __rv(MUU, RawVar, GenRecordInstance, parts, O, transcript) :
#__rv
def __ppp(MUU, parts, GenRecordInstance, O) :
+ """
+ @todo: documentation
+ """
if parts.RawVar or parts.SingleAlleleVarSet :
if parts.RefType == 'r' :
O.addMessage(__file__, 4, "ERNA", "Descriptions on RNA level " \
@@ -1331,6 +1402,9 @@ def __ppp(MUU, parts, GenRecordInstance, O) :
#__ppp
def process(cmd, C, O) :
+ """
+ @todo: documentation
+ """
parser = Parser.Nomenclatureparser(O)
O.addOutput("inputvariant", cmd)
ParseObj = parser.parse(cmd)
@@ -1565,6 +1639,9 @@ def process(cmd, C, O) :
#process
def main(cmd) :
+ """
+ @todo: documentation
+ """
C = Config.Config()
O = Output.Output(__file__, C.Output)
diff --git a/src/UCSC_update.py b/src/UCSC_update.py
index 14ac44b283f4655ff5d6f516aeb458b7ff94ce35..82e1c07394b14a61ce178858141bb045b8297ec5 100644
--- a/src/UCSC_update.py
+++ b/src/UCSC_update.py
@@ -1,9 +1,17 @@
#!/usr/bin/python
"""
- Get updates on mapping information from the UCSC.
+Get updates on mapping information from the UCSC.
- This program is intended to be run daily from cron.
+This program is intended to be run daily from cron.
+
+@requires: sys
+@requires: os
+
+@requires: Modules.Config
+@requires: Modules.Output
+@requires: Modules.Remote
+@requires: Modules.Update
"""
import sys # sys.argv
diff --git a/src/VarInfo.py b/src/VarInfo.py
index 39cd40f3ea0224af0e11be4128f4012e6766c6a2..2756496960057d907e95f0770e9b1e33ac6e45cf 100644
--- a/src/VarInfo.py
+++ b/src/VarInfo.py
@@ -1,20 +1,28 @@
#!/usr/bin/python
"""
- Search for an NM number in the MySQL database, if the version number
- matches, get the start and end positions in a variant and translate these
- positions to g. notation if the variant is in c. notation and vice versa.
-
+Search for an NM number in the MySQL database, if the version number
+matches, get the start and end positions in a variant and translate these
+positions to I{g.} notation if the variant is in I{c.} notation and vice versa.
- If no end position is present, the start position is assumed to be the
end position.
- If the version number is not found in the database, an error message is
generated and a suggestion for an other version is given.
- If the reference sequence is not found at all, an error is returned.
- If no variant is present, the transcription start and end and CDS end
- in c. notation is returned.
+ in I{c.} notation is returned.
- If the variant is not accepted by the nomenclature parser, a parse error
will be printed.
+@requires: sys
+@requires: Modules.Db
+@requires: Modules.Crossmap
+@requires: Modules.Parser
+@requires: Modules.Output
+@requires: Modules.Config
+@requires: Modules.Mapper
+
+@todo: documentation
"""
import sys # argv
@@ -28,11 +36,13 @@ from Modules import Mapper
def __sl2il(l) :
"""
- Convert a list of strings to a list of integers.
-
- Arguments: l ; A list of strings.
+ Convert a list of strings to a list of integers.
+
+ @arg l: A list of strings
+ @type l: list
- Returns: list ; A list of integers.
+ @return: A list of integers
+ @rtype: list
"""
for i in range(len(l)) :
@@ -42,18 +52,21 @@ def __sl2il(l) :
def __getcoords(C, Loc, Type) :
"""
- Return main, offset and g positions given either a position in
- c. or in g. notation.
-
- Arguments:
- C ; A crossmapper.
- Loc ; Either a location in g. or c. notation.
- Type ; The reference type.
- Returns:
- triple:
- 0 ; Main coordinate in c. notation.
- 1 ; Offset coordinate in c. notation.
- 2 ; Position in g. notation.
+ Return main, offset and g positions given either a position in
+ I{c.} or in I{g.} notation.
+
+ @arg C: A crossmapper
+ @type C: object
+ @arg Loc: Either a location in I{g.} or I{c.} notation
+ @type Loc: object
+ @arg Type: The reference type
+ @type Type: character
+
+ @return: triple:
+ - 0 ; Main coordinate in I{c.} notation
+ - 1 ; Offset coordinate in I{c.} notation
+ - 2 ; Position in I{g.} notation
+ @rtype: triple (integer, integer, integer)
"""
if Type == 'c' :
@@ -71,31 +84,37 @@ def __getcoords(C, Loc, Type) :
def main(LOVD_ver, build, acc, var) :
"""
- The entry point (called by the HTML publisher).
-
- Arguments:
- LOVD_ver ; The LOVD version (ignored for now).
- build ; The human genome build.
- acc ; The NM accession number and version.
- var ; The variant, or empty.
-
- Returns:
- start_main ; The main coordinate of the start position in c.
- (non-star) notation.
- start_offset ; The offset coordinate of the start position in c.
- notation (intronic position).
- end_main ; The main coordinate of the end position in c.
- (non-star) notation.
- end_offset ; The offset coordinate of the end position in c.
- notation (intronic position).
- start_g ; The g. notation of the start position.
- end_g ; The g. notation of the end position.
- type ; The mutation type.
-
- Returns (alternative):
- trans_start ; Transcription start in c. notation.
- trans_stop ; Transcription stop in c. notation.
- CDS_stop ; CDS stop in c. notation.
+ The entry point (called by the HTML publisher).
+
+ Returns:
+ - start_main ; The main coordinate of the start position in I{c.}
+ (non-star) notation.
+ - start_offset ; The offset coordinate of the start position in I{c.}
+ notation (intronic position).
+ - end_main ; The main coordinate of the end position in I{c.}
+ (non-star) notation.
+ - end_offset ; The offset coordinate of the end position in I{c.}
+ notation (intronic position).
+ - start_g ; The I{g.} notation of the start position.
+ - end_g ; The I{g.} notation of the end position.
+ - type ; The mutation type.
+
+ Returns (alternative):
+ - trans_start ; Transcription start in I{c.} notation.
+ - trans_stop ; Transcription stop in I{c.} notation.
+ - CDS_stop ; CDS stop in I{c.} notation.
+
+ @arg LOVD_ver: The LOVD version (ignored for now)
+ @type LOVD_ver: string
+ @arg build: The human genome build
+ @type build: string
+ @arg acc: The NM accession number and version
+ @type acc: string
+ @arg var: The variant, or empty
+ @type var: string
+
+ @return:
+ @rtype:
"""
C = Config.Config()
diff --git a/src/handler.py b/src/handler.py
index 12a3a488ddaf2d477fb9be5102c3e28b07e717c0..026ebcaeb4edeaf9549722977f7e50e7049fcaeb 100644
--- a/src/handler.py
+++ b/src/handler.py
@@ -1,13 +1,24 @@
#!/usr/bin/python
"""
- General handler for mod_python.
-
- This handler calls the webservices handler, the HTML publisher or handles
- a request itself, depending on keywords in the URI of the request.
-
- Public methods:
- handler(req) ; The handler.
+General handler for mod_python.
+
+This handler calls the webservices handler, the HTML publisher or handles
+a request itself, depending on keywords in the URI of the request.
+
+Public methods:
+ - handler(req) ; The handler.
+
+@requires: os
+@requires: bz2
+@requires: ZSI.dispatch
+@requires: soaplib.client.make_service_client
+@requires: mod_python.apache
+@requires: mod_python.publisher
+@requires: Modules.Web
+@requires: Modules.Config
+@requires: Modules.File
+@requires: webservice
"""
import os
@@ -24,28 +35,28 @@ import webservice
def handler(req):
"""
- Handle a request passed to us by mod_python.
-
- Keywords in the URI of the request are used to decide what to do:
- "services" ; Dispatch the webservices handler.
- ".js" ; Return the raw content of the file (to include
- JavaScript from an HTML file).
- ".py" ; Return the content as a downloadable file after it has
- been processed by TAL (to generate webservice client
- files).
- ".wsdl" ; Return the content of the file after it has been
- processed by TAL (to generate a WSDL file that refers
- to the correct server).
- By default, the HTML publisher is used for normal HTML files and other
- unhandled requests.
-
- Arguments:
- req ; The request.
-
- Returns:
- int ; An apache return code, either generated in this function
- itself, or by the publisher handler which handles normal HTML
- requests.
+ Handle a request passed to us by mod_python.
+
+ Keywords in the URI of the request are used to decide what to do:
+ - "services" ; Dispatch the webservices handler.
+ - ".js" ; Return the raw content of the file (to include JavaScript
+ from an HTML file).
+ - ".py" ; Return the content as a downloadable file after it has
+ been processed by TAL (to generate webservice client
+ files).
+ - ".wsdl" ; Return the content of the file after it has been
+ processed by TAL (to generate a WSDL file that refers to
+ the correct server).
+
+ By default, the HTML publisher is used for normal HTML files and other
+ unhandled requests.
+
+ @arg req: The request
+ @type req: string
+
+ @return: An apache return code, either generated in this function
+ itself, or by the publisher handler which handles normal HTML requests
+ @rtype: integer
"""
# Figure out where this program is located and go to the parent directory.
diff --git a/src/index.py b/src/index.py
index 061e94ccd90c8dbce08ab5a9b9d8f7bd0602118a..931e078d1ad5890ea401a60b104c822e056553a6 100644
--- a/src/index.py
+++ b/src/index.py
@@ -1,14 +1,34 @@
#!/usr/bin/python
"""
- The HTML publisher.
-
- These functions appear as HTML pages on the web server.
-
- Public methods:
- index(req) ; The mutation checker page.
- Variant_info(req) ; The g. to c. and vice versa interface for LOVD.
- download(req) ; The download page.
+The HTML publisher.
+
+These functions appear as HTML pages on the web server.
+
+Public methods:
+ - index(req) ; The mutation checker page.
+ - Variant_info(req) ; The I{g.} to I{c.} and vice versa interface for LOVD.
+ - download(req) ; The download page.
+
+@requires: Mutalyzer
+@requires: VarInfo
+@requires: pydoc
+@requires: webservice
+@requires: string
+
+@requires: mod_python import apache
+@requires: mod_python import Session
+@requires: mod_python import util
+
+@requires: Modules.Parser
+@requires: Modules.Mapper
+@requires: Modules.Web
+@requires: Modules.Config
+@requires: Modules.Output
+@requires: Modules.Db
+@requires: Modules.Scheduler
+@requires: Modules.Retriever
+@requires: Modules.File
"""
import Mutalyzer
@@ -32,9 +52,20 @@ from Modules import Retriever
from Modules import File
class InputException(Exception):
+ """
+ @todo: documentation
+ """
pass
def snp(req) :
+ """
+ @todo: documentation
+
+ @arg req: the HTTP request
+ @type req: object
+ @return: compiled TAL template
+ @rtype: object
+ """
C = Config.Config()
O = Output.Output(__file__, C.Output)
W = Web.Web()
@@ -61,39 +92,70 @@ def snp(req) :
def index(req) :
+ """
+ @todo: documentation
+
+ @arg req: the HTTP request
+ @type req: object
+ @return: compiled TAL template
+ @rtype: object
+ """
W = Web.Web()
return W.tal("HTML", "templates/index.html", {})
#index
def help(req) :
+ """
+ @todo: documentation
+
+ @arg req: the HTTP request
+ @type req: object
+ @return: compiled TAL template
+ @rtype: object
+ """
W = Web.Web()
return W.tal("HTML", "templates/help.html", {})
#about
def about(req) :
+ """
+ @todo: documentation
+
+ @arg req: the HTTP request
+ @type req: object
+ @return: compiled TAL template
+ @rtype: object
+ """
W = Web.Web()
return W.tal("HTML", "templates/about.html", {})
#about
def nameGenerator(req):
+ """
+ @todo: documentation
+
+ @arg req: the HTTP request
+ @type req: object
+ @return: compiled TAL template
+ @rtype: object
+ """
W = Web.Web()
return W.tal("HTML", "templates/generator.html", {})
#generator
def check(req) :
"""
- The mutation checker page.
+ The mutation checker page.
- If the incoming request has a form, run Mutalyzer. The output of
- Mutalyzer is used together with a version and the last posted value
- to make an HTML page from a TAL template.
+ If the incoming request has a form, run Mutalyzer. The output of
+ Mutalyzer is used together with a version and the last posted value
+ to make an HTML page from a TAL template.
- Arguments:
- req ; The request:
- req.form['mutationName'] ; A description of a variant.
+ @arg req: The request: req.form['mutationName'] ; A description of a variant
+ @type req: object
- Returns:
- string ; An HTML page containing the results of Mutalyzer.
+ @return: a compiled TAL template containing the results of Mutalyzer
+ @rtype: object
"""
W = Web.Web()
@@ -172,26 +234,25 @@ def check(req) :
def getGS(req):
"""
- LOVD bypass to get the correct GeneSymbol incl Transcript variant.
-
- Used by LOVD to get the correct transcript variant out of a genomic
- record. LOVD uses a genomic reference (NC_?) in combination with a gene
- symbol to pass variant info to mutalyzer. Mutalyzer 1.0 was only using
- the first transcript. LOVD supplies the NM of the transcript needed but
- this was ignored. This helper allows LOVD to get the requested
- transcript variant from a genomic reference.
-
- Arguments:
- req ; The request:
- req.form['mutationName'] ; the mutationname without
- gene symbol
- re.form['variantRecord'] ; the NM reference of the
- variant
- re.form['forward'] ; if set this forwards the
- request to the name checker
- Returns
- string ; The GeneSymbol with the variant notation
- web ; If forward is set the request is forwarded to check
+ LOVD bypass to get the correct GeneSymbol incl Transcript variant.
+
+ Used by LOVD to get the correct transcript variant out of a genomic
+ record. LOVD uses a genomic reference (NC_?) in combination with a gene
+ symbol to pass variant info to mutalyzer. Mutalyzer 1.0 was only using
+ the first transcript. LOVD supplies the NM of the transcript needed but
+ this was ignored. This helper allows LOVD to get the requested
+ transcript variant from a genomic reference.
+
+ @arg req: The request:
+ - req.form['mutationName'] ; the mutationname without gene symbol
+ - re.form['variantRecord'] ; the NM reference of the variant
+ - re.form['forward'] ; if set this forwards the request to the name
+ checker
+ @type req:
+
+ @return:
+ - string ; The GeneSymbol with the variant notation
+ - web ; If forward is set the request is forwarded to check
"""
W = Web.Web()
C = Config.Config()
@@ -223,6 +284,12 @@ def getGS(req):
def checkForward(req) :
+ """
+ @arg req:
+ @type req:
+
+ @todo: documentation
+ """
session = Session.Session(req)
session['mut'] = req.form.get("mutationName", None)
session.save()
@@ -232,15 +299,15 @@ def checkForward(req) :
def syntaxCheck(req) :
"""
- Checks the syntax of a variant
+ Checks the syntax of a variant
- Arguments:
- req ; The request:
- req.form['variant'] ; A description of the variant.
+ @arg req: The request:
+ req.form['variant'] ; A description of the variant
+ @type req: object
- Returns:
- string ; An HTML page containing the remark if the variant syntax
- is OK or not
+ @return: An HTML page containing the remark if the variant syntax is OK or
+ not
+ @rtype: string
"""
W = Web.Web()
@@ -278,6 +345,12 @@ def syntaxCheck(req) :
#checkingSyntax
def positionConverter(req):
+ """
+ @arg req:
+ @type req:
+
+ @todo: documentation
+ """
W = Web.Web()
C = Config.Config()
O = Output.Output(__file__, C.Output)
@@ -337,17 +410,17 @@ def positionConverter(req):
def Variant_info(req) :
"""
- The g. to c. and vice versa interface for LOVD.
+ The I{g.} to I{c.} and vice versa interface for LOVD.
- Arguments:
- req ; The request:
- req.form['LOVD_ver'] ; The version of the calling LOVD.
- req.form['build'] ; The human genome build (hg19 assumed).
- req.form['acc'] ; The accession number (NM number).
- req.form['var'] ; A description of the variant.
+ @arg req: The request:
+ - req.form['LOVD_ver'] ; The version of the calling LOVD
+ - req.form['build'] ; The human genome build (hg19 assumed)
+ - req.form['acc'] ; The accession number (NM number)
+ - req.form['var'] ; A description of the variant
+ @type req: object
- Returns:
- string ; An HTML page containing the results of Variant_info.
+ @return: An HTML page containing the results of Variant_info
+ @rtype: string
"""
W = Web.Web()
@@ -369,13 +442,13 @@ def Variant_info(req) :
def webservices(req) :
"""
- The download page.
+ The download page.
- Arguments:
- req ; The request.
+ @arg req: The request
+ @type req: object
- Returns:
- string ; An HTML page.
+ @return: An HTML page
+ @rtype: object
"""
W = Web.Web()
@@ -386,6 +459,14 @@ def webservices(req) :
#download
def __checkInt(inpv, refname):
+ """
+ @arg inpv:
+ @type inpv:
+ @arg refname:
+ @type refname:
+
+ @todo: documentation
+ """
#remove , . and -
inpv = inpv.replace(',','').replace('.','').replace('-','')
try:
@@ -395,6 +476,13 @@ def __checkInt(inpv, refname):
def upload(req) :
"""
+ @arg req:
+ @type req:
+
+ @return:
+ @rtype:
+
+ @todo: documentation
"""
C = Config.Config()
@@ -469,7 +557,15 @@ def upload(req) :
def progress(req):
"""
- Progress page for batch runs
+ Progress page for batch runs
+
+ @arg req:
+ @type req:
+
+ @return:
+ @rtype:
+
+ @todo: documentation
"""
W = Web.Web()
C = Config.Config()
@@ -499,7 +595,18 @@ def progress(req):
def batch(req, batchType=None):
"""
- Batch function to add batch jobs to the Database
+ Batch function to add batch jobs to the Database
+
+ @arg batchType: Type of the batch job
+ @type batchType: string
+
+
+ @arg req: the HTTP request
+ @type req: object
+ @return: compiled TAL template
+ @rtype: object
+
+ @todo: documentation
"""
W = Web.Web()
C = Config.Config()
@@ -560,15 +667,41 @@ def batch(req, batchType=None):
#batch
def disclaimer(req) :
+ """
+ @arg req: the HTTP request
+ @type req: object
+ @return: compiled TAL template
+ @rtype: object
+
+ @todo: documentation
+ """
W = Web.Web()
return W.tal("HTML", "templates/disclaimer.html", [])
#disclaimer
def batchNameChecker(req):
+ """
+ @arg req:
+ @type req:
+
+ @return:
+ @rtype:
+
+ @todo: documentation
+ """
return batch(req, "NameChecker")
#batchCheck
def batchPositionConverter(req):
+ """
+ @arg req:
+ @type req:
+
+ @return:
+ @rtype:
+
+ @todo: documentation
+ """
return batch(req, "PositionConverter")
#batchConvert
@@ -578,13 +711,13 @@ def batchSyntaxChecker(req):
def documentation(req) :
"""
- Generate documentation for the webservice.
+ Generate documentation for the webservice.
- Arguments:
- req ; The request.
+ @arg req: The HTTP request
+ @type req: object
- Returns:
- string ; An HTML page.
+ @return: An HTML page
+ @rtype: string
"""
htmldoc = pydoc.HTMLDoc()
@@ -594,6 +727,15 @@ def documentation(req) :
#TODO: taltest.html does not exist
def taltest(req) :
+ """
+ @arg req: the HTTP request
+ @type req: object
+ @return: compiled TAL template
+ @rtype: object
+
+ @todo: taltest.html does not exist
+ @todo: documentation
+ """
W = Web.Web()
C = Config.Config()
variant = ""
diff --git a/src/webservice.py b/src/webservice.py
index aa718f0ffbb1d1a88faf116f8c493675c2ecea74..44168c451251530456993fd92c6fc806c22ffb17 100644
--- a/src/webservice.py
+++ b/src/webservice.py
@@ -1,11 +1,29 @@
#!/usr/bin/python
"""
- Mutalyzer webservices.
-
- Public classes:
- MutalyzerService ; Mutalyzer webservices.
+Mutalyzer webservices.
+
+@requires: soaplib.wsgi_soap.SimpleWSGISoapApp
+@requires: soaplib.service.soapmethod
+@requires: soaplib.serializers.primitive.String
+@requires: soaplib.serializers.primitive.Integer
+@requires: soaplib.serializers.primitive.Array
+@requires: ZSI.fault.Fault
+
+@requires: Modules.Web
+@requires: Modules.Db
+@requires: Modules.Output
+@requires: Modules.Config
+@requires: Modules.Parser
+@requires: Modules.Mapper
+
+@requires: Modules.Serializers.SoapMessage
+@requires: Modules.Serializers.Mapping
+@requires: Modules.Serializers.Transcript
"""
+# Public classes:
+# - MutalyzerService ; Mutalyzer webservices.
+
from soaplib.wsgi_soap import SimpleWSGISoapApp
from soaplib.service import soapmethod
@@ -25,48 +43,46 @@ from Modules.Serializers import SoapMessage, Mapping, Transcript, \
class MutalyzerService(SimpleWSGISoapApp) :
"""
- Mutalyzer webservices.
-
- These methods are made public via a SOAP interface.
-
- Private methods:
- __checkBuild(L, D, build) ; Check if the build is supported.
- __checkChrom(L, D, chrom) ; Check if the chromosome is in our
- database.
- __checkPos(L, pos) ; Check if the position is valid.
-
- Public methods:
- getTranscripts(build, chrom, ; Get all transcripts that overlap
- pos) with a chromosomal position.
- getTranscriptsRange(build, ; Get all transcripts that overlap
- chrom, with a range on a chromosome.
- pos1,
- pos2,
- method)
- getGeneName(build, accno) ; Find the gene name associated with a
- transcript.
- mappingInfo(LOVD_ver, build, ; Convert a transcript coordinate to a
- accNo, variant) chromosomal one, or vice versa.
- transcriptInfo(LOVD_ver, ; Find transcription start and end,
- build, and CDS end (in c. notation) for a
- accNo) given transcript.
- cTogConversion(self, build, ; Convert c. to g.
- variant)
- gTocConversion(self, build, ; Convert g. to c.
- variant)
+ Mutalyzer webservices.
+
+ These methods are made public via a SOAP interface.
+
+ Private methods:
+ - __checkBuild(L, D, build) ; Check if the build is supported.
+ - __checkChrom(L, D, chrom) ; Check if the chromosome is in our
+ database.
+ - __checkPos(L, pos) ; Check if the position is valid.
+
+ Public methods:
+ - getTranscripts(build, chrom, pos); Get all transcripts that overlap
+ with a chromosomal position.
+ - getTranscriptsRange(build, chrom, pos1, pos2, method) ; Get all
+ transcripts that overlap with a range on a chromosome.
+ - getGeneName(build, accno) ; Find the gene name associated with a
+ transcript.
+ - mappingInfo(LOVD_ver, build, accNo, variant) ; Convert a transcript
+ coordinate to a chromosomal one, or vice versa.
+ - transcriptInfo(LOVD_ver, build, accNo) ; Find transcription start and
+ end, and CDS end (in I{c.} notation) for a given transcript.
+ - cTogConversion(self, build, variant) ; Convert I{c.} to I{g.}
+ - gTocConversion(self, build, variant) ; Convert I{g.} to I{c.}
+
"""
- def __checkBuild(self, build, config) :
+ def __checkBuild(self, L, build, config) :
"""
- Check if the build is supported (hg18 or hg19).
+ Check if the build is supported (hg18 or hg19).
+
- Arguments:
- L ; An output object for logging.
- D ; A handle to the database.
- build ; The build name that needs to be checked.
+ Returns:
+ - Nothing (but raises an EARG exception).
- Returns:
- Nothing (but raises an EARG exception).
+ @arg L: an output object for logging
+ @type L: object
+ @arg build: The human genome build name that needs to be checked
+ @type build: string
+ @arg config: configuration object of the Db module
+ @type config: object
"""
if not build in config.dbNames :
@@ -79,15 +95,17 @@ class MutalyzerService(SimpleWSGISoapApp) :
def __checkChrom(self, L, D, chrom) :
"""
- Check if the chromosome is in our database.
+ Check if the chromosome is in our database.
- Arguments:
- L ; An output object for logging.
- D ; A handle to the database.
- chrom ; The name of the chromosome.
+ Returns:
+ - Nothing (but raises an EARG exception).
- Returns:
- Nothing (but raises an EARG exception).
+ @arg L: An output object for logging
+ @type L: object
+ @arg D: A handle to the database.
+ @type D: object
+ @arg chrom: The name of the chromosome
+ @type chrom: string
"""
if not D.isChrom(chrom) :
@@ -100,14 +118,15 @@ class MutalyzerService(SimpleWSGISoapApp) :
def __checkPos(self, L, pos) :
"""
- Check if the position is valid.
+ Check if the position is valid.
- Arguments:
- L ; An output object for logging.
- pos ; The position.
+ Returns:
+ - Nothing (but raises an ERANGE exception).
- Returns:
- Nothing (but raises an ERANGE exception).
+ @arg L: An output object for logging
+ @type L: object
+ @arg pos: The position
+ @type pos: integer
"""
if pos < 1 :
@@ -119,14 +138,15 @@ class MutalyzerService(SimpleWSGISoapApp) :
def __checkVariant(self, L, variant) :
"""
- Check if a variant is provided.
+ Check if a variant is provided.
- Arguments:
- L ; An output object for logging.
- variant ; The variant.
+ Returns:
+ - Nothing (but raises an EARG exception).
- Returns:
- Nothing (but raises an EARG exception).
+ @arg L: An output object for logging
+ @type L: object
+ @arg variant: The variant
+ @type variant: string
"""
if not variant :
@@ -139,21 +159,23 @@ class MutalyzerService(SimpleWSGISoapApp) :
@soapmethod(String, String, Integer, _returns = Array(String))
def getTranscripts(self, build, chrom, pos) :
"""
- Get all the transcripts that overlap with a chromosomal position.
-
- Arguments:
- string build ; The build name encoded as "hg18" or "hg19".
- string chrom ; A chromosome encoded as "chr1", ..., "chrY".
- int pos ; A postion on the chromosome.
-
- Returns:
- string ; A list of transcripts.
-
- On error an exception is raised:
- detail ; Human readable description of the error.
- faultstring: ; A code to indicate the type of error.
- EARG ; The argument was not valid.
- ERANGE ; An invalid range was given.
+ Get all the transcripts that overlap with a chromosomal position.
+
+ On error an exception is raised:
+ - detail ; Human readable description of the error.
+ - faultstring: ; A code to indicate the type of error.
+ - EARG ; The argument was not valid.
+ - ERANGE ; An invalid range was given.
+
+ @arg build: The human genome build (hg19 or hg18)
+ @type build: string
+ @arg chrom: A chromosome encoded as "chr1", ..., "chrY"
+ @type chrom: string
+ @arg pos: A position on the chromosome
+ @type pos: integer
+
+ @return: A list of transcripts
+ @rtype: list
"""
C = Config.Config()
@@ -163,7 +185,7 @@ class MutalyzerService(SimpleWSGISoapApp) :
"Received request getTranscripts(%s %s %s)" % (build,
chrom, pos))
- self.__checkBuild(build, C.Db)
+ self.__checkBuild(L, build, C.Db)
D = Db.Mapping(build, C.Db)
self.__checkChrom(L, D, chrom)
@@ -196,7 +218,7 @@ class MutalyzerService(SimpleWSGISoapApp) :
"Received request getTranscriptsByGene(%s %s)" % (build,
name))
- self.__checkBuild(build, C.Db)
+ self.__checkBuild(L, build, C.Db)
D = Db.Mapping(build, C.Db)
ret = D.get_TranscriptsByGeneName(name)
@@ -208,23 +230,26 @@ class MutalyzerService(SimpleWSGISoapApp) :
#getTranscriptsByGene
@soapmethod(String, String, Integer, Integer, Integer,
- _returns = Array(String))
+ _returns = Array(String))
def getTranscriptsRange(self, build, chrom, pos1, pos2, method) :
"""
- Get all the transcripts that overlap with a range on a chromosome.
-
- Arguments:
- string build ; The build name encoded as "hg18" or "hg19".
- string chrom ; A chromosome encoded as "chr1", ..., "chrY".
- int pos1 ; The first postion of the range.
- int pos2 ; The last postion of the range.
- int method ; The method of determining overlap:
- 0 ; Return only the transcripts that completely
- fall in the range [pos1, pos2].
- 1 ; Return all hit transcripts.
-
- Returns:
- string ; A list of transcripts.
+ Get all the transcripts that overlap with a range on a chromosome.
+
+ @arg build: The human genome build (hg19 or hg18)
+ @type build: string
+ @arg chrom: A chromosome encoded as "chr1", ..., "chrY"
+ @type chrom: string
+ @arg pos1: The first postion of the range
+ @type pos1: integer
+ @arg pos2: The last postion of the range
+ @type pos2: integer
+ @arg method: The method of determining overlap:
+ - 0 ; Return only the transcripts that completely fall in the range
+ [pos1, pos2].
+ - 1 ; Return all hit transcripts
+
+ @return: A list of transcripts
+ @rtype: list
"""
C = Config.Config()
@@ -235,7 +260,7 @@ class MutalyzerService(SimpleWSGISoapApp) :
chrom, pos1, pos2, method))
D = Db.Mapping(build, C.Db)
- self.__checkBuild(build, C.Db)
+ self.__checkBuild(L, build, C.Db)
ret = D.get_Transcripts(chrom, pos1, pos2, method)
@@ -253,14 +278,15 @@ class MutalyzerService(SimpleWSGISoapApp) :
@soapmethod(String, String, _returns = String)
def getGeneName(self, build, accno) :
"""
- Find the gene name associated with a transcript.
+ Find the gene name associated with a transcript.
- Arguments:
- string build ; The build name encoded as "hg18" or "hg19".
- string accno ; The identifier of a transcript.
+ @arg build: The human genome build (hg19 or hg18)
+ @type build: string
+ @arg accno: The identifier of a transcript
+ @type accno: string
- Returns:
- string ; The name of the associated gene.
+ @return: The name of the associated gene
+ @rtype: string
"""
C = Config.Config()
@@ -270,7 +296,7 @@ class MutalyzerService(SimpleWSGISoapApp) :
"Received request getGeneName(%s %s)" % (build, accno))
D = Db.Mapping(build, C.Db)
- self.__checkBuild(build, C.Db)
+ self.__checkBuild(L, build, C.Db)
ret = D.get_GeneName(accno.split('.')[0])
@@ -285,43 +311,42 @@ class MutalyzerService(SimpleWSGISoapApp) :
@soapmethod(String, String, String, String, _returns = Mapping)
def mappingInfo(self, LOVD_ver, build, accNo, variant) :
"""
- Search for an NM number in the MySQL database, if the version
- number matches, get the start and end positions in a variant and
- translate these positions to g. notation if the variant is in c.
- notation and vice versa.
-
- - If no end position is present, the start position is assumed to
- be the end position.
- - If the version number is not found in the database, an error
- message is generated and a suggestion for an other version is
- given.
- - If the reference sequence is not found at all, an error is
- returned.
- - If no variant is present, an error is returned.
- - If the variant is not accepted by the nomenclature parser, a
- parse error will be printed.
-
-
- Arguments (all strings):
- LOVD_ver ; The LOVD version.
- build ; The human genome build (hg19 or hg18).
- accNo ; The NM accession number and version.
- variant ; The variant.
-
- Returns:
- complex object:
- start_main ; The main coordinate of the start position
- in c. (non-star) notation.
- start_offset ; The offset coordinate of the start position
- in c. notation (intronic position).
- end_main ; The main coordinate of the end position in
- c. (non-star) notation.
- end_offset ; The offset coordinate of the end position in
- c. notation (intronic position).
- start_g ; The g. notation of the start position.
- end_g ; The g. notation of the end position.
- type ; The mutation type.
-
+ Search for an NM number in the MySQL database, if the version
+ number matches, get the start and end positions in a variant and
+ translate these positions to I{g.} notation if the variant is in I{c.}
+ notation and vice versa.
+
+ - If no end position is present, the start position is assumed to be
+ the end position.
+ - If the version number is not found in the database, an error message
+ is generated and a suggestion for an other version is given.
+ - If the reference sequence is not found at all, an error is returned.
+ - If no variant is present, an error is returned.
+ - If the variant is not accepted by the nomenclature parser, a parse
+ error will be printed.
+
+ @arg LOVD_ver: The LOVD version
+ @type LOVD_ver: string
+ @arg build: The human genome build (hg19 or hg18)
+ @type build: string
+ @arg accNo: The NM accession number and version
+ @type accNo: string
+ @arg variant: The variant
+ @type variant: string
+
+ @return: complex object:
+ - start_main ; The main coordinate of the start position
+ in I{c.} (non-star) notation.
+ - start_offset ; The offset coordinate of the start position
+ in I{c.} notation (intronic position).
+ - end_main ; The main coordinate of the end position in
+ I{c.} (non-star) notation.
+ - end_offset ; The offset coordinate of the end position in
+ I{c.} notation (intronic position).
+ - start_g ; The I{g.} notation of the start position.
+ - end_g ; The I{g.} notation of the end position.
+ - type ; The mutation type.
+ @rtype: object
"""
C = Config.Config()
@@ -345,21 +370,22 @@ class MutalyzerService(SimpleWSGISoapApp) :
@soapmethod(String, String, String, _returns = Transcript)
def transcriptInfo(self, LOVD_ver, build, accNo) :
"""
- Search for an NM number in the MySQL database, if the version
- number matches, the transcription start and end and CDS end
- in c. notation is returned.
-
-
- Arguments (all strings:
- LOVD_ver ; The LOVD version.
- build ; The human genome build (hg19 or hg18).
- accNo ; The NM accession number and version.
-
- Returns:
- complex object:
- trans_start ; Transcription start in c. notation.
- trans_stop ; Transcription stop in c. notation.
- CDS_stop ; CDS stop in c. notation.
+ Search for an NM number in the MySQL database, if the version
+ number matches, the transcription start and end and CDS end
+ in I{c.} notation is returned.
+
+ @arg LOVD_ver: The LOVD version
+ @type LOVD_ver: string
+ @arg build: The human genome build (hg19 or hg18)
+ @type build: string
+ @arg accNo: The NM accession number and version
+ @type accNo: string
+
+ @return: complex object:
+ - trans_start ; Transcription start in I{c.} notation.
+ - trans_stop ; Transcription stop in I{c.} notation.
+ - CDS_stop ; CDS stop in I{c.} notation.
+ @rtype: object
"""
C = Config.Config()
@@ -381,14 +407,15 @@ class MutalyzerService(SimpleWSGISoapApp) :
@soapmethod(String, String, _returns = String)
def chromAccession(self, build, name) :
"""
- Get the accession number of a chromosome, given a name.
+ Get the accession number of a chromosome, given a name.
- Arguments:
- build ; The human genome build.
- name ; The name of a chromosome.
+ @arg build: The human genome build (hg19 or hg18)
+ @type build: string
+ @arg name: The name of a chromosome (e.g. chr1)
+ @type name: string
- Returns:
- string ; The accession number of a chromosome.
+ @return: The accession number of a chromosome
+ @rtype: string
"""
C = Config.Config() # Read the configuration file.
D = Db.Mapping(build, C.Db)
@@ -397,7 +424,7 @@ class MutalyzerService(SimpleWSGISoapApp) :
L.addMessage(__file__, -1, "INFO",
"Received request chromAccession(%s %s)" % (build, name))
- self.__checkBuild(build, C.Db)
+ self.__checkBuild(L, build, C.Db)
self.__checkChrom(L, D, name)
result = D.chromAcc(name)
@@ -413,14 +440,15 @@ class MutalyzerService(SimpleWSGISoapApp) :
@soapmethod(String, String, _returns = String)
def chromosomeName(self, build, accNo) :
"""
- Get the name of a chromosome, given a chromosome accession number.
+ Get the name of a chromosome, given a chromosome accession number.
- Arguments:
- build ; The human genome build.
- accNo ; The accession number of a chromosome (NC_...).
+ @arg build: The human genome build (hg19 or hg18)
+ @type build: string
+ @arg accNo: The accession number of a chromosome (NC_...)
+ @type accNo: string
- Returns:
- string ; The name of a chromosome.
+ @return: The name of a chromosome
+ @rtype: string
"""
C = Config.Config() # Read the configuration file.
D = Db.Mapping(build, C.Db)
@@ -429,7 +457,7 @@ class MutalyzerService(SimpleWSGISoapApp) :
L.addMessage(__file__, -1, "INFO",
"Received request chromName(%s %s)" % (build, accNo))
- self.__checkBuild(build, C.Db)
+ self.__checkBuild(L, build, C.Db)
# self.__checkChrom(L, D, name)
result = D.chromName(accNo)
@@ -445,14 +473,15 @@ class MutalyzerService(SimpleWSGISoapApp) :
@soapmethod(String, String, _returns = String)
def getchromName(self, build, acc) :
"""
- Get the chromosome name, given a transcript identifier (NM number).
+ Get the chromosome name, given a transcript identifier (NM number).
- Arguments:
- build ; The human genome build.
- acc ; The NM accession number (version NOT included)
+ @arg build: The human genome build (hg19 or hg18)
+ @type build: string
+ @arg acc: The NM accession number (version NOT included)
+ @type acc: string
- Returns:
- string ; The name of a chromosome.
+ @return: The name of a chromosome
+ @rtype: string
"""
C = Config.Config() # Read the configuration file.
D = Db.Mapping(build, C.Db)
@@ -461,7 +490,7 @@ class MutalyzerService(SimpleWSGISoapApp) :
L.addMessage(__file__, -1, "INFO",
"Received request getchromName(%s %s)" % (build, acc))
- self.__checkBuild(build, C.Db)
+ self.__checkBuild(L, build, C.Db)
# self.__checkChrom(L, D, name)
result = D.get_chromName(acc)
@@ -477,17 +506,17 @@ class MutalyzerService(SimpleWSGISoapApp) :
@soapmethod(String, String, _returns = Array(String))
def numberConversion(self, build, variant) :
"""
- Converts c. to g. notation or vice versa
-
+ Converts I{c.} to I{g.} notation or vice versa
- Arguments (all strings:
- build ; The human genome build (hg19 or hg18).
- variant ; The variant in either c. or g. notation, full HGVS
- notation, including NM_ or NC_ accession number.
- Returns:
- string; The variant in either g. or c. notation.
+ @arg build: The human genome build (hg19 or hg18)
+ @type build: string
+ @arg variant: The variant in either I{c.} or I{g.} notation, full HGVS
+ notation, including NM_ or NC_ accession number
+ @type variant: string
+ @return: The variant in either I{g.} or I{c.} notation
+ @rtype: string
"""
C = Config.Config() # Read the configuration file.
@@ -513,8 +542,15 @@ class MutalyzerService(SimpleWSGISoapApp) :
#numberConversion
@soapmethod(String, _returns = String)
- def checkSyntax(self, variant) :
+ def checkSyntax(self, variant):
"""
+ Checks the syntax of a variant.
+
+ @arg variant: the variant to check
+ @type variant: string
+
+ @return: message
+ @rtype: string
"""
C = Config.Config() # Read the configuration file.
L = Output.Output(__file__, C.Output)