From 8131c606e9e80d1f3e9387b0d97411d6bf57925b Mon Sep 17 00:00:00 2001
From: "J.F.J. Laros" <j.f.j.laros@lumc.nl>
Date: Sat, 4 Aug 2012 12:07:35 +0000
Subject: [PATCH] Added a webservice function for the description extractor.
rpc.py:
- Added the function descriptionExtract().
- Standardised indentation.
models.py:
- Added a RawVar and an Allele class for the webservices.
describe.py:
- Made the RawVar class a child of models.RawVar. This is convenient for
webservices since we can simply return this object.
git-svn-id: https://humgenprojects.lumc.nl/svn/mutalyzer/trunk@591 eb6bd6ab-9ccd-42b9-aceb-e2899b4a52f1
---
extras/soap-tools/describe.py | 478 ----------------------------------
mutalyzer/describe.py | 5 +-
mutalyzer/models.py | 28 ++
mutalyzer/services/rpc.py | 212 ++++++++-------
4 files changed, 148 insertions(+), 575 deletions(-)
delete mode 100755 extras/soap-tools/describe.py
diff --git a/extras/soap-tools/describe.py b/extras/soap-tools/describe.py
deleted file mode 100755
index 34778407..00000000
--- a/extras/soap-tools/describe.py
+++ /dev/null
@@ -1,478 +0,0 @@
-#!/usr/bin/python
-
-"""
-Prototype of a module that can generate a HGVS description of the variant(s)
-leading from one sequence to an other.
-
-@requires: sys
-@requires: argparse
-@requires: Bio.Seq
-@requires: suds.client.Client
-"""
-
-# NOTE: The following modules are not needed once this is an integrated module.
-import sys
-import argparse
-from suds.client import Client
-from mutalyzer.util import monkey_patch_suds; monkey_patch_suds()
-
-WSDL_LOCATION = "http://localhost/mutalyzer/services/?wsdl"
-
-# NOTE: The following modules are really needed.
-import Bio.Seq
-from mutalyzer.util import longest_common_prefix, longest_common_suffix
-from mutalyzer.util import palinsnoop, roll
-
-def printMatrix(M) :
- for i in M :
- print i
-
-def LCSMatrix(s1, s2) :
- """
- """
-
- y_max = len(s1) + 1
- x_max = len(s2) + 1
- M = [[0] * x_max for i in xrange(y_max)]
- #printMatrix(M)
-
- for x in xrange(1, y_max) :
- for y in xrange(1, x_max) :
- if s1[x - 1] == s2[y - 1] :
- M[x][y] = M[x - 1][y - 1] + 1
-
- return M
-#LCSMatrix
-
-def findMax(M, x1, x2, y1, y2) :
- """
- M = describe.LCSMatrix("banaan", "ana")
-
- N = describe.LCSMatrix("banaan", "n")
- describe.findMax(M, 1, 7, 2, 3)
-
- N = describe.LCSMatrix("banaan", "na")
- describe.findMax(M, 1, 7, 2, 4)
- """
-
- longest, x_longest, y_longest = 0, 0, 0
-
- for x in xrange(x1, x2) :
- x_relative = x - x1
-
- for y in xrange(y1, y2) :
- y_relative = y - y1
- realVal = min(x_relative, y_relative, M[x][y])
- #print realVal,
-
- if realVal > longest :
- longest = realVal
- x_longest = x_relative
- y_longest = y_relative
- #if
- #for
- #print
- #for
-
- return x_longest, y_longest, longest
-#findMax
-
-def LongestCommonSubstring(s1, s2) :
- """
- Find the longest common substring between {s1} and {s2}.
-
- Mainly copied from:
- http://en.wikibooks.org/wiki/Algorithm_Implementation/Strings/
- Longest_common_substring#Python
-
- @arg s1: String 1.
- @type s1: str
- @arg s2: String 2.
- @type s2: str
-
- @returns: The end locations and the length of the longest common substring.
- @rtype: tuple(int, int, int)
- """
-
- len_s1 = len(s1)
- len_s2 = len(s2)
- M = [[0] * (len_s2 + 1) for i in xrange(len_s1 + 1)]
- longest, x_longest, y_longest = 0, 0, 0
-
- for x in xrange(1, len_s1 + 1) :
- for y in xrange(1, len_s2 + 1) :
- if s1[x - 1] == s2[y - 1] :
- M[x][y] = M[x - 1][y - 1] + 1
-
- if M[x][y] > longest :
- longest = M[x][y]
- x_longest = x
- y_longest = y
- #if
- #if
- else : # Doesn't seem to do anything?
- M[x][y] = 0
- #for
- #for
-
- #print s1, s2
- #printMatrix(M)
- return x_longest, y_longest, longest
-#LongestCommonSubstring
-
-class RawVar() :
- """
- Container for a raw variant.
-
- To use this class correctly, do not supply more than the minimum amount of
- data. The {description()} function may not work properly if too much
- information is given.
-
- Example: if {end} is initialised for a substitution, a range will be
- retuned, resulting in a description like: 100_100A>T
- """
- # TODO: We now use the length of the variant as a measure of its
- # ``length'', but that makes it a bit context dependent, e.g., c.1A>T
- # and g.100A>T may be the same variant giving different lengths.
- # Maybe we should ignore the positions in a description.
-
- def __init__(self, start = 0, start_offset = 0, end = 0, end_offset = 0,
- type = "none", deleted = "", inserted = "", shift = 0) :
- """
- Initialise the class with the appropriate values.
-
- @arg start: Start position.
- @type start: int
- @arg start_offset:
- @type start_offset: int
- @arg end: End position.
- @type end: int
- @arg end_offset:
- @type end_offset: int
- @arg type: Variant type.
- @type type: str
- @arg deleted: Deleted part of the reference sequence.
- @type deleted: str
- @arg inserted: Inserted part.
- @type inserted: str
- @arg shift: Amount of freedom.
- @type shift: int
- """
- # TODO: Will this container be used for all variants, or only genomic?
- # start_offset and end_offset may be never used.
-
- self.start = start
- self.start_offset = start_offset
- self.end = end
- self.end_offset= end_offset
- self.type = type
- self.deleted = deleted
- self.inserted = inserted
- self.shift = shift
- #__init__
-
- def description(self) :
- """
- Give the HGVS description of the raw variant stored in this class.
-
- Note that this function relies on the absence of values to make the
- correct description. Also see the comment in the class definition.
-
- @returns: The HGVS description of the raw variant stored in this class.
- @rtype: str
- """
-
- if not self.start :
- return "="
-
- descr = "%i" % self.start
-
- if self.end :
- descr += "_%i" % self.end
-
- if self.type != "subst" :
- descr += "%s" % self.type
-
- if self.inserted :
- return descr + "%s" % self.inserted
- return descr
- #if
-
- return descr + "%s>%s" % (self.deleted, self.inserted)
- #description
-#RawVar
-
-def alleleDescription(allele) :
- """
- Convert a list of raw variants to an HGVS allele description.
-
- @arg allele: A list of raw variants representing an allele description.
- @type allele: list(RawVar)
-
- @returns: The HGVS description of {allele}.
- @rval: str
- """
-
- if len(allele) > 1 :
- return "[%s]" % ';'.join(map(lambda x : x.description(), allele))
- return allele[0].description()
-#alleleDescription
-
-def printpos(s, start, end, fill = 0) :
- """
- For debugging purposes.
- """
- # TODO: See if this can partially replace or be merged with the
- # visualisation in the __mutate() function of mutator.py
-
- fs = 10 # Flank size.
-
- return "%s %s%s %s" % (s[start - fs:start], s[start:end], '-' * fill,
- s[end:end + fs])
-#printpos
-
-def DNA_description(M, s1, s2, s1_start, s1_end, s2_start, s2_end) :
- """
- Give an allele description of the change from {s1} to {s2} in the range
- {s1_start}..{s1_end} on {s1} and {s2_start}..{s2_end} on {s2}.
-
- arg s1: Sequence 1.
- type s1: str
- arg s2: Sequence 2.
- type s2: str
- arg s1_start: Start of the range on {s1}.
- type s1_start: int
- arg s1_end: End of the range on {s1}.
- type s1_end: int
- arg s2_start: Start of the range on {s2}.
- type s2_start: int
- arg s2_end: End of the range on {s2}.
- type s2_end: int
-
- @returns: A list of RawVar objects, representing the allele.
- @rval: list(RawVar)
- """
- # TODO: Instead of copying this function and adjusting it to make it work
- # for proteins, consider disabling parts like the inversion.
- # TODO: Think about frameshift descriptions.
-
- # Nothing happened.
- if s1 == s2:
- return [RawVar()]
-
- # Insertion / Duplication.
- if s1_start == s1_end :
- ins_length = s2_end - s2_start
- shift5, shift3 = roll(s2, s2_start + 1, s2_end)
- shift = shift5 + shift3
-
- s1_start += shift3
- s1_end += shift3
- s2_start += shift3
- s2_end += shift3
-
- if s2_start - ins_length >= 0 and \
- s1[s1_start - ins_length:s1_start] == s2[s2_start:s2_end] :
-
- if ins_length == 1 :
- return [RawVar(start = s1_start, type = "dup", shift = shift)]
- return [RawVar(start = s1_start - ins_length + 1, end = s1_end,
- type = "dup", shift = shift)]
- #if
- return [RawVar(start = s1_start, end = s1_start + 1,
- inserted = s2[s2_start:s2_end], type = "ins", shift = shift)]
- #if
-
- # Deletion.
- if s2_start == s2_end :
- shift5, shift3 = roll(s1, s1_start + 1, s1_end)
- shift = shift5 + shift3
-
- s1_start += shift3 + 1
- s1_end += shift3
-
- if s1_start == s1_end :
- return [RawVar(start = s1_start, type = "del", shift = shift)]
- return [RawVar(start = s1_start, end = s1_end, type = "del",
- shift = shift)]
- #if
-
- # Substitution.
- if s1_start + 1 == s1_end and s2_start + 1 == s2_end :
- return [RawVar(start = s1_start + 1, deleted = s1[s1_start],
- inserted = s2[s2_start], type = "subst")]
-
- # Simple InDel.
- if s1_start + 1 == s1_end :
- return [RawVar(start = s1_start + 1, inserted = s2[s2_start:s2_end],
- type = "delins")]
-
- # TODO: Refactor the code after this point.
-
- # At this stage, we either have an inversion, an indel or a Compound
- # variant.
- a, b, c = findMax(M, s1_start, s1_end, s2_start, s2_end)
- s1_end_f, s2_end_f, lcs_f_len = LongestCommonSubstring(s1[s1_start:s1_end],
- s2[s2_start:s2_end])
- s1_end_r, s2_end_r, lcs_r_len = LongestCommonSubstring(s1[s1_start:s1_end],
- Bio.Seq.reverse_complement(s2[s2_start:s2_end]))
- print "N:", a, b, c
- print "O:", s1_end_f, s2_end_f, lcs_f_len
-
- # Palindrome snooping.
- trim = palinsnoop(s1[s1_start + s1_end_r - lcs_r_len:s1_start + s1_end_r])
- if trim == -1 : # Full palindrome.
- lcs_r_len = 0 # s1_end_r and s2_end_r should not be used after this.
-
- # Inversion or Compound variant.
- default = [RawVar(start = s1_start + 1, end = s1_end,
- inserted = s2[s2_start:s2_end], type = "delins")]
-
- if not (lcs_f_len or lcs_r_len) : # Optimisation, not really needed.
- return default
-
- # Inversion.
- if lcs_f_len <= lcs_r_len :
- if trim > 0 : # Partial palindrome.
- s1_end_r -= trim
- s2_end_r -= trim
- lcs_r_len -= 2 * trim
- #if
-
- # Simple Inversion.
- if s2_end - s2_start == lcs_r_len and s1_end - s1_start == lcs_r_len :
- return [RawVar(start = s1_start + 1, end = s1_end, type = "inv")]
-
- r1_len = s1_end_r - lcs_r_len
- r2_len = s1_end - s1_start - s1_end_r
- m1_len = s2_end_r - lcs_r_len
- m2_len = s2_end - s2_start - s2_end_r
-
- # The flanks of the inversion (but not both) can be empty, so we
- # generate descriptions conditionally.
- leftRv = []
- rightRv = []
- if r1_len or m2_len :
- lcs = len(longest_common_suffix(s1[s1_start:s1_start + r1_len],
- s2[s2_start:s2_start + m2_len]))
- leftRv = DNA_description(M, s1, s2,
- s1_start, s1_start + r1_len - lcs,
- s2_start, s2_start + m2_len - lcs)
- #if
- if r2_len or m1_len :
- lcp = len(longest_common_prefix(s1[s1_end - r2_len:s1_end],
- s2[s2_end - m1_len:s2_end]))
- rightRv = DNA_description(M, s1, s2,
- s1_end - r2_len + lcp, s1_end, s2_end - m1_len + lcp, s2_end)
- #if
-
- partial = leftRv + [RawVar(start = s1_start + r1_len + 1,
- end = s1_end - r2_len, type = "inv")] + rightRv
- #if
-
- # Compound variant.
- else :
- r1_len = s1_end_f - lcs_f_len
- r2_len = s1_end - s1_start - s1_end_f
- m1_len = s2_end_f - lcs_f_len
- m2_len = s2_end - s2_start - s2_end_f
-
- partial = DNA_description(M, s1, s2, s1_start, s1_start + r1_len,
- s2_start, s2_start + m1_len) + DNA_description(M, s1, s2,
- s1_end - r2_len, s1_end, s2_end - m2_len, s2_end)
- #else
-
- if len(alleleDescription(partial)) - 2 <= len(alleleDescription(default)) :
- return partial
- return default
-#DNA_description
-
-def describeDNA(original, mutated) :
- """
- Convenience function for DNA_description().
-
- @arg original:
- @type original: str
- @arg mutated:
- @type mutated: str
-
- @returns: A list of RawVar objects, representing the allele.
- @rval: list(RawVar)
- """
-
- s1 = str(original)
- s2 = str(mutated)
- lcp = len(longest_common_prefix(s1, s2))
- lcs = len(longest_common_suffix(s1[lcp:], s2[lcp:]))
- s1_end = len(s1) - lcs
- s2_end = len(s2) - lcs
-
- #M = LCSMatrix(s1[lcp:s1_end], s2[lcp:s2_end])
- M = LCSMatrix(s1, s2)
-
- return DNA_description(M, s1, s2, lcp, s1_end, lcp, s2_end)
-#describeDNA
-
-# NOTE: Everything below this point is not needed once this is an integrated
-# module.
-
-def describe(description) :
- """
- Call Mutalyzer with a variant description to get the original and the
- mutated sequence and make our own description.
-
- @arg description: A HGVS description of the variant to be checked.
- @type description: str
- """
-
- service = Client(WSDL_LOCATION, cache = None).service
- result = service.runMutalyzer(description)
-
- if result.rawVariants :
- for i in result.rawVariants.RawVariant :
- print i.description
- print i.visualisation
- print
- #for
-
- newDescription = describeDNA(result.original, result.mutated)
-
- print("old: %s" % result.genomicDescription)
- print("new: XX_XXXXXX.X:X.%s" % alleleDescription(newDescription))
-
- for i in newDescription :
- print("%s" % printpos(result.original, i.start, i.end + 1))
-
- # NOTE: Maybe save this part for making a nice table?
- print("\nstart\tend\ttype\tdel\tins\tshift\thgvs")
- for i in newDescription :
- print("%i\t%i\t%s\t%s\t%s\t%i\t%s" % (i.start, i.end, i.type,
- i.deleted, i.inserted, i.shift, i.description()))
-#describe
-
-def main() :
- """
- Main entry point.
- """
-
- parser = argparse.ArgumentParser(
- prog = "describe",
- formatter_class = argparse.RawDescriptionHelpFormatter,
- description = "",
- epilog = """
-examples:
- NM_002001.2:c.1_10delinsCTGGATCCTC
- NM_002001.2:c.1_5delinsCCATG
- NM_002001.2:c.[1_5delinsCCATG;15del]
-""")
-
- parser.add_argument("-d", dest = "description", type = str,
- required = True, help = "HGVS description of a variant.")
-
- arguments = parser.parse_args()
-
- describe(arguments.description)
-#main
-
-if __name__ == "__main__" :
- main()
diff --git a/mutalyzer/describe.py b/mutalyzer/describe.py
index 6ee458c9..2b8fcc50 100644
--- a/mutalyzer/describe.py
+++ b/mutalyzer/describe.py
@@ -10,6 +10,7 @@ leading from one sequence to an other.
import Bio.Seq
from mutalyzer.util import longest_common_prefix, longest_common_suffix
from mutalyzer.util import palinsnoop, roll
+from mutalyzer import models
def LCSMatrix(s1, s2) :
"""
@@ -102,7 +103,7 @@ def LongestCommonSubstring(s1, s2) :
return x_longest, y_longest, longest
#LongestCommonSubstring
-class RawVar() :
+class RawVar(models.RawVar) :
"""
Container for a raw variant.
@@ -142,7 +143,7 @@ class RawVar() :
self.start = start
self.start_offset = start_offset
self.end = end
- self.end_offset= end_offset
+ self.end_offset = end_offset
self.type = type
self.deleted = deleted
self.inserted = inserted
diff --git a/mutalyzer/models.py b/mutalyzer/models.py
index 5f2c3422..95de214d 100644
--- a/mutalyzer/models.py
+++ b/mutalyzer/models.py
@@ -87,6 +87,34 @@ class RawVariant(ComplexModel):
#RawVariant
+class RawVar(ComplexModel):
+ """
+ Used in MutalyzerOutput data type.
+ """
+ __namespace__ = SOAP_NAMESPACE
+
+ start = Mandatory.Integer
+ start_offset = Mandatory.Integer
+ end = Mandatory.Integer
+ end_offset = Mandatory.Integer
+ type = Mandatory.String
+ deleted = Mandatory.String
+ inserted = Mandatory.String
+ shift = Mandatory.Integer
+#RawVar
+
+
+class Allele(ComplexModel):
+ """
+ Used in MutalyzerOutput data type.
+ """
+ __namespace__ = SOAP_NAMESPACE
+
+ description = Mandatory.String
+ allele = Array(RawVar)
+#Allele
+
+
class MutalyzerOutput(ComplexModel):
"""
Return type of SOAP method runMutalyzer.
diff --git a/mutalyzer/services/rpc.py b/mutalyzer/services/rpc.py
index e8e05596..6551e3df 100644
--- a/mutalyzer/services/rpc.py
+++ b/mutalyzer/services/rpc.py
@@ -28,6 +28,7 @@ from mutalyzer.mapping import Converter
from mutalyzer import Retriever
from mutalyzer import GenRecord
from mutalyzer.models import *
+from mutalyzer import describe
def _checkBuild(L, build) :
@@ -69,9 +70,8 @@ def _checkChrom(L, D, chrom) :
if not D.isChrom(chrom) :
L.addMessage(__file__, 4, "EARG", "EARG %s" % chrom)
- raise Fault("EARG",
- "The chrom argument (%s) was not a valid " \
- "chromosome name." % chrom)
+ raise Fault("EARG", "The chrom argument (%s) was not a valid " \
+ "chromosome name." % chrom)
#if
#_checkChrom
@@ -91,8 +91,7 @@ def _checkPos(L, pos) :
if pos < 1 :
L.addMessage(__file__, 4, "ERANGE", "ERANGE %i" % pos)
- raise Fault("ERANGE",
- "The pos argument (%i) is out of range." % pos)
+ raise Fault("ERANGE", "The pos argument (%i) is out of range." % pos)
#if
#_checkPos
@@ -128,7 +127,7 @@ class MutalyzerService(ServiceBase):
#__init__
@srpc(Mandatory.String, Mandatory.String, Mandatory.Integer, Boolean,
- _returns = Array(Mandatory.String))
+ _returns=Array(Mandatory.String))
def getTranscripts(build, chrom, pos, versions=False) :
"""
Get all the transcripts that overlap with a chromosomal position.
@@ -154,8 +153,8 @@ class MutalyzerService(ServiceBase):
L = Output(__file__)
L.addMessage(__file__, -1, "INFO",
- "Received request getTranscripts(%s %s %s %s)" % (build,
- chrom, pos, versions))
+ "Received request getTranscripts(%s %s %s %s)" % (build, chrom,
+ pos, versions))
_checkBuild(L, build)
D = Db.Mapping(build)
@@ -172,17 +171,16 @@ class MutalyzerService(ServiceBase):
ret = [r[0] for r in ret]
L.addMessage(__file__, -1, "INFO",
- "Finished processing getTranscripts(%s %s %s %s)" % (build,
- chrom, pos, versions))
+ "Finished processing getTranscripts(%s %s %s %s)" % (build, chrom,
+ pos, versions))
- L.addMessage(__file__, -1, "INFO",
- "We return %s" % ret)
+ L.addMessage(__file__, -1, "INFO", "We return %s" % ret)
del D, L
return ret
#getTranscripts
- @srpc(Mandatory.String, Mandatory.String, _returns = Array(Mandatory.String))
+ @srpc(Mandatory.String, Mandatory.String, _returns=Array(Mandatory.String))
def getTranscriptsByGeneName(build, name):
"""
Todo: documentation.
@@ -190,8 +188,7 @@ class MutalyzerService(ServiceBase):
L = Output(__file__)
L.addMessage(__file__, -1, "INFO",
- "Received request getTranscriptsByGene(%s %s)" % (build,
- name))
+ "Received request getTranscriptsByGene(%s %s)" % (build, name))
_checkBuild(L, build)
D = Db.Mapping(build)
@@ -199,8 +196,7 @@ class MutalyzerService(ServiceBase):
ret = D.get_TranscriptsByGeneName(name)
L.addMessage(__file__, -1, "INFO",
- "Finished processing getTranscriptsByGene(%s %s)" % (
- build, name))
+ "Finished processing getTranscriptsByGene(%s %s)" % (build, name))
if ret :
l = []
@@ -212,7 +208,7 @@ class MutalyzerService(ServiceBase):
#getTranscriptsByGene
@srpc(Mandatory.String, Mandatory.String, Mandatory.Integer,
- Mandatory.Integer, Mandatory.Integer, _returns = Array(Mandatory.String))
+ Mandatory.Integer, Mandatory.Integer, _returns=Array(Mandatory.String))
def getTranscriptsRange(build, chrom, pos1, pos2, method) :
"""
Get all the transcripts that overlap with a range on a chromosome.
@@ -256,7 +252,8 @@ class MutalyzerService(ServiceBase):
#getTranscriptsRange
@srpc(Mandatory.String, Mandatory.String, Mandatory.Integer,
- Mandatory.Integer, Mandatory.Integer, _returns = Array(TranscriptMappingInfo))
+ Mandatory.Integer, Mandatory.Integer,
+ _returns=Array(TranscriptMappingInfo))
def getTranscriptsMapping(build, chrom, pos1, pos2, method):
"""
Get all the transcripts and their info that overlap with a range on a
@@ -288,8 +285,8 @@ class MutalyzerService(ServiceBase):
"""
output = Output(__file__)
output.addMessage(__file__, -1, 'INFO', 'Received request ' \
- 'getTranscriptsRange(%s %s %s %s %s)' % \
- (build, chrom, pos1, pos2, method))
+ 'getTranscriptsRange(%s %s %s %s %s)' % (build, chrom, pos1, pos2,
+ method))
_checkBuild(output, build)
@@ -298,9 +295,9 @@ class MutalyzerService(ServiceBase):
for transcript in database.get_Transcripts(chrom, pos1, pos2, method):
t = TranscriptMappingInfo()
- d = dict(zip(('transcript', 'start', 'stop', 'cds_start', 'cds_stop',
- 'exon_starts', 'exon_stops', 'gene', 'chromosome',
- 'orientation', 'protein', 'version'), transcript))
+ d = dict(zip(('transcript', 'start', 'stop', 'cds_start',
+ 'cds_stop', 'exon_starts', 'exon_stops', 'gene', 'chromosome',
+ 'orientation', 'protein', 'version'), transcript))
if d['orientation'] == '-':
d['start'], d['stop'] = d['stop'], d['start']
d['cds_start'], d['cds_stop'] = d['cds_stop'], d['cds_start']
@@ -316,13 +313,13 @@ class MutalyzerService(ServiceBase):
transcripts.append(t)
output.addMessage(__file__, -1, 'INFO', 'Finished processing ' \
- 'getTranscriptsRange(%s %s %s %s %s)' % \
- (build, chrom, pos1, pos2, method))
+ 'getTranscriptsRange(%s %s %s %s %s)' % (build, chrom, pos1, pos2,
+ method))
return transcripts
#getTranscriptsMapping
- @srpc(Mandatory.String, Mandatory.String, _returns = Mandatory.String)
+ @srpc(Mandatory.String, Mandatory.String, _returns=Mandatory.String)
def getGeneName(build, accno) :
"""
Find the gene name associated with a transcript.
@@ -338,7 +335,7 @@ class MutalyzerService(ServiceBase):
L = Output(__file__)
L.addMessage(__file__, -1, "INFO",
- "Received request getGeneName(%s %s)" % (build, accno))
+ "Received request getGeneName(%s %s)" % (build, accno))
D = Db.Mapping(build)
_checkBuild(L, build)
@@ -346,7 +343,7 @@ class MutalyzerService(ServiceBase):
ret = D.get_GeneName(accno.split('.')[0])
L.addMessage(__file__, -1, "INFO",
- "Finished processing getGeneName(%s %s)" % (build, accno))
+ "Finished processing getGeneName(%s %s)" % (build, accno))
del D, L
return ret
@@ -354,7 +351,7 @@ class MutalyzerService(ServiceBase):
@srpc(Mandatory.String, Mandatory.String, Mandatory.String,
- Mandatory.String, _returns = Mapping)
+ Mandatory.String, _returns=Mapping)
def mappingInfo(LOVD_ver, build, accNo, variant) :
"""
Search for an NM number in the MySQL database, if the version
@@ -364,9 +361,11 @@ class MutalyzerService(ServiceBase):
- 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 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.
@@ -397,22 +396,22 @@ class MutalyzerService(ServiceBase):
L = Output(__file__)
L.addMessage(__file__, -1, "INFO",
- "Reveived request mappingInfo(%s %s %s %s)" % (
- LOVD_ver, build, accNo, variant))
+ "Reveived request mappingInfo(%s %s %s %s)" % (LOVD_ver, build,
+ accNo, variant))
conv = Converter(build, L)
result = conv.mainMapping(accNo, variant)
L.addMessage(__file__, -1, "INFO",
- "Finished processing mappingInfo(%s %s %s %s)" % (
- LOVD_ver, build, accNo, variant))
+ "Finished processing mappingInfo(%s %s %s %s)" % (LOVD_ver, build,
+ accNo, variant))
del L
return result
#mappingInfo
@srpc(Mandatory.String, Mandatory.String, Mandatory.String,
- _returns = Transcript)
+ _returns=Transcript)
def transcriptInfo(LOVD_ver, build, accNo) :
"""
Search for an NM number in the MySQL database, if the version
@@ -435,19 +434,19 @@ class MutalyzerService(ServiceBase):
O = Output(__file__)
O.addMessage(__file__, -1, "INFO",
- "Received request transcriptInfo(%s %s %s)" % (LOVD_ver,
- build, accNo))
+ "Received request transcriptInfo(%s %s %s)" % (LOVD_ver, build,
+ accNo))
converter = Converter(build, O)
T = converter.mainTranscript(accNo)
O.addMessage(__file__, -1, "INFO",
- "Finished processing transcriptInfo(%s %s %s)" % (
- LOVD_ver, build, accNo))
+ "Finished processing transcriptInfo(%s %s %s)" % (LOVD_ver, build,
+ accNo))
return T
#transcriptInfo
- @srpc(Mandatory.String, Mandatory.String, _returns = Mandatory.String)
+ @srpc(Mandatory.String, Mandatory.String, _returns=Mandatory.String)
def chromAccession(build, name) :
"""
Get the accession number of a chromosome, given a name.
@@ -464,7 +463,7 @@ class MutalyzerService(ServiceBase):
L = Output(__file__)
L.addMessage(__file__, -1, "INFO",
- "Received request chromAccession(%s %s)" % (build, name))
+ "Received request chromAccession(%s %s)" % (build, name))
_checkBuild(L, build)
_checkChrom(L, D, name)
@@ -472,14 +471,13 @@ class MutalyzerService(ServiceBase):
result = D.chromAcc(name)
L.addMessage(__file__, -1, "INFO",
- "Finished processing chromAccession(%s %s)" % (build,
- name))
+ "Finished processing chromAccession(%s %s)" % (build, name))
del D,L
return result
#chromAccession
- @srpc(Mandatory.String, Mandatory.String, _returns = Mandatory.String)
+ @srpc(Mandatory.String, Mandatory.String, _returns=Mandatory.String)
def chromosomeName(build, accNo) :
"""
Get the name of a chromosome, given a chromosome accession number.
@@ -496,7 +494,7 @@ class MutalyzerService(ServiceBase):
L = Output(__file__)
L.addMessage(__file__, -1, "INFO",
- "Received request chromName(%s %s)" % (build, accNo))
+ "Received request chromName(%s %s)" % (build, accNo))
_checkBuild(L, build)
# self._checkChrom(L, D, name)
@@ -504,14 +502,13 @@ class MutalyzerService(ServiceBase):
result = D.chromName(accNo)
L.addMessage(__file__, -1, "INFO",
- "Finished processing chromName(%s %s)" % (build,
- accNo))
+ "Finished processing chromName(%s %s)" % (build, accNo))
del D,L
return result
#chromosomeName
- @srpc(Mandatory.String, Mandatory.String, _returns = Mandatory.String)
+ @srpc(Mandatory.String, Mandatory.String, _returns=Mandatory.String)
def getchromName(build, acc) :
"""
Get the chromosome name, given a transcript identifier (NM number).
@@ -528,7 +525,7 @@ class MutalyzerService(ServiceBase):
L = Output(__file__)
L.addMessage(__file__, -1, "INFO",
- "Received request getchromName(%s %s)" % (build, acc))
+ "Received request getchromName(%s %s)" % (build, acc))
_checkBuild(L, build)
# self._checkChrom(L, D, name)
@@ -536,14 +533,14 @@ class MutalyzerService(ServiceBase):
result = D.get_chromName(acc)
L.addMessage(__file__, -1, "INFO",
- "Finished processing getchromName(%s %s)" % (build,
- acc))
+ "Finished processing getchromName(%s %s)" % (build, acc))
del D,L
return result
#chromosomeName
- @srpc(Mandatory.String, Mandatory.String, String, _returns = Array(Mandatory.String))
+ @srpc(Mandatory.String, Mandatory.String, String,
+ _returns=Array(Mandatory.String))
def numberConversion(build, variant, gene=None):
"""
Converts I{c.} to I{g.} notation or vice versa
@@ -563,8 +560,7 @@ class MutalyzerService(ServiceBase):
D = Db.Mapping(build)
O = Output(__file__)
O.addMessage(__file__, -1, "INFO",
- "Received request cTogConversion(%s %s)" % (
- build, variant))
+ "Received request cTogConversion(%s %s)" % (build, variant))
converter = Converter(build, O)
variant = converter.correctChrVariant(variant)
@@ -576,12 +572,11 @@ class MutalyzerService(ServiceBase):
result = [""]
O.addMessage(__file__, -1, "INFO",
- "Finished processing cTogConversion(%s %s)" % (
- build, variant))
+ "Finished processing cTogConversion(%s %s)" % (build, variant))
return result
#numberConversion
- @srpc(Mandatory.String, _returns = CheckSyntaxOutput)
+ @srpc(Mandatory.String, _returns=CheckSyntaxOutput)
def checkSyntax(variant):
"""
Checks the syntax of a variant.
@@ -597,7 +592,7 @@ class MutalyzerService(ServiceBase):
"""
output = Output(__file__)
output.addMessage(__file__, -1, "INFO",
- "Received request checkSyntax(%s)" % (variant))
+ "Received request checkSyntax(%s)" % (variant))
result = CheckSyntaxOutput()
@@ -608,7 +603,7 @@ class MutalyzerService(ServiceBase):
result.valid = bool(parsetree)
output.addMessage(__file__, -1, "INFO",
- "Finished processing checkSyntax(%s)" % (variant))
+ "Finished processing checkSyntax(%s)" % (variant))
result.messages = []
for message in output.getMessages():
@@ -620,7 +615,7 @@ class MutalyzerService(ServiceBase):
return result
#checkSyntax
- @srpc(Mandatory.String, _returns = MutalyzerOutput)
+ @srpc(Mandatory.String, _returns=MutalyzerOutput)
def runMutalyzer(variant) :
"""
Run the Mutalyzer name checker.
@@ -664,7 +659,7 @@ class MutalyzerService(ServiceBase):
"""
O = Output(__file__)
O.addMessage(__file__, -1, "INFO",
- "Received request runMutalyzer(%s)" % (variant))
+ "Received request runMutalyzer(%s)" % (variant))
variantchecker.check_variant(variant, O)
result = MutalyzerOutput()
@@ -713,7 +708,7 @@ class MutalyzerService(ServiceBase):
result.errors, result.warnings, result.summary = O.Summary()
O.addMessage(__file__, -1, "INFO",
- "Finished processing runMutalyzer(%s)" % (variant))
+ "Finished processing runMutalyzer(%s)" % (variant))
result.messages = []
for message in O.getMessages():
@@ -725,7 +720,7 @@ class MutalyzerService(ServiceBase):
return result
#runMutalyzer
- @srpc(Mandatory.String, Mandatory.String, _returns = TranscriptNameInfo)
+ @srpc(Mandatory.String, Mandatory.String, _returns=TranscriptNameInfo)
def getGeneAndTranscript(genomicReference, transcriptReference) :
"""
Todo: documentation.
@@ -734,8 +729,8 @@ class MutalyzerService(ServiceBase):
D = Db.Cache()
O.addMessage(__file__, -1, "INFO",
- "Received request getGeneAndTranscript(%s, %s)" % (genomicReference,
- transcriptReference))
+ "Received request getGeneAndTranscript(%s, %s)" % (
+ genomicReference, transcriptReference))
retriever = Retriever.GenBankRetriever(O, D)
record = retriever.loadrecord(genomicReference)
@@ -758,7 +753,7 @@ class MutalyzerService(ServiceBase):
return ret
#getGeneAndTranscript
- @srpc(Mandatory.String, String, _returns = Array(TranscriptInfo))
+ @srpc(Mandatory.String, String, _returns=Array(TranscriptInfo))
def getTranscriptsAndInfo(genomicReference, geneName=None):
"""
Given a genomic reference, return all its transcripts with their
@@ -806,7 +801,8 @@ class MutalyzerService(ServiceBase):
D = Db.Cache()
O.addMessage(__file__, -1, "INFO",
- "Received request getTranscriptsAndInfo(%s, %s)" % (genomicReference, geneName))
+ "Received request getTranscriptsAndInfo(%s, %s)" % (
+ genomicReference, geneName))
retriever = Retriever.GenBankRetriever(O, D)
record = retriever.loadrecord(genomicReference)
@@ -835,7 +831,8 @@ class MutalyzerService(ServiceBase):
# Some raw info we don't use directly:
# - transcript.CDS.location CDS start and stop (g)
# - transcript.CDS.positionList: CDS splice sites (g) ?
- # - transcript.mRNA.location: translation start and stop (g)
+ # - transcript.mRNA.location: translation start and stop
+ # (g)
# - transcript.mRNA.positionList: splice sites (g)
t.exons = []
@@ -843,10 +840,12 @@ class MutalyzerService(ServiceBase):
exon = ExonInfo()
exon.gStart = transcript.CM.getSpliceSite(i)
exon.cStart = transcript.CM.g2c(exon.gStart)
- exon.chromStart = GenRecordInstance.record.toChromPos(exon.gStart)
+ exon.chromStart = GenRecordInstance.record.toChromPos(
+ exon.gStart)
exon.gStop = transcript.CM.getSpliceSite(i + 1)
exon.cStop = transcript.CM.g2c(exon.gStop)
- exon.chromStop = GenRecordInstance.record.toChromPos(exon.gStop)
+ exon.chromStop = GenRecordInstance.record.toChromPos(
+ exon.gStop)
t.exons.append(exon)
# Beware that CM.info() gives a made-up value for trans_end,
@@ -854,12 +853,14 @@ class MutalyzerService(ServiceBase):
# it in our output and use the end position of the last exon
# instead. The made-up value is still useful for sorting, so
# we return it as sortableTransEnd.
- trans_start, sortable_trans_end, cds_stop = transcript.CM.info()
+ trans_start, sortable_trans_end, cds_stop = \
+ transcript.CM.info()
cds_start = 1
t.cTransEnd = str(t.exons[-1].cStop)
t.gTransEnd = t.exons[-1].gStop
- t.chromTransEnd = GenRecordInstance.record.toChromPos(t.gTransEnd)
+ t.chromTransEnd = GenRecordInstance.record.toChromPos(
+ t.gTransEnd)
t.sortableTransEnd = sortable_trans_end
# Todo: If we have no CDS info, CM.info() gives trans_end as
@@ -872,10 +873,12 @@ class MutalyzerService(ServiceBase):
t.product = transcript.transcriptProduct
t.cTransStart = str(trans_start)
t.gTransStart = transcript.CM.x2g(trans_start, 0)
- t.chromTransStart = GenRecordInstance.record.toChromPos(t.gTransStart)
+ t.chromTransStart = GenRecordInstance.record.toChromPos(
+ t.gTransStart)
t.cCDSStart = str(cds_start)
t.gCDSStart = transcript.CM.x2g(cds_start, 0)
- t.chromCDSStart = GenRecordInstance.record.toChromPos(t.gCDSStart)
+ t.chromCDSStart = GenRecordInstance.record.toChromPos(
+ t.gCDSStart)
t.cCDSStop = str(cds_stop)
t.gCDSStop = transcript.CM.x2g(cds_stop, 0)
t.chromCDSStop = GenRecordInstance.record.toChromPos(t.gCDSStop)
@@ -899,7 +902,7 @@ class MutalyzerService(ServiceBase):
return transcripts
#getTranscriptsAndInfo
- @srpc(Mandatory.String, _returns = Mandatory.String)
+ @srpc(Mandatory.String, _returns=Mandatory.String)
def upLoadGenBankLocalFile(content) :
"""
Not implemented yet.
@@ -907,7 +910,7 @@ class MutalyzerService(ServiceBase):
raise Fault('ENOTIMPLEMENTED', 'Not implemented yet')
#upLoadGenBankLocalFile
- @srpc(Mandatory.String, _returns = Mandatory.String)
+ @srpc(Mandatory.String, _returns=Mandatory.String)
def upLoadGenBankRemoteFile(url) :
"""
Not implemented yet.
@@ -916,7 +919,7 @@ class MutalyzerService(ServiceBase):
#upLoadGenBankRemoteFile
@srpc(Mandatory.String, Mandatory.String, Mandatory.Integer,
- Mandatory.Integer, _returns = Mandatory.String)
+ Mandatory.Integer, _returns=Mandatory.String)
def sliceChromosomeByGene(geneSymbol, organism, upStream,
downStream) :
"""
@@ -946,7 +949,7 @@ class MutalyzerService(ServiceBase):
#sliceChromosomeByGene
@srpc(Mandatory.String, Mandatory.Integer, Mandatory.Integer,
- Mandatory.Integer, _returns = Mandatory.String)
+ Mandatory.Integer, _returns=Mandatory.String)
def sliceChromosome(chromAccNo, start, end, orientation) :
"""
Todo: documentation, error handling, argument checking, tests.
@@ -972,7 +975,7 @@ class MutalyzerService(ServiceBase):
return UD
#sliceChromosome
- @srpc(_returns = InfoOutput)
+ @srpc(_returns=InfoOutput)
def info():
"""
Gives some static application information, such as the current running
@@ -1010,7 +1013,7 @@ class MutalyzerService(ServiceBase):
return result
#info
- @srpc(_returns = Mandatory.String)
+ @srpc(_returns=Mandatory.String)
def ping():
"""
Simple function to test the interface.
@@ -1021,7 +1024,28 @@ class MutalyzerService(ServiceBase):
return 'pong'
#ping
- @srpc(DateTime, _returns = Array(CacheEntry))
+ @srpc(Mandatory.String, Mandatory.String, _returns=Allele)
+ def descriptionExtract(reference, observed):
+ """
+ Extract the HGVS variant description from a reference sequence and an
+ observed sequence.
+ """
+ output = Output(__file__)
+
+ output.addMessage(__file__, -1, 'INFO',
+ 'Received request descriptionExtract')
+
+ result = Allele()
+ result.allele = describe.describeDNA(reference, observed)
+ result.description = describe.alleleDescription(result.allele)
+
+ output.addMessage(__file__, -1, 'INFO',
+ 'Finished processing descriptionExtract')
+
+ return result
+ #descriptionExtract
+
+ @srpc(DateTime, _returns=Array(CacheEntry))
def getCache(created_since=None):
"""
Get a list of entries from the local cache created since given date.
@@ -1031,8 +1055,7 @@ class MutalyzerService(ServiceBase):
"""
output = Output(__file__)
- output.addMessage(__file__, -1, 'INFO',
- 'Received request getCache')
+ output.addMessage(__file__, -1, 'INFO', 'Received request getCache')
database = Db.Cache()
sync = CacheSync(output, database)
@@ -1042,18 +1065,17 @@ class MutalyzerService(ServiceBase):
def cache_entry_to_soap(entry):
e = CacheEntry()
for attr in ('name', 'gi', 'hash', 'chromosomeName',
- 'chromosomeStart', 'chromosomeStop',
- 'chromosomeOrientation', 'url', 'created', 'cached'):
+ 'chromosomeStart', 'chromosomeStop', 'chromosomeOrientation',
+ 'url', 'created', 'cached'):
setattr(e, attr, entry[attr])
return e
- output.addMessage(__file__, -1, 'INFO',
- 'Finished processing getCache')
+ output.addMessage(__file__, -1, 'INFO', 'Finished processing getCache')
return map(cache_entry_to_soap, cache)
#getCache
- @srpc(Mandatory.String, _returns = Array(Mandatory.String))
+ @srpc(Mandatory.String, _returns=Array(Mandatory.String))
def getdbSNPDescriptions(rs_id):
"""
Lookup HGVS descriptions for a dbSNP rs identifier.
@@ -1067,19 +1089,19 @@ class MutalyzerService(ServiceBase):
output = Output(__file__)
output.addMessage(__file__, -1, 'INFO',
- 'Received request getdbSNPDescription(%s)' % rs_id)
+ 'Received request getdbSNPDescription(%s)' % rs_id)
retriever = Retriever.Retriever(output, None)
descriptions = retriever.snpConvert(rs_id)
output.addMessage(__file__, -1, 'INFO',
- 'Finished processing getdbSNPDescription(%s)' % rs_id)
+ 'Finished processing getdbSNPDescription(%s)' % rs_id)
# Todo: use SOAP Fault object here (see Trac issue #41).
messages = output.getMessages()
if messages:
- error = 'The request could not be completed\n' \
- + '\n'.join(map(lambda m: str(m), output.getMessages()))
+ error = 'The request could not be completed\n' + \
+ '\n'.join(map(lambda m: str(m), output.getMessages()))
raise Exception(error)
return descriptions
--
GitLab