diff --git a/mutalyzer/Crossmap.py b/mutalyzer/Crossmap.py
index a78a3f2530c659688505d1e4711d895a7f88f54d..cd289e3ebd5e558886bc1204401f4e81cb759847 100644
--- a/mutalyzer/Crossmap.py
+++ b/mutalyzer/Crossmap.py
@@ -435,7 +435,7 @@ class Crossmap() :
return int(s)
#main2int
- def int2offset(self, t) :
+ def int2offset(self, t, fuzzy=False):
"""
Convert a tuple of integers to offset-notation. This adds a `+',
and `u' or `d' to the offset when appropriate. The main value is
@@ -443,17 +443,22 @@ class Crossmap() :
@arg t: A tuple of integers: (main, offset) in __STOP notation
@type t: tuple
+ @kwarg fuzzy: Denotes that the coordinate is fuzzy (i.e. offset is
+ unknown).
+ @type fuzzy: bool
@return: The offset in HGVS notation
@rtype: string
"""
if t[1] > 0 : # The exon boundary is downstream.
+ if fuzzy: return '+?'
if t[0] >= self.__trans_end : # It is downstream of the last exon.
return "+d" + str(t[1])
return '+' + str(t[1])
#if
if t[1] < 0 : # The exon boundary is uptream.
+ if fuzzy: return '-?'
if t[0] <= self.__trans_start : # It is upstream of the first exon.
return "-u" + str(-t[1])
return str(t[1])
@@ -490,32 +495,38 @@ class Crossmap() :
return int(s[1:])
#offset2int
- def tuple2string(self, t) :
+ def tuple2string(self, t, fuzzy=False) :
"""
Convert a tuple (main, offset) in __STOP notation to I{c.} notation.
@arg t: A tuple (main, offset) in __STOP notation
@type t: tuple
+ @kwarg fuzzy: Denotes that the coordinate is fuzzy (i.e. offset is
+ unknown).
+ @type fuzzy: bool
@return: The position in HGVS notation
@rtype: string
"""
- return str(self.int2main(t[0])) + str(self.int2offset(t))
+ return str(self.int2main(t[0])) + str(self.int2offset(t, fuzzy))
#tuple2string
- def g2c(self, a) :
+ def g2c(self, a, fuzzy=False) :
"""
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
+ @kwarg fuzzy: Denotes that the coordinate is fuzzy (i.e. offset is
+ unknown).
+ @type fuzzy: bool
@return: The position in HGVS notation
@rtype: string
"""
- return self.tuple2string(self.g2x(a))
+ return self.tuple2string(self.g2x(a), fuzzy)
#g2c
def info(self) :
diff --git a/mutalyzer/GenRecord.py b/mutalyzer/GenRecord.py
index 4f3b1559822cdbf3292fe825cb4b94e865111dc0..3c96487220f582f3f076ed45151dda011194faf4 100644
--- a/mutalyzer/GenRecord.py
+++ b/mutalyzer/GenRecord.py
@@ -81,7 +81,7 @@ class Locus(object) :
- exon ; A position list object.
- txTable ; The translation table.
- CM ; A Crossmap object.
-
+
@arg name: identifier of the locus
@type name: string
"""
@@ -110,21 +110,37 @@ class Locus(object) :
self.proteinProduct = None
#__init__
- def addToDescription(self, rawVariant) :
+ def cancelDescription(self):
+ """
+ Set the description on this locus to 'unknown'.
+
+ This can be used if at some point we give up creating a sensible
+ description on this locus. It also makes sure future additions to
+ the description are ignored and it keeps the 'unknown' value.
+
+ @note: This depends on the check for the unknown value in the
+ addToDescription method. This is a not a beatiful solution.
+ """
+ self.description = '?'
+ #cancelDescription
+
+ 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:
- self.description = "%s;%s" % (self.description, rawVariant)
- else :
+ # Don't change anything if we already have an unknown value.
+ if self.description != '?':
+ self.description = "%s;%s" % (self.description, rawVariant)
+ else:
self.description = rawVariant
#addToDescription
#Locus
+
class Gene(object) :
"""
A Gene object, to store a list of Locus objects and the orientation of
@@ -150,7 +166,7 @@ class Gene(object) :
- longName ;
Private variables (altered):
- __locusTag ;
-
+
@arg name: gene name
@type name: string
"""
@@ -166,7 +182,7 @@ class Gene(object) :
def newLocusTag(self) :
"""
Generates a new Locus tag.
-
+
@return: Locus tag
@rtype: integer (3 digits, if < 100 preceeded with 0's)
"""
@@ -179,10 +195,10 @@ 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
"""
@@ -196,7 +212,7 @@ class Gene(object) :
def listLoci(self) :
"""
Provides a list of transcript variant numbers
-
+
@return: list of transcript variant numbers
@rtype: list
"""
@@ -210,10 +226,10 @@ 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
"""
@@ -280,10 +296,10 @@ 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
"""
@@ -297,10 +313,10 @@ class Record(object) :
def listGenes(self) :
"""
List the names of all genes found in this record.
-
+
@return: Genes list
@rtype: list
-
+
"""
ret = []
@@ -312,7 +328,7 @@ 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
"""
@@ -326,11 +342,11 @@ class Record(object) :
def toChromPos(self, i) :
"""
Converts a g. position (relative to the start of the record) to a
- chromosomal g. position
-
+ chromosomal g. position
+
@arg i: g. position (relative to the start of the record)
@type i: integer
-
+
@return: chromosomal g. position
@rtype: integer
"""
@@ -366,10 +382,10 @@ class GenRecord() :
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
@@ -384,13 +400,13 @@ 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:
+
+ @return:
@rtype: boolean
"""
@@ -414,12 +430,12 @@ class GenRecord() :
return True
return False
#__checkExonList
-
+
def __constructCDS(self, mRNA, CDSpos) :
"""
- Construct a list of coordinates that contains CDS start and stop and
+ 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
@@ -449,14 +465,14 @@ class GenRecord() :
"""
Return the reverse-complement of a DNA sequence if the gene is in
the reverse orientation.
-
- @arg gene: Gene
+
+ @arg gene: Gene
@type gene: object
@arg string: DNA sequence
@type string: string
@kwarg string_reverse: DNA sequence to use (if not None) for the
reverse complement.
-
+
@return: reverse-complement (if applicable), otherwise return the
original.
@rtype: string
@@ -472,7 +488,7 @@ class GenRecord() :
"""
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
"""
@@ -602,7 +618,8 @@ class GenRecord() :
return None
#current_transcript
- def name(self, start_g, stop_g, varType, arg1, arg2, roll, arg1_reverse=None):
+ def name(self, start_g, stop_g, varType, arg1, arg2, roll, arg1_reverse=None,
+ start_fuzzy=False, stop_fuzzy=False):
"""
Generate variant descriptions for all genes, transcripts, etc.
@@ -620,6 +637,10 @@ class GenRecord() :
@type roll: tuple (integer, integer)
@kwarg arg1_reverse: argument 1 to be used on reverse strand
@type arg1_reverse: string
+ @kwarg start_fuzzy: Indicates if start position of variant is fuzzy.
+ @type start_fuzzy: bool
+ @kwarg stop_fuzzy: Indicates if stop position of variant is fuzzy.
+ @type stop_fuzzy: bool
"""
forwardStart = start_g
forwardStop = stop_g
@@ -634,23 +655,64 @@ class GenRecord() :
if varType != "subst" :
if forwardStart != forwardStop :
- self.record.addToDescription("%s_%s%s%s" % (forwardStart,
- forwardStop, varType, arg1))
- self.record.addToChromDescription("%s_%s%s%s" % (
- self.record.toChromPos(forwardStart),
- self.record.toChromPos(forwardStop), varType, arg1))
+ # Todo: Fuzzy offsets to genomic positions (see bug #38).
+ #
+ # The genomic positioning is problematic. We would like to
+ # have it in brackets (as fuzzy positions), like the above
+ # g.(34299_23232)del example.
+ #
+ # Now consider a variant c.a-?_b+18del where only the offset
+ # before the exon is unknown but the offset after the exon is
+ # exact. Now a genomic description like g.(34299)_23232del
+ # comes to mind, however, this notation is not allowed by the
+ # HGVS grammar.
+ #
+ # I think all we can do is to treat both positions as fuzzy in
+ # the genomic description, even if only one of them really is.
+ #
+ # Peter thinks the HGVS grammar should at some point be
+ # updated to allow the brackets around individual locations.
+ if start_fuzzy or stop_fuzzy:
+ self.record.addToDescription("(%s_%s)%s%s" % (
+ forwardStart, forwardStop, varType, arg1))
+ self.record.addToChromDescription("(%s_%s)%s%s" % (
+ self.record.toChromPos(forwardStart),
+ self.record.toChromPos(forwardStop), varType, arg1))
+ else:
+ self.record.addToDescription("%s_%s%s%s" % (
+ forwardStart, forwardStop, varType, arg1))
+ self.record.addToChromDescription("%s_%s%s%s" % (
+ self.record.toChromPos(forwardStart),
+ self.record.toChromPos(forwardStop), varType, arg1))
#if
else :
- self.record.addToDescription("%s%s%s" % (forwardStart, varType,
- arg1))
- self.record.addToChromDescription("%s%s%s" % (
- self.record.toChromPos(forwardStart), varType, arg1))
+ if start_fuzzy or stop_fuzzy:
+ # Todo: Current HGVS does not allow for () around single
+ # positions, only around ranges (see above and #38).
+ self.record.addToDescription("(%s)%s%s" % (
+ forwardStart, varType, arg1))
+ self.record.addToChromDescription("(%s)%s%s" % (
+ self.record.toChromPos(forwardStart), varType, arg1))
+ else:
+ self.record.addToDescription("%s%s%s" % (
+ forwardStart, varType, arg1))
+ self.record.addToChromDescription("%s%s%s" % (
+ self.record.toChromPos(forwardStart), varType, arg1))
#else
#if
else :
- self.record.addToDescription("%s%c>%c" % (forwardStart, arg1, arg2))
- self.record.addToChromDescription("%s%c>%c" % (
- self.record.toChromPos(forwardStart), arg1, arg2))
+ if start_fuzzy or stop_fuzzy:
+ # Todo: Current HGVS does not allow for () around single
+ # positions, only around ranges (see above and #38).
+ self.record.addToDescription("(%s)%c>%c" % (
+ forwardStart, arg1, arg2))
+ self.record.addToChromDescription("(%s)%c>%c" % (
+ self.record.toChromPos(forwardStart), arg1, arg2))
+ else:
+ self.record.addToDescription("%s%c>%c" % (
+ forwardStart, arg1, arg2))
+ self.record.addToChromDescription("%s%c>%c" % (
+ self.record.toChromPos(forwardStart), arg1, arg2))
for i in self.record.geneList :
for j in i.transcriptList :
@@ -683,24 +745,45 @@ class GenRecord() :
if varType != "subst" :
if orientedStart != orientedStop :
- j.addToDescription("%s_%s%s%s" % (
- j.CM.g2c(orientedStart), j.CM.g2c(orientedStop),
- varType, self.__maybeInvert(i, arg1, arg1_reverse)))
- self.checkIntron(i, j, orientedStart)
- self.checkIntron(i, j, orientedStop)
+ if (start_fuzzy or stop_fuzzy) and not j.current:
+ # Don't generate descriptions on transcripts
+ # other than the current in the case of fuzzy
+ # positions.
+ j.cancelDescription()
+ else:
+ j.addToDescription("%s_%s%s%s" % (
+ j.CM.g2c(orientedStart, start_fuzzy),
+ j.CM.g2c(orientedStop, stop_fuzzy),
+ varType, self.__maybeInvert(i, arg1, arg1_reverse)))
+ self.checkIntron(i, j, orientedStart)
+ self.checkIntron(i, j, orientedStop)
#if
else :
- j.addToDescription("%s%s%s" % (
- j.CM.g2c(orientedStart), varType,
- self.__maybeInvert(i, arg1, arg1_reverse)))
- self.checkIntron(i, j, orientedStart)
+ if start_fuzzy and not j.current:
+ # Don't generate descriptions on transcripts
+ # other than the current in the case of fuzzy
+ # positions.
+ j.cancelDescription()
+ else:
+ j.addToDescription("%s%s%s" % (
+ j.CM.g2c(orientedStart, start_fuzzy),
+ varType,
+ self.__maybeInvert(i, arg1, arg1_reverse)))
+ self.checkIntron(i, j, orientedStart)
#else
#if
else :
- j.addToDescription("%s%c>%c" % (j.CM.g2c(orientedStart),
- self.__maybeInvert(i, arg1, arg1_reverse),
- self.__maybeInvert(i, arg2)))
- self.checkIntron(i, j, orientedStart)
+ if start_fuzzy and not j.current:
+ # Don't generate descriptions on transcripts
+ # other than the current in the case of fuzzy
+ # positions.
+ j.cancelDescription()
+ else:
+ j.addToDescription("%s%c>%c" % (
+ j.CM.g2c(orientedStart, start_fuzzy),
+ self.__maybeInvert(i, arg1, arg1_reverse),
+ self.__maybeInvert(i, arg2)))
+ self.checkIntron(i, j, orientedStart)
#else
#if
#for
@@ -710,14 +793,14 @@ class GenRecord() :
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.
"""
diff --git a/mutalyzer/templates/check.html b/mutalyzer/templates/check.html
index 271293e2bff8feb9fa951c69f396e97ee5e51958..ca1fd558341c2202182036351688ad0a207221c9 100644
--- a/mutalyzer/templates/check.html
+++ b/mutalyzer/templates/check.html
@@ -95,9 +95,10 @@
<b>Affected transcripts:</b><br>
<br>
<tt tal:repeat = "i descriptions">
- <a tal:content = "i/0"
+ <a tal:condition = "i/1" tal:content = "i/0"
tal:attributes =
- "href string:checkForward?mutationName=${i/1}"></a><br>
+ "href string:checkForward?mutationName=${i/1}"></a><tal
+ tal:condition = "not:i/1" tal:replace = "i/0"></tal><br>
</tt>
<br>
<br>
diff --git a/mutalyzer/variantchecker.py b/mutalyzer/variantchecker.py
index 4068cba0424ad8aa16e241d76a88c941d72e71dc..126219694ceac857f7c2b6e21994fbac27b45e30 100644
--- a/mutalyzer/variantchecker.py
+++ b/mutalyzer/variantchecker.py
@@ -302,7 +302,8 @@ def apply_substitution(position, original, substitute, mutator, record, O):
#apply_substitution
-def apply_deletion_duplication(first, last, type, mutator, record, O):
+def apply_deletion_duplication(first, last, type, mutator, record, O,
+ first_fuzzy=False, last_fuzzy=False):
"""
Do a semantic check for a deletion or duplication, do the actual
deletion/duplication and give it a name.
@@ -319,6 +320,13 @@ def apply_deletion_duplication(first, last, type, mutator, record, O):
@type record: Modules.GenRecord.GenRecord
@arg O: The Output object.
@type O: Modules.Output.Output
+
+ @kwarg first_fuzzy: Denotes that the start position is fuzzy (e.g. in the
+ case of an unknown offset in c. notation).
+ @type first_fuzzy: bool
+ @kwarg last_fuzzy: Denotes that the end position is fuzzy (e.g. in the
+ case of an unknown offset in c. notation).
+ @type last_fuzzy: bool
"""
reverse_roll, forward_roll = util.roll(mutator.orig, first, last)
@@ -391,7 +399,9 @@ def apply_deletion_duplication(first, last, type, mutator, record, O):
else:
mutator.dupM(first, last)
- record.name(first, last, type, '', '', (reverse_roll, forward_roll))
+ record.name(first, last, type, '', '', (reverse_roll, forward_roll),
+ start_fuzzy=first_fuzzy,
+ stop_fuzzy=last_fuzzy)
#apply_deletion_duplication
@@ -644,21 +654,71 @@ def apply_delins(first, last, delete, insert, mutator, record, output):
#apply_delins
-def _get_offset(location):
+def _get_offset(location, main_genomic, sites, output):
"""
Convert the offset coordinate in a location (from the Parser) to an
integer.
@arg location: A location.
@type location: pyparsing.ParseResults
+ @arg main_genomic: Genomic main position to which the offset belongs.
+ @type main_genomic: int
+ @arg sites: List of splice sites.
+ @type sites: list
+ @arg output: The Output object.
+ @type output: Modules.Output.Output
@return: Integer representation of the offset coordinate.
@rtype: int
"""
if location.Offset :
- if location.Offset == '?' : # This is highly debatable.
- return 0
- offset = int(location.Offset)
+ if location.Offset == '?' :
+ try:
+ # Todo: If it removes CDS start, don't do protein translation.
+ # Todo: Wrt orientation, perhaps always go to splice site
+ # locations via the crossmapper...
+ # Todo: Also check if +? and -? are correctly used.
+ # Todo: Exactly centering might not be so nice, since the center
+ # might be closer to a neighbouring exon, making a+xxx from b-?
+ # and vice versa. This might not be fixed directly by doing a
+ # center +/- 1 because there might be rolling. Ideally we
+ # disable rolling entirely for these positions...
+ #
+ # Note that the code below might be a bit confusing, especially
+ # considering reverse strand transcripts. Magically, it works
+ # for both orientations.
+ i = sites.index(main_genomic)
+ if i == 0:
+ # Before first exon (or last on the reverse strand).
+ offset = main_genomic / 2
+ elif i == len(sites) - 1:
+ # After last exon (or first on the reverse strand).
+ # Todo: Get length of reference, and calculate a sensible
+ # offset.
+ #
+ # We now use that 2000 is the default downstream length,
+ # but of course this is bogus on the reverse strand and
+ # just a hack anyway.
+ offset = 1000
+ elif i % 2 == 0:
+ # Acceptor site (or donor on the reverse strand).
+ offset = abs(main_genomic - sites[i - 1]) / 2 - 1
+ else:
+ # Donor site (or acceptor on the reverse strand).
+ offset = abs(sites[i + 1] - main_genomic) / 2 - 1
+ # Todo: We would like to use the c. position in this message.
+ output.addMessage(__file__, 1, "IUNKNOWNOFFSET", "Unknown offset " \
+ "relative to %s interpreted as middle of " \
+ "flanking intron." % main_genomic)
+ except ValueError:
+ # Todo: This means we don't get an error if the main position
+ # was not on an exon boundary. We should return something else
+ # than 0 I guess.
+ #return 0 # This is highly debatable.
+ # Any non-zero value will do.
+ return 1
+ else:
+ offset = int(location.Offset)
if location.OffSgn == '-' :
return -offset
return offset
@@ -761,7 +821,7 @@ def _genomic_to_genomic(first_location, last_location):
return first, last
-def _coding_to_genomic(first_location, last_location, transcript):
+def _coding_to_genomic(first_location, last_location, transcript, output):
"""
Get genomic range from parsed c. location.
@@ -771,6 +831,8 @@ def _coding_to_genomic(first_location, last_location, transcript):
@type last_location: pyparsing.ParseResults
@arg transcript: todo
@type transcript: todo
+ @arg output: The Output object.
+ @type output: Modules.Output.Output
@return: A tuple of:
- first: Genomic start location represented by given location.
@@ -792,11 +854,15 @@ def _coding_to_genomic(first_location, last_location, transcript):
first_main = transcript.CM.main2int(first_location.MainSgn + \
first_location.Main)
- first_offset = _get_offset(first_location)
+ first_main_genomic = transcript.CM.x2g(first_main, 0)
+ first_offset = _get_offset(first_location, first_main_genomic,
+ transcript.CM.RNA, output)
last_main = transcript.CM.main2int(last_location.MainSgn + \
last_location.Main)
- last_offset = _get_offset(last_location)
+ last_main_genomic = transcript.CM.x2g(last_main, 0)
+ last_offset = _get_offset(last_location, last_main_genomic,
+ transcript.CM.RNA, output)
# These raise _RawVariantError exceptions on invalid positions.
_check_intronic_position(first_main, first_offset, transcript)
@@ -912,7 +978,8 @@ def process_raw_variant(mutator, variant, record, transcript, output):
try:
if transcript:
# Coding positioning.
- first, last = _coding_to_genomic(first_location, last_location, transcript)
+ first, last = _coding_to_genomic(first_location, last_location,
+ transcript, output)
else:
# Genomic positioning.
first, last = _genomic_to_genomic(first_location, last_location)
@@ -1062,8 +1129,12 @@ def process_raw_variant(mutator, variant, record, transcript, output):
# Deletion or duplication.
if variant.MutationType in ['del', 'dup']:
+ # The fuzzy flags are to support deletions of the form c.a-?_b+?del.
+ first_fuzzy = variant.StartLoc.PtLoc.Offset == '?'
+ last_fuzzy = variant.EndLoc and variant.EndLoc.PtLoc.Offset == '?'
apply_deletion_duplication(first, last, variant.MutationType, mutator,
- record, output)
+ record, output, first_fuzzy=first_fuzzy,
+ last_fuzzy=last_fuzzy)
# Inversion.
if variant.MutationType == 'inv':
@@ -1259,6 +1330,9 @@ def process_variant(mutator, description, record, output):
if transcript_id:
transcript = gene.findLocus(transcript_id)
if not transcript:
+ # Todo: Incorrect error message, it might also be that
+ # there are no transcripts at all (e.g. N4BP2L1 on
+ # NG_012772.1).
output.addMessage(__file__, 4, "ENOTRANSCRIPT",
"Multiple transcripts found for gene %s. Please " \
"choose from: %s" %(gene.name,
@@ -1302,6 +1376,9 @@ def process_variant(mutator, description, record, output):
# this gene.
transcript = gene.transcriptList[0]
else:
+ # Todo: Incorrect error message, it might also be that
+ # there are no transcripts at all (e.g. N4BP2L1 on
+ # NG_012772.1).
output.addMessage(__file__, 4, "ENOTRANSCRIPT",
"Multiple transcripts found for gene %s. Please " \
"choose from: %s" %(gene.name,
@@ -1484,6 +1561,7 @@ def check_variant(description, config, output):
mutator.newSplice(transcript.CDS.positionList),
transcript.CM.orientation)),
IUPAC.unambiguous_dna)
+
if transcript.CM.orientation == -1:
cds_original = Bio.Seq.reverse_complement(cds_original)
cds_variant = Bio.Seq.reverse_complement(cds_variant)
@@ -1509,9 +1587,15 @@ def check_variant(description, config, output):
return
protein_variant = cds_variant.translate(table=transcript.txTable,
to_stop=True)
- cds_length = util.cds_length(mutator.newSplice(transcript.CDS.positionList))
- transcript.proteinDescription = util.protein_description(
- cds_length, protein_original, protein_variant)[0]
+ try:
+ cds_length = util.cds_length(
+ mutator.newSplice(transcript.CDS.positionList))
+ transcript.proteinDescription = util.protein_description(
+ cds_length, protein_original, protein_variant)[0]
+ except IndexError:
+ # Todo: Probably CDS start was hit by removal of exon...
+ transcript.proteinDescription = 'p.?'
+
else:
output.addMessage(__file__, 2, "ECDS", "CDS length is " \
"not a multiple of three in gene %s, transcript " \
diff --git a/mutalyzer/website.py b/mutalyzer/website.py
index 817bb0e35724299eb0b0d75add0bfee89323ef5b..be9c833b4362d8716ee0a53344e2cd02b5473e90 100644
--- a/mutalyzer/website.py
+++ b/mutalyzer/website.py
@@ -685,6 +685,13 @@ class Check:
genomic_description = output.getIndexedOutput('genomicDescription', 0, '')
+ # Create a tuple (description, link) from a description
+ def description_to_link(description):
+ link = None
+ if description[-1] != '?':
+ link = urllib.quote(description)
+ return description, link
+
# Todo: Generate the fancy HTML views for the proteins here instead
# of in mutalyzer/variantchecker.py.
args = {
@@ -697,7 +704,7 @@ class Check:
'chromDescription' : output.getIndexedOutput('genomicChromDescription', 0),
'genomicDNA' : genomic_dna,
'visualisation' : output.getOutput('visualisation'),
- 'descriptions' : map(lambda d: (d, urllib.quote(d)), output.getOutput('descriptions')),
+ 'descriptions' : map(description_to_link, output.getOutput('descriptions')),
'protDescriptions' : output.getOutput('protDescriptions'),
'oldProtein' : output.getOutput('oldProteinFancy'),
'altStart' : output.getIndexedOutput('altStart', 0),
diff --git a/tests/test_variantchecker.py b/tests/test_variantchecker.py
index be4c39bf5e585aa445850091e5f7e2cd5ba84dba..debc39bfdd49999a817e8668cf79e3e7634912de 100644
--- a/tests/test_variantchecker.py
+++ b/tests/test_variantchecker.py
@@ -262,7 +262,6 @@ class TestVariantchecker():
"""
Deletion of an entire exon with unknown offsets should be possible.
"""
- return # Todo
check_variant('NG_012772.1(BRCA2_v001):c.632-?_681+?del',
self.config, self.output)
assert len(self.output.getMessagesWithErrorCode('WOVERSPLICE')) > 0
@@ -275,6 +274,8 @@ class TestVariantchecker():
'NG_012772.1:g.(17550_19725)del')
assert 'NG_012772.1(BRCA2_v001):c.632-?_681+?del' \
in self.output.getOutput('descriptions')
+ assert 'NG_012772.1(BRCA2_i001):p.(Val211Glufs*10)' \
+ in self.output.getOutput('protDescriptions')
# Todo: .c notation should still be c.632-?_681+?del, but what about
# other transcripts?
@@ -287,7 +288,6 @@ class TestVariantchecker():
NG_012772.1(BRCA2_v001):c.68-?_316+?del is such a variant, since
positions 68 through 316 are exactly one exon and (316-68+1)/3 = 83.
"""
- return # Todo
check_variant('NG_012772.1(BRCA2_v001):c.68-?_316+?del',
self.config, self.output)
assert len(self.output.getMessagesWithErrorCode('WOVERSPLICE')) > 0
@@ -308,8 +308,7 @@ class TestVariantchecker():
Deletion of an entire exon with unknown offsets and another composed
variant with exact positioning should be possible.
"""
- return # Todo
- check_variant('UD_129433404385(DMD_v010):c.[281-?_492+?del;492+4del]',
+ check_variant('NG_012772.1(BRCA2_v001):c.[632-?_681+?del;681+4del]',
self.config, self.output)
assert len(self.output.getMessagesWithErrorCode('WOVERSPLICE')) > 0
assert len(self.output.getMessagesWithErrorCode('IDELSPLICE')) > 0
@@ -318,8 +317,28 @@ class TestVariantchecker():
assert self.output.getOutput('newprotein')
# Genomic positions should be centered in flanking introns and unsure.
assert_equal(self.output.getIndexedOutput('genomicDescription', 0),
- 'UD_129433404385:g.[(1640003_1675849)del;1665239del]')
- assert 'UD_129433404385(DMD_v010):c.[281-?_492+?del;492+4del]' \
+ 'NG_012772.1:g.[(17550_19725)del;19017del]')
+ assert 'NG_012772.1(BRCA2_v001):c.[632-?_681+?del;681+4del]' \
+ in self.output.getOutput('descriptions')
+ # Todo: .c notation should still be c.632-?_681+?del, but what about
+ # other transcripts?
+
+ def test_del_exon_unknown_offsets_reverse(self):
+ """
+ Deletion of an entire exon with unknown offsets should be possible,
+ also on the reverse strand.
+ """
+ check_variant('AL449423.14(CDKN2A_v001):c.151-?_457+?del',
+ self.config, self.output)
+ assert len(self.output.getMessagesWithErrorCode('WOVERSPLICE')) > 0
+ assert len(self.output.getMessagesWithErrorCode('IDELSPLICE')) > 0
+ # Todo: For now, the following is how to check if protein
+ # prediction is done.
+ assert self.output.getOutput('newprotein')
+ # Genomic positions should be centered in flanking introns and unsure.
+ assert_equal(self.output.getIndexedOutput('genomicDescription', 0),
+ 'AL449423.14:g.(60314_63683)del')
+ assert 'AL449423.14(CDKN2A_v001):c.151-?_457+?del' \
in self.output.getOutput('descriptions')
# Todo: .c notation should still be c.632-?_681+?del, but what about
# other transcripts?
diff --git a/tests/test_website.py b/tests/test_website.py
index de31f2c74cd84992b8046aafc15f0734263683f3..089e09a97cbdf1a27dd663921458c1b0d7e9ef15 100644
--- a/tests/test_website.py
+++ b/tests/test_website.py
@@ -577,7 +577,6 @@ facilisi."""
and thus the cached file from request i cannot be re-used in
request i+1.
"""
- return
r = self.app.get('/check')
form = r.forms[0]
form['mutationName'] = 'AB026906.1:c.274G>T'