Merge pull request #173 from FRED-2/develop

[INTERNAL] MutationSyntax annotates GeneID
FRED-2 · Jul 7, 2016 · b0466a7 · b0466a7
2 parents c4220b6 + f9ef1f9
commit b0466a7
Show file tree

Hide file tree

Showing 2 changed files with 7 additions and 6 deletions.
diff --git a/Fred2/Core/Variant.py b/Fred2/Core/Variant.py
@@ -37,9 +37,10 @@ class MutationSyntax():
     :param str cds: The complete cds_mutation_syntax string
     :param str aas: The complete protein_mutation_syntax string
     """
-    def __init__(self, transID, transPos, protPos, cds, aas):
+    def __init__(self, transID, transPos, protPos, cds, aas, geneID=None):
         #TODO: is protPos always given? what about synonymous variants?
         self.transID = transID
+        self.geneID = geneID
         self.tranPos = transPos
         self.protPos = protPos
         self.cdsMutationSyntax = cds  #c. ...
@@ -79,7 +80,6 @@ def __init__(self, id, type, chrom, genomePos, ref, obs, coding,
         self.genomePos = genomePos
         self.ref = ref.upper()
         self.obs = obs.upper()
-        self.gene = None
         self.isHomozygous = isHomozygous
         self.isSynonymous = isSynonymous
         self.coding = coding  # dict transcript_id:MutationSyntax

diff --git a/Fred2/IO/FileReader.py b/Fred2/IO/FileReader.py
@@ -127,7 +127,7 @@ def read_annovar_exonic(annovar_file, gene_filter=None, experimentalDesig=None):
     #fgd3:nm_001083536:exon6:c.g823a:p.v275i,fgd3:nm_001286993:exon6:c.g823a:p.v275i,fgd3:nm_033086:exon6:c.g823a:p.v275i
     #RE = re.compile("\w+:(\w+):exon\d+:c.(\D*)(\d+)_*(\d*)(\D\w*):p.\w+:\D*->\D*:(\D).*?,")
     #RE = re.compile("\w+:(\w+):exon\d+:c.(\D*)(\d+)_*(\d*)(\D\w*):p.(\D*)(\d+)_*(\d*)(\D\w*):(\D).*?,")
-    RE = re.compile("((\w+):exon\d+:c.\D*(\d+)\D\w*:p.\D*(\d+)\D\w*)")
+    RE = re.compile("((\w+):(\w+):exon\d+:c.\D*(\d+)\D\w*:p.\D*(\d+)\D\w*)")
     type_mapper = {('synonymous', 'snv'): VariationType.SNP,
                    ('nonsynonymous', 'snv'): VariationType.SNP,
                    ('stoploss', 'snv'): VariationType.SNP,
@@ -157,13 +157,14 @@ def read_annovar_exonic(annovar_file, gene_filter=None, experimentalDesig=None):
             #print "Debug ", line, RE.findall(line), type, zygos
             coding = {}
             for nm_id_pos in RE.findall(line):
-                mutation_string, nm_id, trans_pos, prot_start = nm_id_pos
+                mutation_string, geneID, nm_id, trans_pos, prot_start = nm_id_pos
                 #print "Debug ",nm_id_pos
 
                 nm_id = nm_id.upper()
-                _, _, trans_coding, prot_coding = mutation_string.split(":")
+                _,_, _, trans_coding, prot_coding = mutation_string.split(":")
                 #internal transcript and protein position start at 0!
-                coding[nm_id] = MutationSyntax(nm_id, int(trans_pos)-1, int(prot_start)-1, trans_coding, prot_coding)
+                coding[nm_id] = MutationSyntax(nm_id, int(trans_pos)-1, int(prot_start)-1, trans_coding, prot_coding,
+                                               geneID=geneID.upper())
 
             ty = tuple(mut_type.split())