def parseRecord(self, fields):
if (len(fields) > 9):
raise Exception("too many fields in GFF3 record" +
"\t".join(fields))
(substrate, source, type, begin, end, score, strand, frame,
extra) = fields
extra = extra.rstrip()
extraFields = extra.split(";")
extraHash = {}
rex = Rex()
for field in extraFields:
if (not rex.find("(.+)=(.+)", field)):
raise Exception("Can't parse GFF3 field: " + field)
key = rex[1]
value = rex[2]
extraHash[key] = value
rec = {
"substrate": substrate,
"source": source,
"type": type,
"begin": int(begin) - 1,
"end": int(end),
"score": score,
"strand": strand,
"frame": frame,
"extra": extraHash
}
return rec
def loadGFF_UTR(self,fields,line,transcriptBeginEnd,GFF,
transcripts,readOrder,genes):
exonBegin=int(fields[3])-1
exonEnd=int(fields[4])
exonScore=fields[5]
strand=fields[6]
frame=fields[7]
transcriptId=None
rex=Rex()
if(rex.find('transgrp[:=]\s*(\S+)',line)): transcriptId=rex[1]
elif(rex.find('transcript_id[:=]?\s*"?([^\s";]+)"?',line)):
transcriptId=rex[1]
elif(rex.find('Parent=([^;,\s]+)',line)): transcriptId=rex[1]
geneId=None
if(rex.find('genegrp=(\S+)',line)): geneId=rex[1]
elif(rex.find('gene_id[:=]?\s*"?([^\s\;"]+)"?',line)): geneId=rex[1]
if(transcriptId is None): transcriptId=geneId
if(geneId is None): geneId=transcriptId
if(transcriptId is None):
raise Exception(line+" : no transcript ID found")
if(rex.find("(\S+);$",transcriptId)): transcriptId=rex[1]
if(rex.find("(\S+);$",geneId)): geneId=rex[1]
extra=""
for i in range(8,len(fields)): extra+=fields[i]+" "
if(exonBegin>exonEnd): (exonBegin,exonEnd)=(exonEnd,exonBegin)
transcript=transcripts.get(transcriptId,None)
if(not transcript):
transcripts[transcriptId]=transcript= \
Transcript(transcriptId,strand)
transcript.setStopCodons(self.stopCodons)
transcript.readOrder=readOrder
readOrder+=1
transcript.substrate=fields[0]
transcript.source=fields[1]
if(transcriptBeginEnd.get(transcriptId,None) is not None):
(begin,end)=transcriptBeginEnd[transcriptId]
transcript.setBegin(begin)
transcript.setEnd(end)
else:
transcript.setBegin(exonBegin)
transcript.setEnd(exonEnd)
transcript.geneId=geneId
gene=genes.get(geneId,None)
if(gene is None):
genes[geneId]=gene=Gene(); gene.setId(geneId)
transcript.setGene(gene)
exon=Exon(exonBegin,exonEnd,transcript)
exon.extraFields=extra
if(transcript.rawExons is not None):
exon.frame=frame
exon.score=exonScore
exon.type=fields[2]
transcript.rawExons.append(exon)
elif(not transcript.exonOverlapsExon(exon)):
exon.frame=frame
exon.score=exonScore
exon.type=fields[2]
transcript.UTR.append(exon) # OK -- we sort later
gene.addTranscript(transcript)
def crear_aldea(nombre, num_rex, num_spinosaurus, num_triceraptors):
a = Aldea(nombre)
for i in range(num_rex):
a.add_dinosaurio(
Rex("r" + str(i), 1000, random.randrange(-200, 200), a))
for i in range(num_spinosaurus):
a.add_dinosaurio(
Spinosaurus("s" + str(i), 1000, random.randrange(-200, 200),
a))
for i in range(num_triceraptors):
a.add_dinosaurio(
Triceraptors("t" + str(i), 1000, random.randrange(-200, 200),
a))
return a
def loadGFF_transcript(self,fields,line,transcriptBeginEnd,GFF,
transcripts,readOrder,genes):
begin=int(fields[3])-1
end=int(fields[4])
rex=Rex()
if(rex.find('transcript_id[:=]?\s*"?([^\s";]+)"?',line)):
transcriptId=rex[1]
transcriptBeginEnd[transcriptId]=[begin,end]
strand=fields[6]
score=fields[5]
transcriptExtraFields=""
for i in range(8,len(fields)):
transcriptExtraFields+=fields[i]+" "
transcript=transcripts.get(transcriptId,None)
if(transcript is None):
transcripts[transcriptId]=transcript= \
Transcript(transcriptId,strand)
transcript.setStopCodons(self.stopCodons)
transcript.readOrder=readOrder;
readOrder+=1
transcript.substrate=fields[0]
transcript.source=fields[1]
transcript.setBegin(begin)
transcript.setEnd(end)
if(transcript.score is None and
score!="."): transcript.score=float(score)
geneId=None
if(rex.find("genegrp=(\S+)",line)): geneId=rex[1]
elif(rex.find('gene_id[:=]?\s*\"?([^\s\;"]+)\"?',line)):
geneId=rex[1]
if(not geneId): raise Exception("can't parse GTF: "+line)
transcript.geneId=geneId
gene=genes.get(geneId,None)
if(not gene): genes[geneId]=gene=Gene(); gene.setId(geneId)
transcript.setGene(gene)
gene.addTranscript(transcript)
transcript.extraFields=transcriptExtraFields
# This is OPEN SOURCE SOFTWARE governed by the Gnu General Public
# License (GPL) version 3, as described at www.opensource.org.
#=========================================================================
from __future__ import (absolute_import, division, print_function,
unicode_literals, generators, nested_scopes,
with_statement)
from builtins import (bytes, dict, int, list, object, range, str, ascii, chr,
hex, input, next, oct, open, pow, round, super, filter,
map, zip)
# The above imports should allow this program to run in both Python 2 and
# Python 3. You might need to update your version of module "future".
import sys
import ProgramName
import gzip
from Rex import Rex
rex = Rex()
from scipy import stats
from statsmodels.stats.multitest import multipletests
def getCounts(filename, variants, MIN_COUNT):
counts = {}
with open(filename, "rt") as IN:
for line in IN:
fields = line.rstrip().split()
if (len(fields) != 7): continue
(id, chr, pos, ref, alt, refCount, altCount) = fields
refCount = int(refCount)
altCount = int(altCount)
if (refCount + altCount < MIN_COUNT): continue
counts[id] = [refCount, altCount]
