handle2=open(ECfilename ,'r')
strand="+"
for line in handle2:
row=line.strip().split("\t")
gene=row[0].split('.')[0]
if gene==id:
transcript_length=0
variant_exons[row[0]]={}
variant=ISOFORM(id=row[0],chr=row[1],strand=row[2],chr_start=int(row[3]),chr_end=int(row[4]),cds_start=int(row[5]),cds_end=int(row[6]),exon=int(row[7]))
variant.chr_span=int(row[4])-int(row[3])
strand=row[2]
startlist=row[8].split(',')
endlist=row[9].split(',')
for i in range(len(endlist[:-1])):
exon=EXON(variant=row[0],chr=row[1],strand=row[2])
if variant.strand=="+":
exon.number=i+1
exon.start=int(startlist[i])
exon.end=int(endlist[i])
else:
exon.number=len(endlist[:-1])-i
exon.start=int(endlist[i])
exon.end=int(startlist[i])
exon.length=abs(exon.end-exon.start)
transcript_length+=exon.length
variant_exons[row[0]][exon.number]=exon
variant.transcript_length=transcript_length
variantID = row[0]
geneID = row[0].split(".")[0]
if geneID in gene_variant:
gene_variant[geneID].append(row[0])
if variantID in variant_dic:
chr_start_list = row[8][:-1].split(",")
chr_end_list = row[9][:-1].split(",")
variant_dic[variantID].chr = row[1]
variant_dic[variantID].strand = row[2]
variant_dic[variantID].cdsStart = int(row[5])
variant_dic[variantID].cdsEnd = int(row[6])
variant_dic[variantID].exon = []
tx = 1
for i in range(len(chr_start_list)):
exon = EXON(variant=row[0], chr=row[1], strand=row[2])
exon.number = i + 1
if int(chr_start_list[i]
) >= variant_dic[variantID].cdsStart and int(
chr_end_list[i]) <= variant_dic[variantID].cdsEnd:
exon.start = int(chr_start_list[i])
exon.end = int(chr_end_list[i])
exonlen = exon.end - exon.start
exon.trans_start = tx
exon.trans_end = tx + exonlen - 1
tx += exonlen
elif int(
chr_end_list[i]
) >= variant_dic[variantID].cdsStart and int(
chr_start_list[i]) <= variant_dic[variantID].cdsStart:
exon.start = variant_dic[variantID].cdsStart
geneID=row[0].split(".")[0]
if geneID in gene_variant:
gene_variant[geneID].append(row[0])
if variantID in variant_dic:
chr_start_list=row[8][:-1].split(",")
chr_end_list=row[9][:-1].split(",")
variant_dic[variantID].chr=row[1]
variant_dic[variantID].strand=row[2]
variant_dic[variantID].cdsStart=int(row[5])
variant_dic[variantID].cdsEnd=int(row[6])
variant_dic[variantID].exon=[]
tx=1
for i in range(len(chr_start_list)):
exon=EXON(variant=row[0],chr=row[1],strand=row[2])
exon.number=i+1
if int(chr_start_list[i])>=variant_dic[variantID].cdsStart and int(chr_end_list[i])<=variant_dic[variantID].cdsEnd:
exon.start=int(chr_start_list[i])
exon.end=int(chr_end_list[i])
exonlen=exon.end-exon.start
exon.trans_start=tx
exon.trans_end=tx+exonlen-1
tx+=exonlen
elif int(chr_end_list[i])>=variant_dic[variantID].cdsStart and int(chr_start_list[i])<=variant_dic[variantID].cdsStart:
exon.start=variant_dic[variantID].cdsStart
exon.end=int(chr_end_list[i])
exonlen=exon.end-exon.start
exon.trans_start=tx
exon.trans_end=tx+exonlen-1
tx+=exonlen
variant_exons[row[0]] = {}
variant = ISOFORM(id=row[0],
chr=row[1],
strand=row[2],
chr_start=int(row[3]),
chr_end=int(row[4]),
cds_start=int(row[5]),
cds_end=int(row[6]),
exon=int(row[7]))
variant.chr_span = int(row[4]) - int(row[3])
strand = row[2]
startlist = row[8].split(',')
endlist = row[9].split(',')
for i in range(len(endlist[:-1])):
exon = EXON(variant=row[0], chr=row[1], strand=row[2])
if variant.strand == "+":
exon.number = i + 1
exon.start = int(startlist[i])
exon.end = int(endlist[i])
else:
exon.number = len(endlist[:-1]) - i
exon.start = int(endlist[i])
exon.end = int(startlist[i])
exon.length = abs(exon.end - exon.start)
transcript_length += exon.length
variant_exons[row[0]][exon.number] = exon
variant.transcript_length = transcript_length
