def process_alts( ref,alts,contig,pos,contig2position,gene2position,contig2fasta,l ):
"""
"""
outline = ""
for alt in alts:
genes = filter( lambda x: x[0]<pos+1<x[1], contig2position[contig] )
if genes:
for start,stop,feature,geneid in genes:
# check effect of mutations
if len(ref)!=len(alt): # indel
if feature == 'gene':
contig,CDSs,strand,function = gene2position[geneid] # get exons
cds = filter( lambda x: x[0]<pos+1<x[1],CDSs ) # check if overlaping with indel
if cds and len(ref)%3 != len(alt)%3:
outline += "%s\texonic\t%s\tframe-shift\t\t\t\t\t\t%s\n" % ( l,geneid,function )
else:
outline += "%s\tintronic\t%s\t\t\t\t\t\t%s\n" % ( l,geneid,function )
else:
outline += "%s\tintergenic\n" % l
elif feature == 'gene':
contig,CDSs,strand,function = gene2position[geneid]
outline += "%s\t%s\t%s\n" % ( l,coding_snp_info( contig2fasta[contig],geneid,CDSs,strand,ref,alt,pos ),function )
else:
outline += "%s\t%s\n" % ( l,feature )
else:
outline += "%s\tintergenic\n" % ( l, )
return outline
def process_alt(
ref, alt, contig, pos, contig2position, gene2position, contig2fasta, trans2ann, trans2pfam, trans2tab, l
):
""" """
outline = ""
genes = []
if contig in contig2position:
genes = filter(lambda x: x[0] < pos + 1 < x[1], contig2position[contig])
if genes:
for start, stop, feature, geneid in genes:
if feature == "gene":
fastaAnn = pfamAnn = tabAnn = ""
if geneid in trans2ann:
fastaAnn = trans2ann[geneid]
if geneid in trans2pfam:
pfamAnn = trans2pfam[geneid]
if geneid in trans2tab:
tabAnn = trans2tab[geneid]
contig, CDSs, strand, function, frame = gene2position[geneid]
outline += "%s\t%s\t%s\t%s\t%s\t%s\n" % (
l,
coding_snp_info(contig2fasta[contig], geneid, CDSs, strand, ref, alt, pos),
function,
fastaAnn,
pfamAnn,
"; ".join(tabAnn),
)
else:
outline += "%s\t%s\n" % (l, feature)
else:
outline += "%s\tintergenic\n" % (l,)
return outline
def process_alt(ref, alt, contig, pos, contig2position, gene2position, contig2fasta, \
trans2ann, trans2pfam, trans2tab, l):
""" """
outline = ""
genes = []
if contig in contig2position:
genes = filter(lambda x: x[0]<pos+1<x[1], contig2position[contig])
if genes:
for start,stop,feature,geneid in genes:
if feature == 'gene':
fastaAnn = pfamAnn = tabAnn = ""
if geneid in trans2ann:
fastaAnn = trans2ann[geneid]
if geneid in trans2pfam:
pfamAnn = trans2pfam[geneid]
if geneid in trans2tab:
tabAnn = trans2tab[geneid]
contig,CDSs,strand,function,frame = gene2position[geneid]
outline += "%s\t%s\t%s\t%s\t%s\t%s\n" % (l, coding_snp_info(contig2fasta[contig], geneid, CDSs, strand, ref, alt, pos), function, fastaAnn, pfamAnn, "; ".join(tabAnn))
else:
outline += "%s\t%s\n" % (l, feature)
else:
outline += "%s\tintergenic\n" % (l,)
return outline
def process_alt( ref,alt,contig,pos,contig2position,gene2position,contig2fasta,l ):
"""
"""
outline = ""
genes = filter( lambda x: x[0]<pos+1<x[1], contig2position[contig] )
if genes:
for start,stop,feature,geneid in genes:
# check effect of mutations
if len(ref)!=len(alt): # indel
if feature == 'gene':
contig,CDSs,strand,function = gene2position[geneid] # get exons
cds = filter( lambda x: x[0]<pos+1<x[1],CDSs ) # check if overlaping with indel
if cds and len(ref)%3 != len(alt)%3:
outline += "%s\texonic\t%s\tframe-shift\t\t\t\t\t\t%s\n" % ( l,geneid,function )
else:
outline += "%s\tintronic\t%s\t\t\t\t\t\t%s\n" % ( l,geneid,function )
else:
outline += "%s\tintergenic\n" % l
elif feature == 'gene':
contig,CDSs,strand,function = gene2position[geneid]
outline += "%s\t%s\t%s\n" % ( l,coding_snp_info( contig2fasta[contig],geneid,CDSs,strand,alt,pos ),function )
else:
outline += "%s\t%s\n" % ( l,feature )
else:
outline += "%s\tintergenic\n" % ( l, )
return outline