def gene2go( pfam2goFn,fn,tblout,eTh=1e-05,source='broad'):
"""
"""
pfam2go = load_pfam2go( pfam2goFn )
if source=="broad":
prot2pfam = load_broad_pfam( tblout,eTh )
elif source=="tblout":
prot2pfam = load_pfam_tblout( tblout,eTh )
else:
sys.exit("Specify valid source: tblout or broad!")
out = open( fn+'.go','w')
for prot in prot2pfam:
j=0
line='%s\t' % prot
for pfam in prot2pfam[prot]:
pfamShort = pfam.split('.')[0]
if not pfamShort in pfam2go:
continue
for go in pfam2go[pfamShort]:
line+='%s;' % go
j+=1
if j:
out.write( line.strip(';')+"\n" )
out.close()
def gene2go(pfam2goFn, fn, tblout, eTh=1e-05, source='broad'):
"""
"""
pfam2go = load_pfam2go(pfam2goFn)
if source == "broad":
prot2pfam = load_broad_pfam(tblout, eTh)
elif source == "tblout":
prot2pfam = load_pfam_tblout(tblout, eTh)
else:
sys.exit("Specify valid source: tblout or broad!")
out = open(fn + '.go', 'w')
for prot in prot2pfam:
j = 0
line = '%s\t' % prot
for pfam in prot2pfam[prot]:
pfamShort = pfam.split('.')[0]
if not pfamShort in pfam2go:
continue
for go in pfam2go[pfamShort]:
line += '%s;' % go
j += 1
if j:
out.write(line.strip(';') + "\n")
out.close()
def report(files, pfam, annotation, tab, pTh, verbose):
""" """
#load pfam annotation
geneid2pfam, geneid2annotation, geneid2tab = {}, {}, {}
if pfam:
geneid2pfam = load_pfam_tblout(pfam)
sys.stderr.write(" PFAMs for %s entries loaded.\n" % len(geneid2pfam))
if tab:
geneid2tab = load_annotation(open(tab))
sys.stderr.write(" Tab annotation for %s entries loaded.\n" %
len(geneid2tab))
if annotation:
if annotation.endswith('.gff'):
geneid2annotation = load_gff_annotation(open(annotation))
elif annotation.endswith('.gtf'):
geneid2annotation = load_gtf_annotation(open(annotation))
else:
geneid2annotation = load_annotation(open(annotation), True)
sys.stderr.write(" Annotations for %s entries loaded.\n" %
len(geneid2annotation))
#load all cuffdiff files
fn2data = {}
fnames = []
for f in files:
fn = f.name
fnames.append(fn)
fn2data[fn] = load_cuffdiff(f)
#write output
header = "#transcript id\tgene id"
for fn in fnames:
header += "\tcontrol\t%s\tlog2(FC)\tP-value" % fn
header += "\tannotation\n"
sys.stdout.write(header)
#open outfiles for ids
outfiles = [open("%s.%s.ids" % (fn, pTh), "w") for fn in fnames]
#process all genes
for transid in sorted(fn2data[fn]):
lineData = []
pFilter = False
exprData = [fn2data[fn][transid] for fn in fnames] #; print exprData
for exprTuple, out in zip(exprData, outfiles):
geneid, locus, v1, v2, log_fc, p = exprTuple
if not lineData:
lineData = [transid, geneid]
lineData += [str(v1), str(v2), str(log_fc), str(p)]
#check p value
if p <= pTh:
pFilter = True
out.write(geneid + "\n")
if pFilter:
#add PFAM annotation
annList = []
if transid in geneid2pfam:
if type(geneid2pfam[transid]) is list:
annList.append(";".join(geneid2pfam[transid]))
else:
for pfam, data in geneid2pfam[transid].iteritems():
annList.append("%s [%s]" % (data[1], pfam))
lineData.append("; ".join(annList))
#add tab annotation
annList = []
if geneid2tab and transid in geneid2tab:
annList.append(";".join(geneid2tab[transid]))
lineData.append("; ".join(annList))
#add Arabidopsis annotation
if transid in geneid2annotation:
for ann in geneid2annotation[transid]:
lineData.append(ann)
#output info
sys.stdout.write("\t".join(lineData) + "\n")
for out in outfiles:
out.close()
def report(files, pfam, annotation, tab, pTh, verbose):
""" """
#load pfam annotation
geneid2pfam, geneid2annotation, geneid2tab = {}, {}, {}
if pfam:
geneid2pfam = load_pfam_tblout(pfam)
sys.stderr.write(" PFAMs for %s entries loaded.\n" % len(geneid2pfam))
if tab:
geneid2tab = load_annotation(open(tab))
sys.stderr.write(" Tab annotation for %s entries loaded.\n" % len(geneid2tab))
if annotation:
if annotation.endswith('.gff'):
geneid2annotation = load_gff_annotation(open(annotation))
elif annotation.endswith('.gtf'):
geneid2annotation = load_gtf_annotation(open(annotation))
else:
geneid2annotation = load_annotation(open(annotation),True )
sys.stderr.write( " Annotations for %s entries loaded.\n" % len(geneid2annotation) )
#load all cuffdiff files
fn2data = {}
fnames = []
for f in files:
fn = f.name
fnames.append(fn)
fn2data[fn] = load_cuffdiff(f)
#write output
header = "#transcript id\tgene id"
for fn in fnames:
header += "\tcontrol\t%s\tlog2(FC)\tP-value" % fn
header += "\tannotation\n"
sys.stdout.write( header )
#open outfiles for ids
outfiles = [ open( "%s.%s.ids" % (fn,pTh),"w") for fn in fnames ]
#process all genes
for transid in sorted(fn2data[fn]):
lineData = []
pFilter=False
exprData = [ fn2data[fn][transid] for fn in fnames ] #; print exprData
for exprTuple,out in zip(exprData,outfiles):
geneid,locus,v1,v2,log_fc,p = exprTuple
if not lineData:
lineData = [ transid,geneid ]
lineData += [ str(v1), str(v2), str(log_fc),str(p) ]
#check p value
if p<=pTh:
pFilter = True
out.write( geneid+"\n" )
if pFilter:
#add PFAM annotation
annList=[]
if transid in geneid2pfam:
if type(geneid2pfam[transid]) is list:
annList.append(";".join(geneid2pfam[transid]))
else:
for pfam,data in geneid2pfam[transid].iteritems():
annList.append( "%s [%s]" % (data[1],pfam) )
lineData.append( "; ".join(annList))
#add tab annotation
annList=[]
if geneid2tab and transid in geneid2tab:
annList.append(";".join(geneid2tab[transid]))
lineData.append( "; ".join(annList))
#add Arabidopsis annotation
if transid in geneid2annotation:
for ann in geneid2annotation[transid]:
lineData.append( ann )
#output info
sys.stdout.write( "\t".join( lineData ) + "\n" )
for out in outfiles:
out.close()
