gensimulatedreadsdata(sample_id,replicate_id,folderdict,genetxreaddict,genetxcigardict,cfg)
if cfg.numtypes==1:
genetxreaddict=getsimulatedoneexpression(genetxcountdict,cfg.readcount)
for replicate_id in range(1,cfg.numdatasets+1):
sample_id=1
gensimulatedreadsdata(sample_id,replicate_id,folderdict,genetxreaddict,genetxcigardict,cfg)
if cfg.numtypes==2:
#print cfg.coverageratiodistribution,cfg.jsddistribution
genetwoexpressions=getsimulatedtwoexpressions(genetxcountdict,cfg.coverageratiodistribution,cfg.jsddistribution,cfg.readcount,cfg.fold_flg)
genetxreaddict1=dict([(gene,[genetwoexpressions[gene][0],genetwoexpressions[gene][2]]) for gene in genetwoexpressions])
genetxreaddict2=dict([(gene,[genetwoexpressions[gene][1],genetwoexpressions[gene][3]]) for gene in genetwoexpressions])
jsdmetadatafile='%s/expression_jsd.txt'%(folderdict['metadata'])
fout=open(jsdmetadatafile,'w')
for gene in genetwoexpressions:
fout.write('%s\t% 7d\t% 7d\t%s\t%s\t%6.4f\n'%(gene,genetwoexpressions[gene][0],genetwoexpressions[gene][1],
common.fl2str(genetwoexpressions[gene][2]),common.fl2str(genetwoexpressions[gene][3]),
genetwoexpressions[gene][4]))
fout.close()
#Todo Plot
sample_id=1
for replicate_id in range(1,cfg.numdatasets+1):
gensimulatedreadsdata(sample_id,replicate_id,folderdict,genetxreaddict1,genetxcigardict,cfg)
sample_id=2
for replicate_id in range(1,cfg.numdatasets+1):
gensimulatedreadsdata(sample_id,replicate_id,folderdict,genetxreaddict2,genetxcigardict,cfg)
# if debug_flg==0:
# deletesamfiles(folderdict)
#print folderdict
deletesamfiles(folderdict)
def divdictToflow(self,divdict):
'''
divdict=position:[[incoming/outgoing=0,1,exonstart=0=no,1=yes,2=start transcript,3=end transcript][exon, flowlist]]
exonstart=0=no,1=yes,2=start transcript and exonstart,3=end transcript and exonstart,4=start transcript and no exonstart(insplice),
5=end transcript and no exonstart outsplice
flowlist=[exon/splicelist]
wtgraphstruct=(exonlist,intronlist,splicelist,startnodelist,endnodelist,novelnodelist,exonwtlist,intronwtlist,splicewtlist)
flowlist len=1 for start or end transcript
getedgevalue edgetype = 10/11,20/21,3 = exon,intron,splice
flowdict[position]=[[outgoingflg,exonstartflg],[[wt1,wt2],nflowvec]]
'''
flowdict={}
for position in divdict.keys():
flowvec=[]
outgoingflg,exonstartflg=divdict[position][0]
exon,flowlist=divdict[position][1]
#message='Flowlist : %s'%str(flowlist)
#common.printstatus(message,'S',common.func_name())
edgetype=10+outgoingflg
wt1=self.getedgevalue(exon,edgetype)[0]
if exonstartflg==2:
if len(flowlist)!=1:
message='Transcript Start Exon has incoming splice; Flowlist : %s, %s'%(str(exon),common.fl2str(flowlist))
common.printstatus(message,'W',common.func_name())
else:
#incoming flow
edgetype=10+outgoingflg
#prev exon
wtoth=self.getedgevalue(flowlist[0],edgetype)[0]
flowvec=[wtoth,max(wt1-wtoth,0)]
if wt1-wtoth<0:
message='Flow decreases at transcript start exon: %s; Prev Exon: %s; Weight Start=%10.4f, Before=%10.4f'%(str(exon),common.fl2str(flowlist[0]),wt1,wtoth)
common.printstatus(message,'W',common.func_name())
#wt2=wt1
wt2=sum(flowvec)
elif exonstartflg==3:
if len(flowlist)!=1:
message='Transcript End Exon has outgoing splice; Flowlist : %s, %s'%(str(exon),common.fl2str(flowlist))
common.printstatus(message,'W',common.func_name())
else:
#outgoing flow
edgetype=10+outgoingflg
#next exon
wtoth=self.getedgevalue(flowlist[0],edgetype)[0]
flowvec=[wtoth,max(wt1-wtoth,0)]
if wt1-wtoth<0:
message='Flow increases at transcript end exon %s: Prev Exon: %s; Weight End=%10.4f, After=%10.4f'%(str(exon),common.fl2str(flowlist[0]),wt1,wtoth)
common.printstatus(message,'W',common.func_name())
#wt2=wt1
wt2=sum(flowvec)
elif exonstartflg==1:
flowvec=[]
edgetype=10+outgoingflg
flowvec.append(self.getedgevalue(flowlist[0],edgetype)[0])
for flowedge in flowlist[1:]:
flowvec.append(self.getedgevalue(flowedge,3)[0])
wt2=sum(flowvec)
elif exonstartflg==0:
flowvec=[]
for flowedge in flowlist:
flowvec.append(self.getedgevalue(flowedge,3)[0])
wt2=sum(flowvec)
if len(flowvec)>0:
nflowvec=common.normalize_vector(flowvec)
flowdict[position]=[[outgoingflg,exonstartflg],[[wt1,wt2],nflowvec]]
return flowdict
cfg.jsddistribution, cfg.readcount, cfg.fold_flg)
genetxreaddict1 = dict([
(gene, [genetwoexpressions[gene][0], genetwoexpressions[gene][2]])
for gene in genetwoexpressions
])
genetxreaddict2 = dict([
(gene, [genetwoexpressions[gene][1], genetwoexpressions[gene][3]])
for gene in genetwoexpressions
])
jsdmetadatafile = '%s/expression_jsd.txt' % (folderdict['metadata'])
fout = open(jsdmetadatafile, 'w')
for gene in genetwoexpressions:
fout.write('%s\t% 7d\t% 7d\t%s\t%s\t%6.4f\n' %
(gene, genetwoexpressions[gene][0],
genetwoexpressions[gene][1],
common.fl2str(genetwoexpressions[gene][2]),
common.fl2str(genetwoexpressions[gene][3]),
genetwoexpressions[gene][4]))
fout.close()
#Todo Plot
sample_id = 1
for replicate_id in range(1, cfg.numdatasets + 1):
gensimulatedreadsdata(sample_id, replicate_id, folderdict,
genetxreaddict1, genetxcigardict, cfg)
sample_id = 2
for replicate_id in range(1, cfg.numdatasets + 1):
gensimulatedreadsdata(sample_id, replicate_id, folderdict,
genetxreaddict2, genetxcigardict, cfg)
# if debug_flg==0:
# deletesamfiles(folderdict)