def RNAmetasource2source(parameterlist):
"""
Output:
Gene Dict: Transcript Dict: chromosome, strand, startbase, cigar, txsize
"""
# empirical parameter
genewithnovelskippedexonpct=50
metasourcefilename=parameterlist[0][0]
filetype=parameterlist[1][0]
if parameterlist[1][1]=='no_novel_transcript':
novel_skipped_exon_flg=0
else:
novel_skipped_exon_flg=1
numgenes=int(parameterlist[1][2])
genelist=parameterlist[1][3]
if filetype=='gtf':
metasource=gtffile.gtfFile(metasourcefilename)
genetranscriptdict=metasource.getgenetranscriptdict()
elif filetype=='pck':
genetranscriptdict=cPickle.load(open(metasourcefilename))
allgenes=genetranscriptdict.keys()
if len(genelist)==0:
if numgenes==0:
numgenes=len(genetranscriptdict)
else:
numgenes=min(numgenes,len(genetranscriptdict))
choosegenes=random.sample(allgenes,numgenes)
else:
choosegenes=genelist[0:]
#print len(genelist),len(choosegenes)
outtranscriptdict={}
for gene in choosegenes:
txdict=genetranscriptdict[gene]
txexonslist=[txdict[tx][2] for tx in txdict]
if novel_skipped_exon_flg==1 and common.toss(genewithnovelskippedexonpct/100.0):
newtxflg=0
trys=0
while not newtxflg and trys<10:
trys+=1
tx=random.choice(txdict.keys())
txexons=txdict[tx][2]
if len(txexons)>2:
skipped=random.randint(1,len(txexons)-2)
newtx=txexons[:skipped-1]+txexons[skipped:]
if newtx not in txexonslist:
newtxflg=1
txdict['%s_skip'%tx]=[txdict[tx][0],txdict[tx][1],newtx]
outtranscriptdict[gene]={}
for tx in txdict:
cigartup=common.exonlist2cigar(txdict[tx][2])
outtranscriptdict[gene][tx]=[txdict[tx][0],txdict[tx][1],cigartup[0],cigartup[1],cigartup[2]]
return outtranscriptdict
cfg.setfdmfastpair(options.fdm_fast_pair)
if options.analysis_genefile != '':
cfg.setfdmgenefile(options.analysis_genefile)
if options.fdm_full_pair != '':
cfg.setfdmfullpair(options.fdm_full_pair)
if options.analysis_genefile != '':
cfg.setfdmgenefile(options.analysis_genefile)
message = 'Program Started'
common.printstatus(message, 'S', common.func_name())
rootdir = cfg.root_dir
gtffilename = cfg.annotation_file
gtffile = gtffile.gtfFile(gtffilename, 0, cfg.annotation_file_type)
gtffile.getgenetranscriptdict()
geneannodivdict = gtffile.getgeneannodivdict()
annochrjuncdict = gtffile.getchrjuncdict()
islanddict = gtffile.getislanddict()
genelist = islanddict.keys()
chrlist = gtffile.getchrlist()
islandlist = gtffile.getislandlist()
chrgenelistdict = {}
for island in islandlist:
chrnm = '%s' % island[0]
if chrnm not in chrgenelistdict:
chrgenelistdict[chrnm] = [island[3]]
cfg.setfdmfastpair(options.fdm_fast_pair)
if options.analysis_genefile!='':
cfg.setfdmgenefile(options.analysis_genefile)
if options.fdm_full_pair!='':
cfg.setfdmfullpair(options.fdm_full_pair)
if options.analysis_genefile!='':
cfg.setfdmgenefile(options.analysis_genefile)
message='Program Started'
common.printstatus(message,'S',common.func_name())
rootdir=cfg.root_dir
gtffilename=cfg.annotation_file
gtffile=gtffile.gtfFile(gtffilename,0,cfg.annotation_file_type)
gtffile.getgenetranscriptdict()
geneannodivdict=gtffile.getgeneannodivdict()
annochrjuncdict=gtffile.getchrjuncdict()
islanddict=gtffile.getislanddict()
genelist=islanddict.keys()
chrlist=gtffile.getchrlist()
islandlist=gtffile.getislandlist()
chrgenelistdict={}
for island in islandlist:
chrnm='%s'%island[0]
if chrnm not in chrgenelistdict:
chrgenelistdict[chrnm]=[island[3]]
def RNAmetasource2source(parameterlist):
"""
Output:
Gene Dict: Transcript Dict: chromosome, strand, startbase, cigar, txsize
"""
# empirical parameter
genewithnovelskippedexonpct = 50
metasourcefilename = parameterlist[0][0]
filetype = parameterlist[1][0]
if parameterlist[1][1] == 'no_novel_transcript':
novel_skipped_exon_flg = 0
else:
novel_skipped_exon_flg = 1
numgenes = int(parameterlist[1][2])
genelist = parameterlist[1][3]
if filetype == 'gtf':
metasource = gtffile.gtfFile(metasourcefilename)
genetranscriptdict = metasource.getgenetranscriptdict()
elif filetype == 'pck':
genetranscriptdict = cPickle.load(open(metasourcefilename))
allgenes = genetranscriptdict.keys()
if len(genelist) == 0:
if numgenes == 0:
numgenes = len(genetranscriptdict)
else:
numgenes = min(numgenes, len(genetranscriptdict))
choosegenes = random.sample(allgenes, numgenes)
else:
choosegenes = genelist[0:]
#print len(genelist),len(choosegenes)
outtranscriptdict = {}
for gene in choosegenes:
txdict = genetranscriptdict[gene]
txexonslist = [txdict[tx][2] for tx in txdict]
if novel_skipped_exon_flg == 1 and common.toss(
genewithnovelskippedexonpct / 100.0):
newtxflg = 0
trys = 0
while not newtxflg and trys < 10:
trys += 1
tx = random.choice(txdict.keys())
txexons = txdict[tx][2]
if len(txexons) > 2:
skipped = random.randint(1, len(txexons) - 2)
newtx = txexons[:skipped - 1] + txexons[skipped:]
if newtx not in txexonslist:
newtxflg = 1
txdict['%s_skip' %
tx] = [txdict[tx][0], txdict[tx][1], newtx]
outtranscriptdict[gene] = {}
for tx in txdict:
cigartup = common.exonlist2cigar(txdict[tx][2])
outtranscriptdict[gene][tx] = [
txdict[tx][0], txdict[tx][1], cigartup[0], cigartup[1],
cigartup[2]
]
return outtranscriptdict