def make_sjex(gtfpath, dstpre, np=12):
if UT.isstring(gtfpath):
gtf = GGB.read_gtf(gtfpath)
else:
gtf = gtfpath
sj,ex = gtf2exonsj(gtf, np=np)
print(ex.groupby(['kind','cat']).size())
ex.loc[ex['kind']=='5','cat'] = '5'
ex.loc[ex['kind']=='3','cat'] = '3'
UT.write_pandas(ex, dstpre+'.ex.txt.gz', 'h')
UT.write_pandas(sj, dstpre+'.sj.txt.gz', 'h')
# make ci
ci = UT.chopintervals(ex, dstpre+'.ci.txt.gz')
return {'sj':sj,'ex':ex}
def make_sjex(self, np=4):
sjpath, expath = self.sjexpaths()
if not os.path.exists(self.gtfpath):
raise RuntimeError('file {0} does not exist'.format(self.gtfpath))
LOG.info('making sj,ex...')
gtf = GGB.read_gtf(self.gtfpath) # ~ 1.5 min =>
# if 'cov' in gtf.iloc[0]['extra']:
# gtf['cov'] = GGB.get_gtf_attr_col(gtf, 'cov')
# convert gtf to sjex
pre = self.fname('graphpre{0}_'.format(uuid.uuid4()))
sj, ex = gtf2exonsj(gtf, np=np, graphpre=pre)
# save
UT.write_pandas(sj, sjpath, 'h')
UT.write_pandas(ex, expath, 'h')
return sj,ex
def make_sjexci(path, np):
if path[-3:]=='.gz':
bpath = path[:-3]
else:
bpath = path
ext = bpath[-4:]
if ext not in ['.gtf', '.bed', '.txt']:
raise ValueError('unknown filetype {0}, should be either .gtf,.bed (bed12),.txt (ucsc knownGene)'.format(ext))
pathprefix = bpath[:-4]
if not os.path.exists(path):
raise ValueError('{0} file does not exists'.format(ext))
if ext=='.gtf':
df = GGB.read_gtf(path).sort_values(['chr',])
sj, ex = gtf2exonsj(df, np=np)
elif ext=='.bed':
df = GGB.read_bed(path)
sj, ex = bed2exonsj(df, np=np)
elif ext=='.txt': # UCSC download
if 'knownGene' in path:
df = GGB.read_ucsc_knownGene(path)
sj, ex = kg2exonsj(df, np=np)
elif 'refGene' in path:
df = GGB.read_ucsc_refGene(path)
sj, ex = kg2exonsj(df, np=np) # same as kg
# save
LOG.info('saving sj to {0}'.format(pathprefix+'.sj.txt.gz'))
UT.write_pandas(sj, pathprefix+'.sj.txt.gz', 'h')
LOG.info('saving ex to {0}'.format(pathprefix+'.ex.txt.gz'))
UT.write_pandas(ex, pathprefix+'.ex.txt.gz', 'h')
# make ci
ci = UT.chopintervals(ex, pathprefix+'.ci.txt.gz')
return sj, ex
def test_read_gtf(g4gtfpath):
gtf = GGB.read_gtf(g4gtfpath)
assert len(gtf) == 112665
def g4Xkr4gtf(datadir):
"returns gencod4 Xkr4 gtf exons"
path = os.path.join(datadir, 'assemblies', 'gencode.vM4.Xkr4.gtf.gz')
return GGB.read_gtf(path)
def g4gtf(g4gtfpath):
#GTFCOLS = ['chr','src','typ','st','ed','sc1','strand','sc2','extra']
#return PD.read_table(g4gtfpath, names=GTFCOLS, compression='gzip')
return GGB.read_gtf(g4gtfpath)