def bgzip_and_tabix(fpath, reuse=False, tabix_parameters='', **kwargs):
gzipped_fpath = join(fpath + '.gz')
tbi_fpath = gzipped_fpath + '.tbi'
if reuse and \
file_exists(gzipped_fpath) and (getctime(gzipped_fpath) >= getctime(fpath) if file_exists(fpath) else True) and \
file_exists(tbi_fpath) and getctime(tbi_fpath) >= getctime(gzipped_fpath):
info('Actual compressed file and index exist, reusing')
return gzipped_fpath
info('Compressing and tabixing file, writing ' + gzipped_fpath + '(.tbi)')
bgzip = which('bgzip')
tabix = which('tabix')
if not bgzip:
err('Cannot index file because bgzip is not found')
if not tabix:
err('Cannot index file because tabix is not found')
if not bgzip and not tabix:
return fpath
if isfile(gzipped_fpath):
os.remove(gzipped_fpath)
if isfile(tbi_fpath):
os.remove(tbi_fpath)
info('BGzipping ' + fpath)
cmdline = '{bgzip} {fpath}'.format(**locals())
call_process.run(cmdline)
info('Tabixing ' + gzipped_fpath)
cmdline = '{tabix} {tabix_parameters} {gzipped_fpath}'.format(**locals())
call_process.run(cmdline)
return gzipped_fpath
def bgzip_and_tabix(fpath, reuse=False, tabix_parameters='', **kwargs):
gzipped_fpath = join(fpath + '.gz')
tbi_fpath = gzipped_fpath + '.tbi'
if reuse and \
file_exists(gzipped_fpath) and (getctime(gzipped_fpath) >= getctime(fpath) if file_exists(fpath) else True) and \
file_exists(tbi_fpath) and getctime(tbi_fpath) >= getctime(gzipped_fpath):
info('Actual compressed file and index exist, reusing')
return gzipped_fpath
info('Compressing and tabixing file, writing ' + gzipped_fpath + '(.tbi)')
bgzip = which('bgzip')
tabix = which('tabix')
if not bgzip:
err('Cannot index file because bgzip is not found')
if not tabix:
err('Cannot index file because tabix is not found')
if not bgzip and not tabix:
return fpath
if isfile(gzipped_fpath):
os.remove(gzipped_fpath)
if isfile(tbi_fpath):
os.remove(tbi_fpath)
info('BGzipping ' + fpath)
cmdline = '{bgzip} {fpath}'.format(**locals())
call_process.run(cmdline)
info('Tabixing ' + gzipped_fpath)
cmdline = '{tabix} {tabix_parameters} {gzipped_fpath}'.format(**locals())
call_process.run(cmdline)
return gzipped_fpath
def ungzip_if_needed(cnf, fpath, silent=False):
if fpath.endswith('.gz'):
fpath = fpath[:-3]
if not file_exists(fpath) and file_exists(fpath + '.gz'):
gz_fpath = fpath + '.gz'
cmdline = 'gunzip -c {gz_fpath} > {fpath}'.format(**locals())
res = run_simple(cmdline)
if not silent: info()
if not res:
return None
return fpath
def ungzip_if_needed(cnf, fpath, silent=False):
if fpath.endswith('.gz'):
fpath = fpath[:-3]
if not file_exists(fpath) and file_exists(fpath + '.gz'):
gz_fpath = fpath + '.gz'
cmdline = 'gunzip -c {gz_fpath}'.format(**locals())
res = run(cmdline, output_fpath=fpath)
if not silent: info()
if not res:
return None
return fpath
def tx2genefile(gtf, out_file=None):
"""
write out a file of transcript->gene mappings.
use the installed tx2gene.csv if it exists, else write a new one out
"""
installed_tx2gene = os.path.join(os.path.dirname(gtf), "tx2gene.csv")
if file_exists(installed_tx2gene):
return installed_tx2gene
if file_exists(out_file):
return out_file
with file_transaction(out_file) as tx_out_file:
with open(tx_out_file, "w") as out_handle:
for k, v in transcript_to_gene(gtf).items():
out_handle.write(",".join([k, v]) + "\n")
return out_file
def partition_gtf(gtf, coding=False, out_file=False):
"""
return a GTF file of all non-coding or coding transcripts. the GTF must be annotated
with gene_biotype = "protein_coding" or to have the source column set to the
biotype for all coding transcripts. set coding to
True to get only the coding, false to get only the non-coding
"""
if out_file and file_exists(out_file):
return out_file
if not out_file:
out_file = tempfile.NamedTemporaryFile(delete=False,
suffix=".gtf").name
if coding:
pred = lambda biotype: biotype and biotype == "protein_coding"
else:
pred = lambda biotype: biotype and biotype != "protein_coding"
biotype_lookup = _biotype_lookup_fn(gtf)
db = get_gtf_db(gtf)
with file_transaction(out_file) as tx_out_file:
with open(tx_out_file, "w") as out_handle:
for feature in db.all_features():
biotype = biotype_lookup(feature)
if pred(biotype):
out_handle.write(str(feature) + "\n")
return out_file
def gtf_to_bed(gtf, alt_out_dir=None):
"""
create a BED file of transcript-level features with attached gene name
or gene ids
"""
out_file = os.path.splitext(gtf)[0] + '.bed'
if file_exists(out_file):
return out_file
if not os.access(os.path.dirname(out_file), os.W_OK | os.X_OK):
if not alt_out_dir:
raise IOError('Cannot write transcript BED output file %s' % out_file)
else:
out_file = os.path.join(alt_out_dir, os.path.basename(out_file))
with open(out_file, "w") as out_handle:
db = get_gtf_db(gtf)
for feature in db.features_of_type('transcript', order_by=("seqid", "start", "end")):
chrom = feature.chrom
start = feature.start
end = feature.end
attributes = feature.attributes.keys()
strand = feature.strand
name = (feature['gene_name'][0] if 'gene_name' in attributes else
feature['gene_id'][0])
line = "\t".join([str(x) for x in [chrom, start, end, name, ".",
strand]])
out_handle.write(line + "\n")
return out_file
def get_gtf_db(gtf, in_memory=False):
"""
create a gffutils DB
"""
db_file = gtf + '.db'
if gtf.endswith('.gz'):
db_file = gtf[:-3] + '.db'
if file_exists(db_file):
return gffutils.FeatureDB(db_file)
db_file = ':memory:' if in_memory else db_file
if in_memory or not file_exists(db_file):
debug('GTF database does not exist, creating...')
infer_extent = guess_infer_extent(gtf)
db = gffutils.create_db(gtf, dbfn=db_file,
infer_gene_extent=infer_extent)
return db
else:
return gffutils.FeatureDB(db_file)