def importCEL( infile, outfiles ):
'''import CEL files.'''
map_cel = IOTools.readMap( open(infile, "r"), has_header = True )
indir = PARAMS["datadir"]
for old, new in map_cel.iteritems():
oldname = os.path.join( indir, old + ".CEL" )
newname = os.path.join( ".", new + ".CEL" )
if not os.path.exists( oldname ):
raise IOError( "input file %s does not exist" % oldname )
if os.path.exists(newname): continue
os.symlink( os.path.abspath( oldname), os.path.abspath( newname ) )
def importCEL(infile, outfiles):
"""import CEL files."""
map_cel = IOTools.readMap(open(infile, "r"), has_header=True)
indir = PARAMS["datadir"]
for old, new in map_cel.iteritems():
oldname = os.path.join(indir, old + ".CEL")
newname = os.path.join(".", new + ".CEL")
if not os.path.exists(oldname):
raise IOError("input file %s does not exist" % oldname)
if os.path.exists(newname):
continue
os.symlink(os.path.abspath(oldname), os.path.abspath(newname))
def importFromSeries(infiles, outfile):
'''import expression levels from a GEO series.'''
tablename = P.toTable(outfile)
tmpf = P.getTempFile()
infile_data, infile_map = infiles
map_header = IOTools.readMap(open(infile_map, "r"))
if "ID_REF" not in map_header:
map_header["ID_REF"] = "probeset"
inf = gzip.open(infile_data, "r")
for line in inf:
if line.startswith("!"):
continue
if not line.strip():
continue
line = re.sub('"', "", line)
if line.startswith("ID_REF"):
line = "\t".join([map_header[x]
for x in line[:-1].split("\t")]) + "\n"
tmpf.write(line)
tmpf.close()
tmpname = tmpf.name
header = map_header["ID_REF"]
statement = '''
python %(scriptsdir)s/csv2db.py %(csv2db_options)s \
--index=%(header)s \
--table=%(tablename)s \
< %(tmpname)s > %(outfile)s
'''
P.run()
os.unlink(tmpname)
def importFromSeries(infiles, outfile):
'''import expression levels from a GEO series.'''
tablename = P.toTable(outfile)
tmpf = P.getTempFile()
infile_data, infile_map = infiles
map_header = IOTools.readMap(open(infile_map, "r"))
if "ID_REF" not in map_header:
map_header["ID_REF"] = "probeset"
inf = gzip.open(infile_data, "r")
for line in inf:
if line.startswith("!"):
continue
if not line.strip():
continue
line = re.sub('"', "", line)
if line.startswith("ID_REF"):
line = "\t".join([map_header[x]
for x in line[:-1].split("\t")]) + "\n"
tmpf.write(line)
tmpf.close()
tmpname = tmpf.name
header = map_header["ID_REF"]
statement = '''
python %(scriptsdir)s/csv2db.py %(csv2db_options)s \
--index=%(header)s \
--table=%(tablename)s \
< %(tmpname)s > %(outfile)s
'''
P.run()
os.unlink(tmpname)
def main(argv=None):
"""script main.
parses command line options in sys.argv, unless *argv* is given.
"""
if argv is None:
argv = sys.argv
parser = E.OptionParser(version="%prog version: $Id$")
parser.add_option("-p",
"--peptides-fasta-file",
dest="filename_peptides",
type="string",
help="filename with peptide sequences [%default].")
parser.add_option("-c",
"--cds-gtf-file",
"--cdnas",
dest="filename_cdna",
type="string",
help="filename with cdna sequences [%default].")
parser.add_option(
"-m",
"--map",
dest="filename_map",
type="string",
help=
"filename with map of peptide identifiers to cdna identifiers [%default]."
)
parser.add_option("--output-identifier",
dest="output_identifier",
type="choice",
choices=("cdna", "peptide"),
help="output identifier to use [%default].")
parser.add_option("-f",
"--output-format=",
dest="output_format",
type="choice",
choices=("alignment", "fasta"),
help="output format.")
parser.set_defaults(
peptides=None,
filename_cdna=None,
output_format="alignment",
filename_map=None,
stop_codons=("TAG", "TAA", "TGA"),
output_identifier="peptide",
)
(options, args) = E.Start(parser, add_pipe_options=True)
if not options.filename_cdna:
raise ValueError("please supply filename with cds sequences.")
if options.filename_peptides:
infile = open(options.filename_peptides, "r")
E.info("reading from %s" % options.filename_peptides)
else:
E.info("reading from stdin")
infile = sys.stdin
if options.filename_map:
E.info("reading map")
map_peptide2cds = IOTools.readMap(
IOTools.openFile(options.filename_map, "r"))
E.info("read map for %i identifiers" % len(map_peptide2cds))
else:
map_peptide2cds = {}
E.info("reading cds sequences")
cds_sequences = Genomics.ReadPeptideSequences(
IOTools.openFile(options.filename_cdna, "r"))
E.info("read %i cds sequences" % len(cds_sequences))
ninput, noutput = 0, 0
nskipped, nnosequence = 0, 0
# iterate over peptide sequences
iterator = FastaIterator.FastaIterator(infile)
use_cds_id = options.output_identifier == "cds"
for cur_record in iterator:
ninput += 1
peptide_identifier = re.split("\s+", cur_record.title)[0]
cds_identifier = map_peptide2cds.get(peptide_identifier,
peptide_identifier)
if cds_identifier not in cds_sequences:
nnosequence += 1
continue
p = cur_record.sequence
c = cds_sequences[cds_identifier]
E.debug("processing %s: laa=%i (without gaps=%i), lna=%i" %
(peptide_identifier, len(p), len(re.sub("-", "", p)), len(c)))
try:
map_p2c = Peptides2Cds.getMapPeptide2Cds(p, c, options)
except ValueError:
nskipped += 1
continue
if use_cds_id:
identifier = cds_identifier
else:
identifier = peptide_identifier
if options.output_format == "alignment":
options.stdout.write("\t".join(
map(str, (identifier,
alignlib_lite.py_AlignmentFormatEmissions(map_p2c),
len(cur_record.sequence),
len(cds_sequences[identifier])))) + "\n")
elif options.output_format == "fasta":
map_p2c.switchRowCol()
alignatum = alignlib_lite.py_makeAlignatum(c)
alignatum.mapOnAlignment(map_p2c, len(p) * 3)
s = alignatum.getString()
if len(s) != len(p) * 3:
raise ValueError(
"incomplete aligned string for %s: %s, cds=%s" %
(cur_record.title, s, c))
options.stdout.write(">%s\n%s\n" % (identifier, s))
noutput += 1
sys.stdout.flush()
E.info("ninput=%i, noutput=%i, nnosequence=%i, nskipped=%i" %
(ninput, noutput, nnosequence, nskipped))
E.Stop()
def test_cmdline():
'''test style of scripts
'''
# start script in order to build the command line parser
global ORIGINAL_START
if ORIGINAL_START is None:
ORIGINAL_START = E.Start
# read the first two columns
map_option2action = IOTools.readMap(IOTools.openFile(FILENAME_OPTIONLIST),
columns=(0, 1),
has_header=True)
files = []
for label, expression in EXPRESSIONS:
f = glob.glob(expression)
files.extend(sorted(f))
files = filter_files(files)
# make sure to use the current working directory as
# primary lookup.
sys.path.insert(0, ".")
# files = [
# 'scripts/check_db.py',
# 'scripts/cgat_build_report_page.py']
for f in files:
if os.path.isdir(f):
continue
if os.path.basename(f) in EXCLUDE:
continue
script_name = os.path.abspath(f)
pyxfile = (os.path.join(os.path.dirname(f), "_") +
os.path.basename(f) + "x")
fail_.description = script_name
# check if script contains getopt
with IOTools.openFile(script_name) as inf:
if "getopt" in inf.read():
yield (fail_, "script uses getopt directly: %s" % script_name)
continue
module, modulename = load_script(script_name)
if module is None:
yield (fail_, "module could not be imported: %s\n" % script_name)
continue
E.Start = LocalStart
try:
module.main(argv=["--help"])
except AttributeError:
yield (fail_, "no main method in %s\n" % script_name)
ok_(False, "no main method in %s" % script_name)
except SystemExit:
yield (fail_, "script does not use E.Start() %s\n" % script_name)
except DummyError:
pass
for option in PARSER.option_list:
# ignore options added by optparse
if option.dest is None:
continue
optstring = option.get_opt_string()
if optstring.startswith("--"):
optstring = optstring[2:]
check_option.description = script_name + ":" + optstring
yield (check_option, optstring, os.path.abspath(f),
map_option2action)
# clear up
del sys.modules[modulename]
# scripts with pyximport need special handling.
#
# Multiple imports of pyximport seems to create
# some confusion - here, clear up sys.meta_path after
# each script
if os.path.exists(pyxfile):
sys.meta_path = []
def main():
parser = E.OptionParser( version = "%prog version: $Id: GO.py 2883 2010-04-07 08:46:22Z andreas $", usage = globals()["__doc__"])
dbhandle = Database.Database()
parser.add_option("-s", "--species", dest="species", type="string",
help="species to use [default=%default]." )
parser.add_option("-i", "--slims", dest="filename_slims", type="string",
help="filename with GO SLIM categories [default=%default].")
parser.add_option( "-g", "--genes", dest="filename_genes", type="string",
help="filename with genes to analyse [default=%default]." )
parser.add_option( "-b", "--background", dest="filename_background", type="string",
help="filename with background genes to analyse [default=%default]." )
parser.add_option( "-m", "--minimum-counts", dest="minimum_counts", type="int",
help="minimum count - ignore all categories that have fewer than # number of genes"
" [default=%default]." )
parser.add_option( "-o", "--sort-order", dest="sort_order", type="choice",
choices=("fdr", "pvalue", "ratio" ),
help="output sort order [default=%default]." )
parser.add_option( "--ontology", dest="ontology", type="string", action="append",
help="go ontologies to analyze. Ontologies are tested separately."
" [default=%default]." )
parser.add_option( "-t", "--threshold", dest="threshold", type="float",
help="significance threshold [>1.0 = all ]. If --fdr is set, this refers to the fdr, otherwise it is a cutoff for p-values." )
parser.add_option ("--filename-dump", dest="filename_dump", type="string",
help="dump GO category assignments into a flatfile [default=%default]." )
parser.add_option ("--filename-gene2name", dest="filename_gene2name", type="string",
help="optional filename mapping gene identifiers to gene names [default=%default]." )
parser.add_option ("--filename-ontology", dest="filename_ontology", type="string",
help="filename with ontology in OBO format [default=%default]." )
parser.add_option ( "--filename-input", dest="filename_input", type="string",
help="read GO category assignments from a flatfile [default=%default]." )
parser.add_option ( "--sample-size", dest="sample", type="int",
help="do sampling (with # samples) [default=%default]." )
parser.add_option ( "--filename-output-pattern", "--output-filename-pattern",
dest = "output_filename_pattern", type="string",
help="pattern with output filename pattern (should contain: %(go)s and %(section)s ) [default=%default]")
parser.add_option ( "--fdr", dest="fdr", action="store_true",
help="calculate and filter by FDR [ReadGene2GOFromFiledefault=%default]." )
parser.add_option ( "--go2goslim", dest="go2goslim", action="store_true",
help="convert go assignments in STDIN to goslim assignments and write to STDOUT [default=%default]." )
parser.add_option ( "--gene-pattern", dest = "gene_pattern", type="string",
help="pattern to transform identifiers to GO gene names [default=%default].")
parser.add_option( "--filename-map-slims", dest="filename_map_slims", type="string",
help="write mapping between GO categories and GOSlims [default=%default].")
parser.add_option( "--get-genes", dest="get_genes", type="string",
help="list all genes in the with a certain GOID [default=%default]." )
parser.add_option( "--strict", dest="strict", action="store_true",
help="require all genes in foreground to be part of background. "
"If not set, genes in foreground will be added to the background [default=%default]." )
parser.add_option("-q", "--qvalue-method", dest="qvalue_method", type="choice",
choices = ( "empirical", "storey", "BH" ),
help="method to perform multiple testing correction by controlling the fdr [default=%default]." )
parser.add_option( "--pairwise", dest="compute_pairwise", action="store_true",
help="compute pairwise enrichment for multiple gene lists. "
"[default=%default]." )
# parser.add_option( "--qvalue-lambda", dest="qvalue_lambda", type="float",
# help="fdr computation: lambda [default=%default]." )
# parser.add_option( "--qvalue-pi0-method", dest="qvalue_pi0_method", type="choice",
# choices = ("smoother", "bootstrap" ),
# help="fdr computation: method for estimating pi0 [default=%default]." )
parser.set_defaults( species = None,
filename_genes = "-",
filename_background = None,
filename_slims = None,
minimum_counts = 0,
ontology = [],
filename_dump = None,
sample = 0,
fdr = False,
output_filename_pattern = None,
threshold = 0.05,
filename_map_slims = None,
gene_pattern = None,
sort_order = "ratio",
get_genes = None,
strict = False,
qvalue_method = "empirical",
pairs_min_observed_counts = 3,
compute_pairwise = False,
filename_gene2name = None
)
(options, args) = E.Start( parser, add_mysql_options = True )
if options.go2goslim:
convertGo2Goslim( options )
E.Stop()
sys.exit(0)
if options.fdr and options.sample == 0:
E.warn( "fdr will be computed without sampling" )
#############################################################
## dump GO
if options.filename_dump:
# set default orthologies to GO
if not options.ontology:
options.ontology = ["biol_process", "mol_function", "cell_location"]
E.info( "dumping GO categories to %s" % (options.filename_dump) )
dbhandle.Connect( options )
outfile = IOTools.openFile( options.filename_dump, "w", create_dir = True )
DumpGOFromDatabase( outfile,
dbhandle,
options )
outfile.close()
E.Stop()
sys.exit(0)
#############################################################
## read GO categories from file
if options.filename_input:
E.info( "reading association of categories and genes from %s" % (options.filename_input) )
infile = IOTools.openFile(options.filename_input)
gene2gos, go2infos = ReadGene2GOFromFile( infile )
infile.close()
if options.filename_gene2name:
E.info("reading gene identifier to gene name mapping from %s" % options.filename_gene2name)
infile = IOTools.openFile( options.filename_gene2name)
gene2name = IOTools.readMap( infile, has_header = True )
infile.close()
E.info("read %i gene names for %i gene identifiers" % (len(set(gene2name.values())),
len(gene2name)))
else:
gene2name = None
#############################################################
## read GO ontology from file
if options.filename_ontology:
E.info( "reading ontology from %s" % (options.filename_ontology) )
infile = IOTools.openFile(options.filename_ontology)
ontology = readOntology( infile )
infile.close()
def _g():
return collections.defaultdict( GOInfo )
go2infos = collections.defaultdict( _g );
## substitute go2infos
for go in ontology.values():
go2infos[go.mNameSpace][go.mId] = GOInfo( go.mId,
go_type = go.mNameSpace,
description = go.mName )
#############################################################
## get foreground gene list
input_foreground, genelists = ReadGeneLists( options.filename_genes,
gene_pattern = options.gene_pattern )
E.info( "read %i genes for forground in %i gene lists" % (len(input_foreground), len(genelists)) )
#############################################################
## get background
if options.filename_background:
# nick - bug fix: background is the first tuple element from ReadGeneLists
input_background = ReadGeneLists( options.filename_background,
gene_pattern = options.gene_pattern )[0]
E.info( "read %i genes for background" % len(input_background) )
else:
input_background = None
#############################################################
## sort out which ontologies to test
if not options.ontology:
if options.filename_input:
options.ontology = gene2gos.keys()
E.info( "found %i ontologies: %s" % (len(options.ontology), options.ontology))
summary = []
summary.append( "\t".join( (
"genelist",
"ontology",
"significant",
"threshold",
"ngenes",
"ncategories",
"nmaps",
"nforegound",
"nforeground_mapped",
"nbackground",
"nbackground_mapped",
"nsample_counts",
"nbackground_counts",
"psample_assignments",
"pbackground_assignments") ) + "\n" )
#############################################################
## get go categories for genes
for test_ontology in options.ontology:
# store results for aggregate output of multiple gene lists
all_results = []
all_significant_results = []
all_genelists_with_results = []
E.info( "working on ontology %s" % test_ontology )
#############################################################
## get/read association of GO categories to genes
if options.filename_input:
gene2go, go2info = gene2gos[test_ontology], go2infos[test_ontology]
else:
E.info( "reading data from database ..." )
dbhandle.Connect( options )
gene2go, go2info = ReadGene2GOFromDatabase( dbhandle,
test_ontology,
options.database, options.species )
E.info( "finished" )
if len(go2info) == 0:
E.warn( "could not find information for terms - could be mismatch between ontologies")
ngenes, ncategories, nmaps, counts_per_category = CountGO( gene2go )
E.info( "assignments found: %i genes mapped to %i categories (%i maps)" % (ngenes, ncategories, nmaps) )
if options.minimum_counts > 0:
to_remove = set([ x for x,y in counts_per_category.iteritems() if y < options.minimum_counts ])
E.info("removing %i categories with less than %i genes" % (len(to_remove), options.minimum_counts ) )
removeCategories( gene2go, to_remove )
ngenes, ncategories, nmaps, counts_per_category = CountGO( gene2go )
E.info( "assignments after filtering: %i genes mapped to %i categories (%i maps)" % (ngenes, ncategories, nmaps) )
for genelist_name, foreground in genelists.iteritems():
msgs = []
E.info("processing %s with %i genes" % (genelist_name, len(foreground)))
##################################################################
##################################################################
##################################################################
## build background - reconcile with foreground
##################################################################
if input_background == None:
background = list(gene2go.keys())
else:
background = list(input_background)
# nick - bug-fix backgorund included the foreground in a tuple.
# background is the first tuple element
missing = foreground.difference(set(background))
if options.strict:
assert len(missing) == 0, \
"%i genes in foreground but not in background: %s" % (len(missing), str(missing))
else:
if len(missing) != 0:
E.warn( "%i genes in foreground that are not in background - added to background of %i" %\
(len(missing), len(background)) )
background.extend(missing)
E.info( "(unfiltered) foreground=%i, background=%i" % (len(foreground), len(background)))
#############################################################
## sanity checks:
## are all of the foreground genes in the dataset
## missing = set(genes).difference( set(gene2go.keys()) )
## assert len(missing) == 0, "%i genes in foreground set without GO annotation: %s" % (len(missing), str(missing))
#############################################################
## read GO slims and map GO categories to GO slim categories
if options.filename_slims:
go_slims = GetGOSlims( IOTools.openFile(options.filename_slims, "r") )
if options.loglevel >=1:
v = set()
for x in go_slims.values():
for xx in x: v.add(xx)
options.stdlog.write( "# read go slims from %s: go=%i, slim=%i\n" %\
( options.filename_slims,
len(go_slims),
len( v ) ))
if options.filename_map_slims:
if options.filename_map_slims == "-":
outfile = options.stdout
else:
outfile=IOTools.openFile(options.filename_map_slims, "w" )
outfile.write( "GO\tGOSlim\n" )
for go, go_slim in go_slims.items():
outfile.write("%s\t%s\n" % (go, go_slim))
if outfile != options.stdout:
outfile.close()
gene2go = MapGO2Slims( gene2go, go_slims, ontology = ontology )
if options.loglevel >=1:
ngenes, ncategories, nmaps, counts_per_category = CountGO( gene2go )
options.stdlog.write( "# after go slim filtering: %i genes mapped to %i categories (%i maps)\n" % (ngenes, ncategories, nmaps) )
#############################################################
## Just dump out the gene list
if options.get_genes:
fg, bg, ng = [], [], []
for gene, vv in gene2go.items():
for v in vv:
if v.mGOId == options.get_genes:
if gene in genes:
fg.append( gene )
elif gene in background:
bg.append( gene )
else:
ng.append( gene )
## skip to next GO class
if not (bg or ng): continue
options.stdout.write( "# genes in GO category %s\n" % options.get_genes )
options.stdout.write( "gene\tset\n" )
for x in fg: options.stdout.write("%s\t%s\n" % ("fg", x))
for x in bg: options.stdout.write("%s\t%s\n" % ("bg", x))
for x in ng: options.stdout.write("%s\t%s\n" % ("ng", x))
E.info( "nfg=%i, nbg=%i, nng=%i" % (len(fg), len(bg), len(ng) ))
E.Stop()
sys.exit(0)
#############################################################
outfile = getFileName( options,
go = test_ontology,
section = 'foreground',
set = genelist_name )
outfile.write ("gene_id\n%s\n" % ("\n".join( sorted( foreground) ) ) )
if options.output_filename_pattern:
outfile.close()
outfile = getFileName( options,
go = test_ontology,
section = 'background',
set = genelist_name )
outfile.write ("gene_id\n%s\n" % ("\n".join( sorted( background[0]) ) ) )
if options.output_filename_pattern:
outfile.close()
#############################################################
## do the analysis
go_results = AnalyseGO( gene2go, foreground, background )
if len(go_results.mSampleGenes) == 0:
E.warn( "%s: no genes with GO categories - analysis aborted" % genelist_name)
continue
pairs = go_results.mResults.items()
#############################################################
## calculate fdr for each hypothesis
if options.fdr:
fdrs, samples, method = computeFDRs( go_results,
foreground,
background,
options,
test_ontology,
gene2go,
go2info)
for x,v in enumerate(pairs):
v[1].mQValue = fdrs[v[0]][0]
else:
fdrs, samples, method = {}, {}, None
msgs.append( "fdr=%s" % method)
if options.sort_order == "fdr":
pairs.sort( lambda x, y: cmp(x[1].mQValue, y[1].mQValue))
elif options.sort_order == "ratio":
pairs.sort( lambda x, y: cmp(x[1].mRatio, y[1].mRatio))
elif options.sort_order == "pvalue":
pairs.sort( lambda x, y: cmp(x[1].mPValue, y[1].mPValue))
#############################################################
#############################################################
#############################################################
## output the full result
outfile = getFileName( options,
go = test_ontology,
section = 'overall',
set = genelist_name )
outputResults( outfile, pairs, go2info, options, fdrs = fdrs, samples = samples )
if options.output_filename_pattern:
outfile.close()
#############################################################
#############################################################
#############################################################
# filter significant results and output
filtered_pairs = selectSignificantResults( pairs, fdrs, options )
nselected = len(filtered_pairs)
nselected_up = len( [x for x in filtered_pairs if x[1].mRatio > 1 ] )
nselected_down = len( [x for x in filtered_pairs if x[1].mRatio < 1 ] )
assert nselected_up + nselected_down == nselected
outfile = getFileName( options,
go = test_ontology,
section = 'results',
set = genelist_name )
outputResults( outfile,
filtered_pairs,
go2info,
options,
fdrs = fdrs,
samples = samples )
if options.output_filename_pattern:
outfile.close()
#############################################################
#############################################################
#############################################################
# save results for multi-gene-list analysis
all_results.append( pairs )
all_significant_results.append( filtered_pairs )
all_genelists_with_results.append( genelist_name )
#############################################################
#############################################################
#############################################################
## output parameters
ngenes, ncategories, nmaps, counts_per_category = CountGO( gene2go )
outfile = getFileName( options,
go = test_ontology,
section = 'parameters',
set = genelist_name )
nbackground = len(background)
if nbackground == 0:
nbackground = len(go_results.mBackgroundGenes)
outfile.write( "# input go mappings for gene list '%s' and category '%s'\n" % (genelist_name, test_ontology ))
outfile.write( "parameter\tvalue\tdescription\n" )
outfile.write( "mapped_genes\t%i\tmapped genes\n" % ngenes )
outfile.write( "mapped_categories\t%i\tmapped categories\n" % ncategories )
outfile.write( "mappings\t%i\tmappings\n" % nmaps )
outfile.write( "genes_in_fg\t%i\tgenes in foreground\n" % len(foreground) )
outfile.write( "genes_in_fg_with_assignment\t%i\tgenes in foreground with GO assignments\n" % (len(go_results.mSampleGenes)) )
outfile.write( "genes_in_bg\t%i\tinput background\n" % nbackground )
outfile.write( "genes_in_bg_with_assignment\t%i\tgenes in background with GO assignments\n" % (len(go_results.mBackgroundGenes)) )
outfile.write( "associations_in_fg\t%i\tassociations in sample\n" % go_results.mSampleCountsTotal )
outfile.write( "associations_in_bg\t%i\tassociations in background\n" % go_results.mBackgroundCountsTotal )
outfile.write( "percent_genes_in_fg_with_association\t%s\tpercent genes in sample with GO assignments\n" % (IOTools.prettyPercent( len(go_results.mSampleGenes) , len(foreground), "%5.2f" )))
outfile.write( "percent_genes_in_bg_with_associations\t%s\tpercent genes background with GO assignments\n" % (IOTools.prettyPercent( len(go_results.mBackgroundGenes), nbackground, "%5.2f" )))
outfile.write( "significant\t%i\tsignificant results reported\n" % nselected )
outfile.write( "significant_up\t%i\tsignificant up-regulated results reported\n" % nselected_up )
outfile.write( "significant_down\t%i\tsignificant up-regulated results reported\n" % nselected_down )
outfile.write( "threshold\t%6.4f\tsignificance threshold\n" % options.threshold )
if options.output_filename_pattern:
outfile.close()
summary.append( "\t".join( map(str, ( \
genelist_name,
test_ontology,
nselected,
options.threshold,
ngenes,
ncategories,
nmaps,
len(foreground),
len(go_results.mSampleGenes),
nbackground,
len(go_results.mBackgroundGenes),
go_results.mSampleCountsTotal,
go_results.mBackgroundCountsTotal,
IOTools.prettyPercent( len(go_results.mSampleGenes) , len(foreground), "%5.2f" ),
IOTools.prettyPercent( len(go_results.mBackgroundGenes), nbackground, "%5.2f" ),
",".join( msgs) ) ) ) + "\n" )
#############################################################
#############################################################
#############################################################
## output the fg patterns
outfile = getFileName( options,
go = test_ontology,
section = 'withgenes',
set = genelist_name )
outputResults( outfile, pairs, go2info, options,
fdrs = fdrs,
samples = samples,
gene2go = gene2go,
foreground = foreground,
gene2name = gene2name )
if options.output_filename_pattern:
outfile.close()
if len(genelists) > 1:
######################################################################
######################################################################
######################################################################
## output various summary files
## significant results
outputMultipleGeneListResults( all_significant_results,
all_genelists_with_results,
test_ontology,
go2info,
options,
section = 'significant')
## all results
outputMultipleGeneListResults( all_results,
all_genelists_with_results,
test_ontology,
go2info,
options,
section = 'all')
if options.compute_pairwise:
pairwiseGOEnrichment( all_results,
all_genelists_with_results,
test_ontology,
go2info,
options )
outfile_summary = options.stdout
outfile_summary.write( "".join( summary) )
E.Stop()
def main(argv=None):
parser = E.OptionParser(version="%prog version: $Id$",
usage=globals()["__doc__"])
parser.add_option("-s",
"--species",
dest="species",
type="string",
help="species to use [default=%default].")
parser.add_option("-i",
"--slims",
dest="filename_slims",
type="string",
help="filename with GO SLIM categories "
"[default=%default].")
parser.add_option("-g",
"--genes-tsv-file",
dest="filename_genes",
type="string",
help="filename with genes to analyse "
"[default=%default].")
parser.add_option("-b",
"--background-tsv-file",
dest="filename_background",
type="string",
help="filename with background genes to analyse "
"[default=%default].")
parser.add_option("-m",
"--min-counts",
dest="minimum_counts",
type="int",
help="minimum count - ignore all categories that have "
"fewer than # number of genes"
" [default=%default].")
parser.add_option("-o",
"--sort-order",
dest="sort_order",
type="choice",
choices=("fdr", "pvalue", "ratio"),
help="output sort order [default=%default].")
parser.add_option("--ontology",
dest="ontology",
type="string",
action="append",
help="go ontologies to analyze. Ontologies are tested "
"separately [default=%default].")
parser.add_option(
"-t",
"--threshold",
dest="threshold",
type="float",
help="significance threshold [>1.0 = all ]. If --fdr is set, this "
"refers to the fdr, otherwise it is a cutoff for p-values.")
parser.add_option("--filename-dump",
dest="filename_dump",
type="string",
help="dump GO category assignments into a flatfile "
"[default=%default].")
parser.add_option(
"--gene2name-map-tsv-file",
dest="filename_gene2name",
type="string",
help="optional filename mapping gene identifiers to gene names "
"[default=%default].")
parser.add_option(
"--filename-ontology",
dest="filename_ontology",
type="string",
help="filename with ontology in OBO format [default=%default].")
parser.add_option("--filename-input",
dest="filename_input",
type="string",
help="read GO category assignments from a flatfile "
"[default=%default].")
parser.add_option("--sample-size",
dest="sample",
type="int",
help="do sampling (with # samples) [default=%default].")
parser.add_option(
"--filename-output-pattern",
"--output-filename-pattern",
dest="output_filename_pattern",
type="string",
help="pattern with output filename pattern "
"(should contain: %(go)s and %(section)s ) [default=%default]")
parser.add_option("--fdr",
dest="fdr",
action="store_true",
help="calculate and filter by FDR default=%default].")
parser.add_option(
"--go2goslim",
dest="go2goslim",
action="store_true",
help="convert go assignments in STDIN to goslim assignments and "
"write to STDOUT [default=%default].")
parser.add_option("--gene-pattern",
dest="gene_pattern",
type="string",
help="pattern to transform identifiers to GO gene names "
"[default=%default].")
parser.add_option("--filename-map-slims",
dest="filename_map_slims",
type="string",
help="write mapping between GO categories and GOSlims "
"[default=%default].")
parser.add_option(
"--get-genes",
dest="get_genes",
type="string",
help="list all genes in the with a certain GOID [default=%default].")
parser.add_option(
"--strict",
dest="strict",
action="store_true",
help="require all genes in foreground to be part of background. "
"If not set, genes in foreground will be added to the background "
"[default=%default].")
parser.add_option(
"-q",
"--fdr-method",
dest="qvalue_method",
type="choice",
choices=("empirical", "storey", "BH"),
help="method to perform multiple testing correction by controlling "
"the fdr [default=%default].")
parser.add_option(
"--pairwise",
dest="compute_pairwise",
action="store_true",
help="compute pairwise enrichment for multiple gene lists. "
"[default=%default].")
# parser.add_option( "--fdr-lambda", dest="qvalue_lambda", type="float",
# help="fdr computation: lambda [default=%default]." )
# parser.add_option( "--qvalue-pi0-method", dest="qvalue_pi0_method", type="choice",
# choices = ("smoother", "bootstrap" ),
# help="fdr computation: method for estimating pi0 [default=%default]." )
parser.set_defaults(species=None,
filename_genes="-",
filename_background=None,
filename_slims=None,
minimum_counts=0,
ontology=[],
filename_dump=None,
sample=0,
fdr=False,
output_filename_pattern=None,
threshold=0.05,
filename_map_slims=None,
gene_pattern=None,
sort_order="ratio",
get_genes=None,
strict=False,
qvalue_method="empirical",
pairs_min_observed_counts=3,
compute_pairwise=False,
filename_gene2name=None)
(options, args) = E.Start(parser, add_database_options=True)
if options.go2goslim:
GO.convertGo2Goslim(options)
E.Stop()
sys.exit(0)
if options.fdr and options.sample == 0:
E.warn("fdr will be computed without sampling")
#############################################################
# dump GO
if options.filename_dump:
# set default orthologies to GO
if not options.ontology:
options.ontology = [
"biol_process", "mol_function", "cell_location"
]
E.info("dumping GO categories to %s" % (options.filename_dump))
dbhandle = connectToEnsembl(options)
outfile = IOTools.openFile(options.filename_dump, "w", create_dir=True)
GO.DumpGOFromDatabase(outfile, dbhandle, options)
outfile.close()
E.Stop()
sys.exit(0)
#############################################################
# read GO categories from file
if options.filename_input:
E.info("reading association of categories and genes from %s" %
(options.filename_input))
infile = IOTools.openFile(options.filename_input)
gene2gos, go2infos = GO.ReadGene2GOFromFile(infile)
infile.close()
if options.filename_gene2name:
E.info("reading gene identifier to gene name mapping from %s" %
options.filename_gene2name)
infile = IOTools.openFile(options.filename_gene2name)
gene2name = IOTools.readMap(infile, has_header=True)
infile.close()
E.info("read %i gene names for %i gene identifiers" %
(len(set(gene2name.values())), len(gene2name)))
else:
# use identity mapping
gene2name = dict([(x, x) for x in list(gene2gos.keys())])
#############################################################
# read GO ontology from file
if options.filename_ontology:
E.info("reading ontology from %s" % (options.filename_ontology))
infile = IOTools.openFile(options.filename_ontology)
ontology = GO.readOntology(infile)
infile.close()
def _g():
return collections.defaultdict(GO.GOInfo)
go2infos = collections.defaultdict(_g)
# substitute go2infos
for go in list(ontology.values()):
go2infos[go.mNameSpace][go.mId] = GO.GOInfo(go.mId,
go_type=go.mNameSpace,
description=go.mName)
#############################################################
# get foreground gene list
input_foreground, genelists = GO.ReadGeneLists(
options.filename_genes, gene_pattern=options.gene_pattern)
E.info("read %i genes for forground in %i gene lists" %
(len(input_foreground), len(genelists)))
#############################################################
# get background
if options.filename_background:
# nick - bug fix: background is the first tuple element from
# ReadGeneLists
input_background = GO.ReadGeneLists(
options.filename_background, gene_pattern=options.gene_pattern)[0]
E.info("read %i genes for background" % len(input_background))
else:
input_background = None
#############################################################
# sort out which ontologies to test
if not options.ontology:
if options.filename_input:
options.ontology = list(gene2gos.keys())
E.info("found %i ontologies: %s" %
(len(options.ontology), options.ontology))
summary = []
summary.append("\t".join(
("genelist", "ontology", "significant", "threshold", "ngenes",
"ncategories", "nmaps", "nforegound", "nforeground_mapped",
"nbackground", "nbackground_mapped", "nsample_counts",
"nbackground_counts", "psample_assignments",
"pbackground_assignments", "messages")) + "\n")
#############################################################
# get go categories for genes
for test_ontology in sorted(options.ontology):
# store results for aggregate output of multiple gene lists
all_results = []
all_significant_results = []
all_genelists_with_results = []
E.info("working on ontology %s" % test_ontology)
#############################################################
# get/read association of GO categories to genes
if options.filename_input:
gene2go, go2info = gene2gos[test_ontology], go2infos[test_ontology]
else:
E.info("reading data from database ...")
dbhandle.Connect(options)
gene2go, go2info = GO.ReadGene2GOFromDatabase(
dbhandle, test_ontology, options.database, options.species)
E.info("finished")
if len(go2info) == 0:
E.warn("could not find information for terms - "
"could be mismatch between ontologies")
ngenes, ncategories, nmaps, counts_per_category = GO.CountGO(gene2go)
E.info("assignments found: %i genes mapped to %i categories "
"(%i maps)" % (ngenes, ncategories, nmaps))
if options.minimum_counts > 0:
to_remove = set([
x for x, y in counts_per_category.items()
if y < options.minimum_counts
])
E.info("removing %i categories with less than %i genes" %
(len(to_remove), options.minimum_counts))
GO.removeCategories(gene2go, to_remove)
ngenes, ncategories, nmaps, counts_per_category = \
GO.CountGO(gene2go)
E.info("assignments after filtering: %i genes mapped "
"to %i categories (%i maps)" % (ngenes, ncategories, nmaps))
for genelist_name, foreground in sorted(genelists.items()):
msgs = []
E.info("processing %s with %i genes" %
(genelist_name, len(foreground)))
##################################################################
##################################################################
##################################################################
# build background - reconcile with foreground
##################################################################
if input_background is None:
background = list(gene2go.keys())
else:
background = list(input_background)
# nick - bug-fix backgorund included the foreground in a tuple.
# background is the first tuple element
missing = foreground.difference(set(background))
if options.strict:
assert len(missing) == 0, \
"%i genes in foreground but not in background: %s" % (
len(missing), str(missing))
else:
if len(missing) != 0:
E.warn("%i genes in foreground that are not in "
"background - added to background of %i" %
(len(missing), len(background)))
background.extend(missing)
E.info("(unfiltered) foreground=%i, background=%i" %
(len(foreground), len(background)))
# sort foreground and background, important for reproducibility
# under random seed
foreground = sorted(foreground)
background = sorted(background)
#############################################################
# sanity checks:
# are all of the foreground genes in the dataset
# missing = set(genes).difference( set(gene2go.keys()) )
# assert len(missing) == 0, "%i genes in foreground set without GO annotation: %s" % (len(missing), str(missing))
#############################################################
# read GO slims and map GO categories to GO slim categories
if options.filename_slims:
go_slims = GO.GetGOSlims(
IOTools.openFile(options.filename_slims, "r"))
if options.loglevel >= 1:
v = set()
for x in list(go_slims.values()):
for xx in x:
v.add(xx)
options.stdlog.write(
"# read go slims from %s: go=%i, slim=%i\n" %
(options.filename_slims, len(go_slims), len(v)))
if options.filename_map_slims:
if options.filename_map_slims == "-":
outfile = options.stdout
else:
outfile = IOTools.openFile(options.filename_map_slims,
"w")
outfile.write("GO\tGOSlim\n")
for go, go_slim in sorted(list(go_slims.items())):
outfile.write("%s\t%s\n" % (go, go_slim))
if outfile != options.stdout:
outfile.close()
gene2go = GO.MapGO2Slims(gene2go, go_slims, ontology=ontology)
if options.loglevel >= 1:
ngenes, ncategories, nmaps, counts_per_category = \
GO.CountGO(gene2go)
options.stdlog.write(
"# after go slim filtering: %i genes mapped to "
"%i categories (%i maps)\n" %
(ngenes, ncategories, nmaps))
#############################################################
# Just dump out the gene list
if options.get_genes:
fg, bg, ng = [], [], []
for gene, vv in list(gene2go.items()):
for v in vv:
if v.mGOId == options.get_genes:
if gene in genes:
fg.append(gene)
elif gene in background:
bg.append(gene)
else:
ng.append(gene)
# skip to next GO class
if not (bg or ng):
continue
options.stdout.write("# genes in GO category %s\n" %
options.get_genes)
options.stdout.write("gene\tset\n")
for x in sorted(fg):
options.stdout.write("%s\t%s\n" % ("fg", x))
for x in sorted(bg):
options.stdout.write("%s\t%s\n" % ("bg", x))
for x in sorted(ng):
options.stdout.write("%s\t%s\n" % ("ng", x))
E.info("nfg=%i, nbg=%i, nng=%i" % (len(fg), len(bg), len(ng)))
E.Stop()
sys.exit(0)
#############################################################
outfile = GO.getFileName(options,
go=test_ontology,
section='foreground',
set=genelist_name)
outfile.write("gene_id\n%s\n" % ("\n".join(sorted(foreground))))
if options.output_filename_pattern:
outfile.close()
outfile = GO.getFileName(options,
go=test_ontology,
section='background',
set=genelist_name)
# Jethro bug fix - see section 'build background' for assignment
outfile.write("gene_id\n%s\n" % ("\n".join(sorted(background))))
if options.output_filename_pattern:
outfile.close()
#############################################################
# do the analysis
go_results = GO.AnalyseGO(gene2go, foreground, background)
if len(go_results.mSampleGenes) == 0:
E.warn("%s: no genes with GO categories - analysis aborted" %
genelist_name)
continue
pairs = list(go_results.mResults.items())
#############################################################
# calculate fdr for each hypothesis
if options.fdr:
fdrs, samples, method = GO.computeFDRs(go_results, foreground,
background, options,
test_ontology, gene2go,
go2info)
for x, v in enumerate(pairs):
v[1].mQValue = fdrs[v[0]][0]
else:
fdrs, samples, method = {}, {}, None
msgs.append("fdr=%s" % method)
if options.sort_order == "fdr":
pairs.sort(key=lambda x: x[1].mQValue)
elif options.sort_order == "ratio":
pairs.sort(key=lambda x: x[1].mRatio)
elif options.sort_order == "pvalue":
pairs.sort(key=lambda x: x[1].mPValue)
#############################################################
#############################################################
#############################################################
# output the full result
outfile = GO.getFileName(options,
go=test_ontology,
section='overall',
set=genelist_name)
GO.outputResults(outfile,
pairs,
go2info,
options,
fdrs=fdrs,
samples=samples)
if options.output_filename_pattern:
outfile.close()
#############################################################
#############################################################
#############################################################
# filter significant results and output
filtered_pairs = GO.selectSignificantResults(pairs, fdrs, options)
nselected = len(filtered_pairs)
nselected_up = len([x for x in filtered_pairs if x[1].mRatio > 1])
nselected_down = len(
[x for x in filtered_pairs if x[1].mRatio < 1])
assert nselected_up + nselected_down == nselected
outfile = GO.getFileName(options,
go=test_ontology,
section='results',
set=genelist_name)
GO.outputResults(outfile,
filtered_pairs,
go2info,
options,
fdrs=fdrs,
samples=samples)
if options.output_filename_pattern:
outfile.close()
#############################################################
#############################################################
#############################################################
# save results for multi-gene-list analysis
all_results.append(pairs)
all_significant_results.append(filtered_pairs)
all_genelists_with_results.append(genelist_name)
#############################################################
#############################################################
#############################################################
# output parameters
ngenes, ncategories, nmaps, counts_per_category = \
GO.CountGO(gene2go)
outfile = GO.getFileName(options,
go=test_ontology,
section='parameters',
set=genelist_name)
nbackground = len(background)
if nbackground == 0:
nbackground = len(go_results.mBackgroundGenes)
outfile.write(
"# input go mappings for gene list '%s' and category '%s'\n" %
(genelist_name, test_ontology))
outfile.write("parameter\tvalue\tdescription\n")
outfile.write("mapped_genes\t%i\tmapped genes\n" % ngenes)
outfile.write("mapped_categories\t%i\tmapped categories\n" %
ncategories)
outfile.write("mappings\t%i\tmappings\n" % nmaps)
outfile.write("genes_in_fg\t%i\tgenes in foreground\n" %
len(foreground))
outfile.write(
"genes_in_fg_with_assignment\t%i\tgenes in foreground with GO assignments\n"
% (len(go_results.mSampleGenes)))
outfile.write("genes_in_bg\t%i\tinput background\n" % nbackground)
outfile.write(
"genes_in_bg_with_assignment\t%i\tgenes in background with GO assignments\n"
% (len(go_results.mBackgroundGenes)))
outfile.write("associations_in_fg\t%i\tassociations in sample\n" %
go_results.mSampleCountsTotal)
outfile.write(
"associations_in_bg\t%i\tassociations in background\n" %
go_results.mBackgroundCountsTotal)
outfile.write(
"percent_genes_in_fg_with_association\t%s\tpercent genes in sample with GO assignments\n"
% (IOTools.prettyPercent(len(go_results.mSampleGenes),
len(foreground), "%5.2f")))
outfile.write(
"percent_genes_in_bg_with_associations\t%s\tpercent genes background with GO assignments\n"
% (IOTools.prettyPercent(len(go_results.mBackgroundGenes),
nbackground, "%5.2f")))
outfile.write("significant\t%i\tsignificant results reported\n" %
nselected)
outfile.write(
"significant_up\t%i\tsignificant up-regulated results reported\n"
% nselected_up)
outfile.write(
"significant_down\t%i\tsignificant up-regulated results reported\n"
% nselected_down)
outfile.write("threshold\t%6.4f\tsignificance threshold\n" %
options.threshold)
if options.output_filename_pattern:
outfile.close()
summary.append("\t".join(
map(str, (genelist_name, test_ontology, nselected,
options.threshold, ngenes, ncategories, nmaps,
len(foreground), len(go_results.mSampleGenes),
nbackground, len(go_results.mBackgroundGenes),
go_results.mSampleCountsTotal,
go_results.mBackgroundCountsTotal,
IOTools.prettyPercent(len(go_results.mSampleGenes),
len(foreground), "%5.2f"),
IOTools.prettyPercent(
len(go_results.mBackgroundGenes), nbackground,
"%5.2f"), ",".join(msgs)))) + "\n")
#############################################################
#############################################################
#############################################################
# output the fg patterns
outfile = GO.getFileName(options,
go=test_ontology,
section='withgenes',
set=genelist_name)
GO.outputResults(outfile,
pairs,
go2info,
options,
fdrs=fdrs,
samples=samples,
gene2go=gene2go,
foreground=foreground,
gene2name=gene2name)
if options.output_filename_pattern:
outfile.close()
if len(genelists) > 1:
###################################################################
# output various summary files
# significant results
GO.outputMultipleGeneListResults(all_significant_results,
all_genelists_with_results,
test_ontology,
go2info,
options,
section='significant')
# all results
GO.outputMultipleGeneListResults(all_results,
all_genelists_with_results,
test_ontology,
go2info,
options,
section='all')
if options.compute_pairwise:
GO.pairwiseGOEnrichment(all_results,
all_genelists_with_results,
test_ontology, go2info, options)
outfile_summary = options.stdout
outfile_summary.write("".join(summary))
E.Stop()
def main(argv=None):
"""script main.
parses command line options in sys.argv, unless *argv* is given.
"""
if argv is None:
argv = sys.argv
# setup command line parser
parser = E.OptionParser(version="%prog version: $Id$",
usage=globals()["__doc__"])
parser.add_option("-s",
"--suffix",
dest="suffixes",
action="append",
type="string",
help="mapping of suffix [%default]")
parser.add_option("-m",
"--map",
dest="filename_map",
type="string",
help="filename containing a mapping of filenames "
"to destinations [%default]")
parser.add_option("-u",
"--no-sort",
dest="do_sort",
action="store_false",
help="do not sort filenames before grouping "
"[%default]")
parser.add_option("-n",
"--dry-run",
dest="dry_run",
action="store_true",
help="dry run - do not merge "
"[%default]")
parser.set_defaults(filename_map=None,
do_sort=True,
dry_run=False,
suffixes=[])
# add common options (-h/--help, ...) and parse command line
(options, args) = E.Start(parser, argv=argv)
if options.filename_map:
map_regex2dest = IOTools.readMap(IOTools.openFile(
options.filename_map))
map_regex2dest = dict([(re.compile(x), y)
for x, y in map_regex2dest.items()])
map_suffix2dest = {}
for suffix in options.suffixes:
src, dest = suffix.split("=")
map_suffix2dest[src.strip()] = dest.strip()
filenames = args
if options.do_sort:
filenames.sort()
dest2src = collections.defaultdict(list)
for filename in filenames:
dests = []
for regex, dest in map_regex2dest.items():
if regex.search(filename):
dests.append(dest)
if len(dests) == 0:
raise ValueError("no destination found for %s" % filename)
elif len(dests) > 1:
raise ValueError("multiple destinations found for %s: %s " %
(filename, dests))
dest = dests[0]
# implement suffix mapping, note that
# suffixes can extend beyond an extension
for suffix, new_suffix in map_suffix2dest.items():
if filename.endswith(suffix):
if suffix in map_suffix2dest:
dest = dest + map_suffix2dest[suffix]
break
dest2src[dest].append(filename)
for dest, srcs in sorted(dest2src.iteritems()):
E.info("merging: %s <- %s" % (dest, srcs))
if options.dry_run:
continue
E.run('cat %s > %s' % (" ".join(srcs), dest))
# write footer and output benchmark information.
E.Stop()
def main(argv=None):
parser = E.OptionParser(
version="%prog version: $Id: psl2gff.py 2781 2009-09-10 11:33:14Z andreas $", usage=globals()["__doc__"])
parser.add_option("-a", "--as-gtf", dest="as_gtf", action="store_true",
help="output as gtf.")
parser.add_option("-s", "--filename-strand", dest="filename_strand", type="string",
help="set strand information according to file [default=%DEFAULT].")
parser.set_defaults(as_gtf=False,
filename_strand=None,
test=None)
(options, args) = E.Start(parser, add_pipe_options=True)
####################################
if options.filename_strand:
map_id2strand = IOTools.readMap(open(options.filename_strand, "r"))
else:
map_id2strand = {}
iterator = Blat.BlatIterator(sys.stdin)
ninput, noutput, nskipped = 0, 0, 0
if options.as_gtf:
gff = GTF.Entry()
else:
gff = GTF.Entry()
gff.source = "psl"
gff.feature = "exon"
ids = {}
while 1:
if options.test and ninput >= options.test:
break
match = iterator.next()
if match is None:
break
ninput += 1
if match.mQueryId not in ids:
ids[match.mQueryId] = 1
id = match.mQueryId
else:
id = match.mQueryId + ":%i" % ids[match.mQueryId]
ids[match.mQueryId] += 1
if options.as_gtf:
gff.contig = match.mSbjctId
gff.gene_id = id
gff.transcript_id = id
else:
gff.contig = match.mSbjctId
gff.clearAttributes()
gff.addAttribute("gene_id", id)
if id in map_id2strand:
gff.strand = map_id2strand[id]
else:
gff.strand = match.strand
for qstart, sstart, size in match.getBlocks():
gff.start = sstart
gff.end = sstart + size
options.stdout.write(str(gff) + "\n")
noutput += 1
E.info("ninput=%i, noutput=%i, nskipped=%i" % (ninput, noutput, nskipped))
E.Stop()
(options, args) = E.Start( parser, add_pipe_options = True )
if not options.filename_cdna:
raise ValueError("please supply filename with cds sequences.")
if options.filename_peptides:
infile = open(options.filename_peptides, "r")
E.info("reading from %s" % options.filename_peptides)
else:
E.info("reading from stdin")
infile = sys.stdin
if options.filename_map:
E.info( "reading map" )
map_peptide2cds = IOTools.readMap( IOTools.openFile( options.filename_map, "r" ) )
E.info( "read map for %i identifiers" % len(map_peptide2cds) )
else:
map_peptide2cds = {}
E.info( "reading cds sequences" )
cds_sequences = Genomics.ReadPeptideSequences( IOTools.openFile(options.filename_cdna, "r") )
E.info( "read %i cds sequences" % len(cds_sequences))
ninput, noutput = 0, 0
nskipped, nnosequence = 0, 0
# iterate over peptide sequences
iterator = FastaIterator.FastaIterator( infile )
def test_cmdline():
'''test style of scripts
'''
# start script in order to build the command line parser
global ORIGINAL_START
if ORIGINAL_START is None:
ORIGINAL_START = E.Start
# read the first two columns
map_option2action = IOTools.readMap(
IOTools.openFile(FILENAME_OPTIONLIST),
columns=(0, 1),
has_header=True)
files = []
for label, expression in EXPRESSIONS:
f = glob.glob(expression)
files.extend(sorted(f))
files = filter_files(files)
# make sure to use the current working directory as
# primary lookup.
sys.path.insert(0, ".")
# files = [
# 'scripts/check_db.py',
# 'scripts/cgat_build_report_page.py']
for f in files:
if os.path.isdir(f):
continue
if os.path.basename(f) in EXCLUDE:
continue
script_name = os.path.abspath(f)
pyxfile = (os.path.join(os.path.dirname(f), "_") +
os.path.basename(f) + "x")
fail_.description = script_name
# check if script contains getopt
with IOTools.openFile(script_name) as inf:
if "getopt" in inf.read():
yield (fail_,
"script uses getopt directly: %s" % script_name)
continue
module, modulename = load_script(script_name)
if module is None:
yield (fail_,
"module could not be imported: %s\n" % script_name)
continue
E.Start = LocalStart
try:
module.main(argv=["--help"])
except AttributeError:
yield (fail_,
"no main method in %s\n" % script_name)
ok_(False, "no main method in %s" % script_name)
except SystemExit:
yield (fail_,
"script does not use E.Start() %s\n" % script_name)
except DummyError:
pass
for option in PARSER.option_list:
# ignore options added by optparse
if option.dest is None:
continue
optstring = option.get_opt_string()
if optstring.startswith("--"):
optstring = optstring[2:]
check_option.description = script_name + ":" + optstring
yield(check_option, optstring, os.path.abspath(f),
map_option2action)
# clear up
del sys.modules[modulename]
# scripts with pyximport need special handling.
#
# Multiple imports of pyximport seems to create
# some confusion - here, clear up sys.meta_path after
# each script
if os.path.exists(pyxfile):
sys.meta_path = []
def main(argv=None):
if not argv:
argv = sys.argv
parser = E.OptionParser(version="%prog version: $Id$",
usage=globals()["__doc__"])
parser.add_option("-m", "--merge-exons",
dest="merge_exons",
action="store_true",
help="merge overlapping exons of all transcripts "
"within a gene. "
"The merged exons will be output. "
"Input needs to sorted by gene [default=%default].")
parser.add_option("-t", "--merge-transcripts",
dest="merge_transcripts",
action="store_true",
help="merge all transcripts within a gene. "
"The entry will span the whole gene "
"(exons and introns). "
"The transcript does not include the UTR unless "
"--with-utr is set. [default=%default].")
parser.add_option("--merge-genes", dest="merge_genes", action="store_true",
help="merge overlapping genes if their exons overlap. "
"A gene with a single transcript containing all exons "
"of the overlapping transcripts will be output. "
"This operation ignores strand information "
"The input needs te sorted by transcript "
"[default=%default].")
parser.add_option("--merge-exons-distance",
dest="merge_exons_distance",
type="int",
help="distance in nucleotides between "
"exons to be merged [default=%default].")
parser.add_option("-j", "--join-exons",
dest="join_exons",
action="store_true",
help="join all exons per transcript. "
"A new transcript will be "
"output that spans a whole transcript. "
"Input needs to be sorted by transcript "
"[default=%default].")
parser.add_option("--unset-genes", dest="unset_genes", type="string",
help="unset gene identifiers, keeping "
"transcripts intact. "
"New gene identifiers are set to the "
"pattern given. For example, "
"'--unset-genes=%06i' [default=%default].")
parser.add_option("--sort",
dest="sort",
type="choice",
choices=("gene",
"gene+transcript",
"transcript",
"position",
"contig+gene",
"position+gene",
"gene+position"),
help="sort input data [default=%default].")
parser.add_option("-u", "--with-utr",
dest="with_utr",
action="store_true",
help="include utr in merged transcripts "
"[default=%default].")
parser.add_option("--intersect-transcripts",
dest="intersect_transcripts",
action="store_true",
help="intersect all transcripts within a gene. "
"The entry will only span those bases "
"that are covered by all transcrips."
"The transcript does not include the UTR unless "
"--with-utr is set. This method "
"will remove all other features (stop_codon, etc.) "
"The input needs to be sorted by gene. "
"[default=%default].")
parser.add_option("-i", "--merge-introns",
dest="merge_introns",
action="store_true",
help="merge and output all introns within a "
"gene. The output will contain "
"all intronic regions within a gene. Single exon genes "
"are skipped. "
"The input needs to be sorted by gene. "
"[default=%default].")
parser.add_option("-g", "--set-transcript-to-gene",
"--set-transcript2gene",
dest="set_transcript2gene",
action="store_true",
help="set the transcript_id to the "
"gene_id [default=%default].")
parser.add_option("--set-protein-to-transcript",
dest="set_protein2transcript",
action="store_true",
help="set the protein_id to the "
"transcript_id [default=%default].")
parser.add_option("--add-protein-id",
dest="add_protein_id",
type="string",
help="add a protein_id for each transcript_id. "
"The argument is a filename containing a mapping "
"between "
"transcript_id to protein_id [default=%default].")
parser.add_option("-G", "--set-gene-to-transcript",
"--set-gene2transcript",
dest="set_gene2transcript",
action="store_true",
help="set the gene_id to the "
"transcript_id [default=%default].")
parser.add_option("-d",
"--set-score2distance",
dest="set_score2distance",
action="store_true",
help="set the score field for each feature to the "
"distance to "
"transcription start site [default=%default].")
parser.add_option("--exons2introns",
dest="exons2introns",
action="store_true",
help="for each gene build an 'intronic' transcript "
"containing the union of all intronic regions "
"of all transcripts in a gene."
"The features are labeled as 'intron'."
"The input needs to be sorted by gene. "
"[default=%default].")
parser.add_option("-f", "--filter", dest="filter",
type="choice",
choices=("gene", "transcript", "longest-gene",
"longest-transcript",
"representative-transcript"),
help="apply a filter to the input file. Available "
"filters are: "
"'gene': filter by gene_id, "
"'transcript': filter by transcript_id, "
"'longest-gene': output the longest gene for "
"overlapping genes ,"
"'longest-transcript': output the longest "
"transcript per gene,"
"'representative-transcript': output the "
"representative transcript per gene. "
"The representative transcript is the transcript "
"that shares most exons with "
"the other transcripts in a gene. "
"The input needs to be sorted by gene. "
"[default=%default].")
parser.add_option("-r", "--rename",
dest="rename",
type="choice",
choices=("gene", "transcript"),
help="rename genes or transcripts with a map "
"given by the option `--apply`. "
"Those that can not be renamed are removed "
"[default=%default].")
parser.add_option("--renumber-genes", dest="renumber_genes", type="string",
help="renumber genes according to the given pattern. "
"[default=%default].")
parser.add_option("--renumber-transcripts",
dest="renumber_transcripts",
type="string",
help="renumber transcripts according to the "
"given pattern. "
"[default=%default].")
parser.add_option("-a", "--apply", dest="filename_filter", type="string",
metavar="tsv",
help="filename of ids to map/filter [default=%default].")
parser.add_option("--invert-filter",
dest="invert_filter",
action="store_true",
help="when using --filter, invert selection "
"(like grep -v). "
"[default=%default].")
parser.add_option("--sample-size", dest="sample_size", type="int",
help="extract a random sample of size # if the option "
"'--filter' is set[default=%default].")
parser.add_option("--intron-min-length",
dest="intron_min_length", type="int",
help="minimum length for introns (for --exons2introns) "
"[default=%default].")
parser.add_option("--min-exons-length",
dest="min_exons_length",
type="int",
help="minimum length for gene (sum of exons) "
"(--sample-size) [default=%default].")
parser.add_option("--intron-border",
dest="intron_border",
type="int",
help="number of residues to exclude at intron at either end "
"(--exons2introns) [default=%default].")
parser.add_option("--transcripts2genes",
dest="transcripts2genes",
action="store_true",
help="cluster overlapping transcripts into genes.")
parser.add_option("--reset-strand",
dest="reset_strand",
action="store_true",
help="remove strandedness of features (set to '.') when "
"using --transcripts2genes"
"[default=%default].")
parser.add_option("--remove-overlapping", dest="remove_overlapping",
type="string",
metavar="gff",
help="remove all transcripts that overlap intervals "
"in a gff-formatted file."
"The comparison ignores strand "
"[default=%default].")
parser.add_option("--permit-duplicates", dest="strict",
action="store_false",
help="permit duplicate genes. "
"[default=%default]")
parser.add_option("--remove-duplicates", dest="remove_duplicates",
type="choice",
choices=("gene", "transcript", "ucsc", "coordinates"),
help="remove duplicates by gene/transcript. "
"If ``ucsc`` is chosen, transcripts ending on _dup# are "
"removed. This is necessary to remove duplicate entries "
"that are next to each other in the sort order "
"[%default]")
parser.add_option("--rename-duplicates", dest="rename_duplicates",
action="store_true",
help="rename duplicate gene_ids and transcript_ids by "
"addition of a numerical suffix")
parser.set_defaults(
sort=None,
merge_exons=False,
join_exons=False,
merge_exons_distance=0,
merge_transcripts=False,
set_score2distance=False,
set_gene2transcript=False,
set_transcript2gene=False,
set_protein2transcript=False,
add_protein_id=None,
filename_filter=None,
filter=None,
exons2introns=None,
merge_genes=False,
intron_border=None,
intron_min_length=None,
sample_size=0,
min_exons_length=0,
transripts2genes=False,
reset_strand=False,
with_utr=False,
invert_filter=False,
remove_duplicates=None,
remove_overlapping=None,
renumber_genes=None,
unset_genes=None,
renumber_transcripts=None,
strict=True,
intersect_transcripts=False,
rename_duplicates=False,
)
(options, args) = E.Start(parser, argv=argv)
ninput, noutput, nfeatures, ndiscarded = 0, 0, 0, 0
if options.set_transcript2gene:
for gff in GTF.iterator(options.stdin):
ninput += 1
gff.setAttribute("transcript_id", gff.gene_id)
options.stdout.write("%s\n" % str(gff))
noutput += 1
nfeatures += 1
elif options.remove_duplicates:
counts = collections.defaultdict(int)
if options.remove_duplicates == "ucsc":
store = []
remove = set()
f = lambda x: x[0].transcript_id
gffs = GTF.transcript_iterator(
GTF.iterator(options.stdin), strict=False)
outf = lambda x: "\n".join([str(y) for y in x])
for entry in gffs:
ninput += 1
store.append(entry)
id = f(entry)
if "_dup" in id:
remove.add(re.sub("_dup\d+", "", id))
remove.add(id)
for entry in store:
id = f(entry)
if id not in remove:
options.stdout.write(outf(entry) + "\n")
noutput += 1
else:
ndiscarded += 1
E.info("discarded duplicates for %s" % (id))
else:
if options.remove_duplicates == "gene":
gffs = GTF.gene_iterator(
GTF.iterator(options.stdin), strict=False)
f = lambda x: x[0][0].gene_id
outf = lambda x: "\n".join(
["\n".join([str(y) for y in xx]) for xx in x])
elif options.remove_duplicates == "transcript":
gffs = GTF.transcript_iterator(
GTF.iterator(options.stdin), strict=False)
f = lambda x: x[0].transcript_id
outf = lambda x: "\n".join([str(y) for y in x])
elif options.remove_duplicates == "coordinates":
gffs = GTF.chunk_iterator(GTF.iterator(options.stdin))
f = lambda x: x[0].contig + "_" + \
str(x[0].start) + "-" + str(x[0].end)
outf = lambda x: "\n".join([str(y) for y in x])
store = []
for entry in gffs:
ninput += 1
store.append(entry)
id = f(entry)
counts[id] += 1
# Assumes GTF file sorted by contig then start
last_id = ""
if options.remove_duplicates == "coordinates":
for entry in store:
id = f(entry)
if id == last_id:
ndiscarded += 1
E.info("discarded duplicates for %s: %i" %
(id, counts[id]))
else:
options.stdout.write(outf(entry) + "\n")
noutput += 1
last_id = id
else:
for entry in store:
id = f(entry)
if counts[id] == 1:
options.stdout.write(outf(entry) + "\n")
noutput += 1
else:
ndiscarded += 1
E.info("discarded duplicates for %s: %i" %
(id, counts[id]))
elif options.sort:
for gff in GTF.iterator_sorted(GTF.iterator(options.stdin),
sort_order=options.sort):
ninput += 1
options.stdout.write("%s\n" % str(gff))
noutput += 1
nfeatures += 1
elif options.set_gene2transcript:
for gff in GTF.iterator(options.stdin):
ninput += 1
gff.setAttribute("gene_id", gff.transcript_id)
options.stdout.write("%s\n" % str(gff))
noutput += 1
nfeatures += 1
elif options.set_protein2transcript:
for gff in GTF.iterator(options.stdin):
ninput += 1
gff.setAttribute("protein_id", gff.transcript_id)
options.stdout.write("%s\n" % str(gff))
noutput += 1
nfeatures += 1
elif options.add_protein_id:
transcript2protein = IOTools.readMap(open(options.add_protein_id, "r"))
missing = set()
for gff in GTF.iterator(options.stdin):
ninput += 1
if gff.transcript_id not in transcript2protein:
if gff.transcript_id not in missing:
E.debug(
("removing transcript '%s' due to "
"missing protein id") % gff.transcript_id)
missing.add(gff.transcript_id)
ndiscarded += 1
continue
gff.setAttribute(
"protein_id", transcript2protein[gff.transcript_id])
options.stdout.write("%s\n" % str(gff))
noutput += 1
nfeatures += 1
E.info("transcripts removed due to missing protein ids: %i" %
len(missing))
elif options.join_exons:
for exons in GTF.transcript_iterator(GTF.iterator(options.stdin)):
ninput += 1
strand = Genomics.convertStrand(exons[0].strand)
contig = exons[0].contig
transid = exons[0].transcript_id
geneid = exons[0].gene_id
biotype = exons[0].source
all_start, all_end = min([x.start for x in exons]), max(
[x.end for x in exons])
y = GTF.Entry()
y.contig = contig
y.source = biotype
y.feature = "transcript"
y.start = all_start
y.end = all_end
y.strand = strand
y.transcript_id = transid
y.gene_id = geneid
options.stdout.write("%s\n" % str(y))
elif options.merge_genes:
# merges overlapping genes
#
gffs = GTF.iterator_sorted_chunks(
GTF.flat_gene_iterator(GTF.iterator(options.stdin)),
sort_by="contig-strand-start")
def iterate_chunks(gff_chunks):
last = gff_chunks.next()
to_join = [last]
for gffs in gff_chunks:
d = gffs[0].start - last[-1].end
if gffs[0].contig == last[0].contig and \
gffs[0].strand == last[0].strand:
assert gffs[0].start >= last[0].start, \
("input file should be sorted by contig, strand "
"and position: d=%i:\nlast=\n%s\nthis=\n%s\n") % \
(d,
"\n".join([str(x) for x in last]),
"\n".join([str(x) for x in gffs]))
if gffs[0].contig != last[0].contig or \
gffs[0].strand != last[0].strand or \
d > 0:
yield to_join
to_join = []
last = gffs
to_join.append(gffs)
yield to_join
raise StopIteration
for chunks in iterate_chunks(gffs):
ninput += 1
if len(chunks) > 1:
gene_id = "merged_%s" % chunks[0][0].gene_id
transcript_id = "merged_%s" % chunks[0][0].transcript_id
info = ",".join([x[0].gene_id for x in chunks])
else:
gene_id = chunks[0][0].gene_id
transcript_id = chunks[0][0].transcript_id
info = None
intervals = []
for c in chunks:
intervals += [(x.start, x.end) for x in c]
intervals = Intervals.combine(intervals)
# take single strand
strand = chunks[0][0].strand
for start, end in intervals:
y = GTF.Entry()
y.fromGTF(chunks[0][0], gene_id, transcript_id)
y.start = start
y.end = end
y.strand = strand
if info:
y.addAttribute("merged", info)
options.stdout.write("%s\n" % str(y))
nfeatures += 1
noutput += 1
elif options.renumber_genes:
map_old2new = {}
for gtf in GTF.iterator(options.stdin):
ninput += 1
if gtf.gene_id not in map_old2new:
map_old2new[gtf.gene_id] = options.renumber_genes % (
len(map_old2new) + 1)
gtf.setAttribute("gene_id", map_old2new[gtf.gene_id])
options.stdout.write("%s\n" % str(gtf))
noutput += 1
elif options.unset_genes:
map_old2new = {}
for gtf in GTF.iterator(options.stdin):
ninput += 1
key = gtf.transcript_id
if key not in map_old2new:
map_old2new[key] = options.unset_genes % (len(map_old2new) + 1)
gtf.setAttribute("gene_id", map_old2new[key])
options.stdout.write("%s\n" % str(gtf))
noutput += 1
elif options.renumber_transcripts:
map_old2new = {}
for gtf in GTF.iterator(options.stdin):
ninput += 1
key = (gtf.gene_id, gtf.transcript_id)
if key not in map_old2new:
map_old2new[key] = options.renumber_transcripts % (
len(map_old2new) + 1)
gtf.setAttribute("transcript_id", map_old2new[key])
options.stdout.write("%s\n" % str(gtf))
noutput += 1
elif options.transcripts2genes:
transcripts = set()
genes = set()
reset_strand = options.reset_strand
for gtfs in GTF.iterator_transcripts2genes(
GTF.iterator(options.stdin)):
ninput += 1
for gtf in gtfs:
if reset_strand:
gtf.strand = "."
options.stdout.write("%s\n" % str(gtf))
transcripts.add(gtf.transcript_id)
genes.add(gtf.gene_id)
nfeatures += 1
noutput += 1
E.info("transcripts2genes: transcripts=%i, genes=%i" %
(len(transcripts), len(genes)))
elif options.rename:
map_old2new = IOTools.readMap(open(options.filename_filter, "r"))
if options.rename == "transcript":
is_gene_id = False
elif options.rename == "gene":
is_gene_id = True
for gff in GTF.iterator(options.stdin):
ninput += 1
if is_gene_id:
if gff.gene_id in map_old2new:
gff.setAttribute("gene_id", map_old2new[gff.gene_id])
else:
E.debug("removing missing gene_id %s" % gff.gene_id)
ndiscarded += 1
continue
else:
if gff.transcript_id in map_old2new:
gff.setAttribute(
"transcript_id", map_old2new[gff.transcript_id])
else:
E.debug("removing missing transcript_id %s" %
gff.transcript_id)
ndiscarded += 1
continue
noutput += 1
options.stdout.write("%s\n" % str(gff))
elif options.filter:
keep_genes = set()
if options.filter == "longest-gene":
iterator = GTF.flat_gene_iterator(GTF.iterator(options.stdin))
coords = []
gffs = []
for gff in iterator:
gff.sort(key=lambda x: x.start)
coords.append((gff[0].contig,
min([x.start for x in gff]),
max([x.end for x in gff]),
gff[0].gene_id))
gffs.append(gff)
coords.sort()
last_contig = None
max_end = 0
longest_gene_id = None
longest_length = None
for contig, start, end, gene_id in coords:
ninput += 1
if contig != last_contig or start >= max_end:
if longest_gene_id:
keep_genes.add(longest_gene_id)
longest_gene_id = gene_id
longest_length = end - start
max_end = end
else:
if end - start > longest_length:
longest_length, longest_gene_id = end - start, gene_id
last_contig = contig
max_end = max(max_end, end)
keep_genes.add(longest_gene_id)
invert = options.invert_filter
for gff in gffs:
keep = gff[0].gene_id in keep_genes
if (keep and not invert) or (not keep and invert):
noutput += 1
for g in gff:
nfeatures += 1
options.stdout.write("%s\n" % g)
else:
ndiscarded += 1
elif options.filter in ("longest-transcript", "representative-transcript"):
iterator = GTF.gene_iterator(GTF.iterator(options.stdin))
def selectLongestTranscript(gene):
r = []
for transcript in gene:
transcript.sort(key=lambda x: x.start)
length = transcript[-1].end - transcript[0].start
r.append((length, transcript))
r.sort()
return r[-1][1]
def selectRepresentativeTranscript(gene):
'''select a representative transcript.
The representative transcript represent the largest number
of exons over all transcripts.
'''
all_exons = []
for transcript in gene:
all_exons.extend([(x.start, x.end)
for x in transcript if x.feature == "exon"])
exon_counts = {}
for key, exons in itertools.groupby(all_exons):
exon_counts[key] = len(list(exons))
transcript_counts = []
for transcript in gene:
count = sum([exon_counts[(x.start, x.end)]
for x in transcript if x.feature == "exon"])
transcript_counts.append((count, transcript))
transcript_counts.sort()
return transcript_counts[-1][1]
if options.filter == "longest-transcript":
_select = selectLongestTranscript
elif options.filter == "representative-transcript":
_select = selectRepresentativeTranscript
for gene in iterator:
ninput += 1
transcript = _select(gene)
noutput += 1
for g in transcript:
nfeatures += 1
options.stdout.write("%s\n" % g)
elif options.filter in ("gene", "transcript"):
if options.filename_filter:
ids, nerrors = IOTools.ReadList(
open(options.filename_filter, "r"))
E.info("read %i ids" % len(ids))
ids = set(ids)
by_gene = options.filter == "gene"
by_transcript = options.filter == "transcript"
invert = options.invert_filter
reset_strand = options.reset_strand
for gff in GTF.iterator(options.stdin):
ninput += 1
keep = False
if by_gene:
keep = gff.gene_id in ids
if by_transcript:
keep = gff.transcript_id in ids
if (invert and keep) or (not invert and not keep):
continue
if reset_strand:
gff.strand = "."
options.stdout.write("%s\n" % str(gff))
nfeatures += 1
noutput += 1
elif options.sample_size:
if options.filter == "gene":
iterator = GTF.flat_gene_iterator(
GTF.iterator(options.stdin))
elif options.filter == "transcript":
iterator = GTF.transcript_iterator(
GTF.iterator(options.stdin))
if options.min_exons_length:
iterator = GTF.iterator_min_feature_length(
iterator,
min_length=options.min_exons_length,
feature="exon")
data = [x for x in iterator]
ninput = len(data)
if len(data) > options.sample_size:
data = random.sample(data, options.sample_size)
for d in data:
noutput += 1
for dd in d:
nfeatures += 1
options.stdout.write(str(dd) + "\n")
else:
assert False, "please supply either a filename "
"with ids to filter with (--apply) or a sample-size."
elif options.exons2introns:
for gffs in GTF.flat_gene_iterator(GTF.iterator(options.stdin)):
ninput += 1
cds_ranges = GTF.asRanges(gffs, "CDS")
exon_ranges = GTF.asRanges(gffs, "exon")
input_ranges = Intervals.combine(cds_ranges + exon_ranges)
if len(input_ranges) > 1:
last = input_ranges[0][1]
output_ranges = []
for start, end in input_ranges[1:]:
output_ranges.append((last, start))
last = end
if options.intron_border:
b = options.intron_border
output_ranges = [(x[0] + b, x[1] - b)
for x in output_ranges]
if options.intron_min_length:
l = options.intron_min_length
output_ranges = [
x for x in output_ranges if x[1] - x[0] > l]
for start, end in output_ranges:
entry = GTF.Entry()
entry.copy(gffs[0])
entry.clearAttributes()
entry.transcript_id = "merged"
entry.feature = "intron"
entry.start = start
entry.end = end
options.stdout.write("%s\n" % str(entry))
nfeatures += 1
noutput += 1
else:
ndiscarded += 1
elif options.set_score2distance:
for gffs in GTF.transcript_iterator(GTF.iterator(options.stdin)):
ninput += 1
strand = Genomics.convertStrand(gffs[0].strand)
all_start, all_end = min([x.start for x in gffs]), max(
[x.end for x in gffs])
if strand != ".":
t = 0
if strand == "-":
gffs.reverse()
for gff in gffs:
gff.score = t
t += gff.end - gff.start
if strand == "-":
gffs.reverse()
for gff in gffs:
options.stdout.write("%s\n" % str(gff))
nfeatures += 1
noutput += 1
elif options.remove_overlapping:
index = GTF.readAndIndex(
GTF.iterator(IOTools.openFile(options.remove_overlapping, "r")))
for gffs in GTF.transcript_iterator(GTF.iterator(options.stdin)):
ninput += 1
found = False
for e in gffs:
if index.contains(e.contig, e.start, e.end):
found = True
break
if found:
ndiscarded += 1
else:
noutput += 1
for e in gffs:
nfeatures += 1
options.stdout.write("%s\n" % str(e))
elif options.intersect_transcripts:
for gffs in GTF.gene_iterator(GTF.iterator(options.stdin),
strict=options.strict):
ninput += 1
r = []
for g in gffs:
if options.with_utr:
ranges = GTF.asRanges(g, "exon")
else:
ranges = GTF.asRanges(g, "CDS")
r.append(ranges)
result = r[0]
for x in r[1:]:
result = Intervals.intersect(result, x)
entry = GTF.Entry()
entry.copy(gffs[0][0])
entry.clearAttributes()
entry.transcript_id = "merged"
entry.feature = "exon"
for start, end in result:
entry.start = start
entry.end = end
options.stdout.write("%s\n" % str(entry))
nfeatures += 1
noutput += 1
elif options.rename_duplicates:
gene_ids = list()
transcript_ids = list()
gtfs = list()
for gtf in GTF.iterator(options.stdin):
gtfs.append(gtf)
if gtf.feature == "CDS":
gene_ids.append(gtf.gene_id)
transcript_ids.append(gtf.transcript_id)
dup_gene = [item for item in set(gene_ids) if gene_ids.count(item) > 1]
dup_transcript = [item for item in set(transcript_ids)
if transcript_ids.count(item) > 1]
E.info("Number of duplicated gene_ids: %i" % len(dup_gene))
E.info("Number of duplicated transcript_ids: %i" % len(dup_transcript))
gene_dict = dict(zip(dup_gene, ([0] * len(dup_gene))))
transcript_dict = dict(zip(dup_transcript,
([0] * len(dup_transcript))))
for gtf in gtfs:
if gtf.feature == "CDS":
if gtf.gene_id in dup_gene:
gene_dict[gtf.gene_id] = gene_dict[gtf.gene_id] + 1
gtf.setAttribute('gene_id',
gtf.gene_id + "." +
str(gene_dict[gtf.gene_id]))
if gtf.transcript_id in dup_transcript:
transcript_dict[gtf.transcript_id] = \
transcript_dict[gtf.transcript_id] + 1
gtf.setAttribute('transcript_id',
gtf.transcript_id + "." +
str(transcript_dict[gtf.transcript_id]))
options.stdout.write("%s\n" % gtf)
else:
for gffs in GTF.flat_gene_iterator(
GTF.iterator(options.stdin),
strict=options.strict):
ninput += 1
cds_ranges = GTF.asRanges(gffs, "CDS")
exon_ranges = GTF.asRanges(gffs, "exon")
# sanity checks
strands = set([x.strand for x in gffs])
contigs = set([x.contig for x in gffs])
if len(strands) > 1:
raise ValueError("can not merge gene '%s' on multiple strands: %s" % (
gffs[0].gene_id, str(strands)))
if len(contigs) > 1:
raise ValueError("can not merge gene '%s' on multiple contigs: %s" % (
gffs[0].gene_id, str(contigs)))
strand = Genomics.convertStrand(gffs[0].strand)
if cds_ranges and options.with_utr:
cds_start, cds_end = cds_ranges[0][0], cds_ranges[-1][1]
midpoint = (cds_end - cds_start) / 2 + cds_start
utr_ranges = []
for start, end in Intervals.truncate(exon_ranges, cds_ranges):
if end - start > 3:
if strand == ".":
feature = "UTR"
elif strand == "+":
if start < midpoint:
feature = "UTR5"
else:
feature = "UTR3"
elif strand == "-":
if start < midpoint:
feature = "UTR3"
else:
feature = "UTR5"
utr_ranges.append((feature, start, end))
output_feature = "CDS"
output_ranges = cds_ranges
else:
output_feature = "exon"
output_ranges = exon_ranges
utr_ranges = []
result = []
if options.merge_exons:
# need to combine per feature - skip
# utr_ranges = Intervals.combineAtDistance(
# utr_ranges,
# options.merge_exons_distance)
output_ranges = Intervals.combineAtDistance(
output_ranges, options.merge_exons_distance)
for feature, start, end in utr_ranges:
entry = GTF.Entry()
entry.copy(gffs[0])
entry.clearAttributes()
entry.feature = feature
entry.transcript_id = "merged"
entry.start = start
entry.end = end
result.append(entry)
for start, end in output_ranges:
entry = GTF.Entry()
entry.copy(gffs[0])
entry.clearAttributes()
entry.transcript_id = "merged"
entry.feature = output_feature
entry.start = start
entry.end = end
result.append(entry)
elif options.merge_transcripts:
entry = GTF.Entry()
entry.copy(gffs[0])
entry.clearAttributes()
entry.transcript_id = entry.gene_id
entry.start = output_ranges[0][0]
entry.end = output_ranges[-1][1]
result.append(entry)
elif options.merge_introns:
if len(output_ranges) >= 2:
entry = GTF.Entry()
entry.copy(gffs[0])
entry.clearAttributes()
entry.transcript_id = entry.gene_id
entry.start = output_ranges[0][1]
entry.end = output_ranges[-1][0]
result.append(entry)
else:
ndiscarded += 1
continue
result.sort(key=lambda x: x.start)
for x in result:
options.stdout.write("%s\n" % str(x))
nfeatures += 1
noutput += 1
E.info("ninput=%i, noutput=%i, nfeatures=%i, ndiscarded=%i" %
(ninput, noutput, nfeatures, ndiscarded))
E.Stop()
def main(argv=None):
"""script main.
parses command line options in sys.argv, unless *argv* is given.
"""
if not argv:
argv = sys.argv
# setup command line parser
parser = E.OptionParser(version="%prog version: $Id$",
usage=globals()["__doc__"])
parser.add_option(
"-g", "--gtf-file", dest="filename_gtf", type="string",
help="filename with gene models in gtf format [%default]")
parser.add_option(
"-m", "--filename-mismapped", dest="filename_mismapped", type="string",
help="output bam file for mismapped reads [%default]")
parser.add_option(
"-j", "--junctions-bed-file", dest="filename_junctions", type="string",
help="bam file with reads mapped across junctions [%default]")
parser.add_option(
"-r", "--filename-regions", dest="filename_regions", type="string",
help="filename with regions to remove in bed format [%default]")
parser.add_option(
"-t", "--transcripts-gtf-file", dest="filename_transcriptome",
type="string",
help="bam file with reads mapped against transcripts [%default]")
parser.add_option(
"-p", "--map-tsv-file", dest="filename_map", type="string",
help="filename mapping transcript numbers (used by "
"--filename-transciptome) to transcript names "
"(used by --filename-gtf) [%default]")
parser.add_option(
"-s", "--filename-stats", dest="filename_stats", type="string",
help="filename to output stats to [%default]")
parser.add_option(
"-o", "--colour",
dest="colour_mismatches", action="store_true",
help="mismatches will use colour differences (CM tag) [%default]")
parser.add_option(
"-i", "--ignore-mismatches",
dest="ignore_mismatches", action="store_true",
help="ignore mismatches [%default]")
parser.add_option(
"-c", "--remove-contigs", dest="remove_contigs", type="string",
help="','-separated list of contigs to remove [%default]")
parser.add_option(
"-f", "--force-output", dest="force", action="store_true",
help="force overwriting of existing files [%default]")
parser.add_option("-u", "--unique", dest="unique", action="store_true",
help="remove reads not matching uniquely [%default]")
parser.add_option("--output-sam", dest="output_sam", action="store_true",
help="output in sam format [%default]")
parser.set_defaults(
filename_gtf=None,
filename_mismapped=None,
filename_junctions=None,
filename_transcriptome=None,
filename_map=None,
remove_contigs=None,
force=False,
unique=False,
colour_mismatches=False,
ignore_mismatches=False,
output_sam=False,
filename_table=None,
)
# add common options (-h/--help, ...) and parse command line
(options, args) = E.Start(parser, argv=argv)
if len(args) != 1:
raise ValueError("please supply one bam file")
bamfile_genome = args[0]
genome_samfile = pysam.AlignmentFile(bamfile_genome, "rb")
if options.remove_contigs:
options.remove_contigs = options.remove_contigs.split(",")
if options.filename_map:
E.info("reading map")
id_map = IOTools.readMap(
IOTools.openFile(options.filename_map), has_header=True)
id_map = dict([(y, x) for x, y in id_map.items()])
else:
id_map = None
transcripts = {}
if options.filename_gtf:
E.info("indexing geneset")
mapped, missed = 0, 0
for gtf in GTF.transcript_iterator(
GTF.iterator(IOTools.openFile(options.filename_gtf))):
gtf.sort(key=lambda x: x.start)
transcript_id = gtf[0].transcript_id
if id_map:
try:
transcript_id = id_map[transcript_id]
mapped += 1
except KeyError:
missed += 1
continue
transcripts[transcript_id] = gtf
E.info("read %i transcripts from geneset (%i mapped, %i missed)" %
(len(transcripts), mapped, missed))
regions_to_remove = None
if options.filename_regions:
E.info("indexing regions")
regions_to_remove = IndexedGenome.Simple()
for bed in Bed.iterator(IOTools.openFile(options.filename_regions)):
regions_to_remove.add(bed.contig, bed.start, bed.end)
E.info("read %i regions" % len(regions_to_remove))
if options.filename_transcriptome:
transcripts_samfile = pysam.AlignmentFile(options.filename_transcriptome,
"rb")
else:
transcripts_samfile = None
if options.output_sam:
output_samfile = pysam.AlignmentFile("-", "wh", template=genome_samfile)
else:
output_samfile = pysam.AlignmentFile("-", "wb", template=genome_samfile)
if options.filename_mismapped:
if not options.force and os.path.exists(options.filename_mismapped):
raise IOError("output file %s already exists" %
options.filename_mismapped)
output_mismapped = pysam.AlignmentFile(options.filename_mismapped,
"wb",
template=genome_samfile)
else:
output_mismapped = None
if options.filename_junctions:
junctions_samfile = pysam.AlignmentFile(options.filename_junctions,
"rb")
else:
junctions_samfile = None
c = _bams2bam.filter(genome_samfile,
output_samfile,
output_mismapped,
transcripts_samfile,
junctions_samfile,
transcripts,
regions=regions_to_remove,
unique=options.unique,
remove_contigs=options.remove_contigs,
colour_mismatches=options.colour_mismatches,
ignore_mismatches=options.ignore_mismatches,
ignore_transcripts=transcripts_samfile is None,
ignore_junctions=junctions_samfile is None)
if options.filename_stats:
outf = IOTools.openFile(options.filename_stats, "w")
outf.write("category\tcounts\n%s\n" % c.asTable())
outf.close()
if options.filename_transcriptome:
transcripts_samfile.close()
genome_samfile.close()
output_samfile.close()
if output_mismapped:
output_mismapped.close()
# write footer and output benchmark information.
E.Stop()
def main(argv=None):
if not argv:
argv = sys.argv
parser = E.OptionParser(version="%prog version: $Id$",
usage=globals()["__doc__"])
parser.add_option("-m",
"--merge-exons",
dest="merge_exons",
action="store_true",
help="merge overlapping exons of all transcripts "
"within a gene. "
"The merged exons will be output. "
"Input needs to sorted by gene [default=%default].")
parser.add_option("-t",
"--merge-transcripts",
dest="merge_transcripts",
action="store_true",
help="merge all transcripts within a gene. "
"The entry will span the whole gene "
"(exons and introns). "
"The transcript does not include the UTR unless "
"--with-utr is set. [default=%default].")
parser.add_option("--merge-genes",
dest="merge_genes",
action="store_true",
help="merge overlapping genes if their exons overlap. "
"A gene with a single transcript containing all exons "
"of the overlapping transcripts will be output. "
"This operation ignores strand information "
"The input needs te sorted by transcript "
"[default=%default].")
parser.add_option("--merge-exons-distance",
dest="merge_exons_distance",
type="int",
help="distance in nucleotides between "
"exons to be merged [default=%default].")
parser.add_option("-j",
"--join-exons",
dest="join_exons",
action="store_true",
help="join all exons per transcript. "
"A new transcript will be "
"output that spans a whole transcript. "
"Input needs to be sorted by transcript "
"[default=%default].")
parser.add_option("--unset-genes",
dest="unset_genes",
type="string",
help="unset gene identifiers, keeping "
"transcripts intact. "
"New gene identifiers are set to the "
"pattern given. For example, "
"'--unset-genes=%06i' [default=%default].")
parser.add_option("--sort",
dest="sort",
type="choice",
choices=("gene", "gene+transcript", "transcript",
"position", "contig+gene", "position+gene",
"gene+position"),
help="sort input data [default=%default].")
parser.add_option("-u",
"--with-utr",
dest="with_utr",
action="store_true",
help="include utr in merged transcripts "
"[default=%default].")
parser.add_option("--intersect-transcripts",
dest="intersect_transcripts",
action="store_true",
help="intersect all transcripts within a gene. "
"The entry will only span those bases "
"that are covered by all transcrips."
"The transcript does not include the UTR unless "
"--with-utr is set. This method "
"will remove all other features (stop_codon, etc.) "
"The input needs to be sorted by gene. "
"[default=%default].")
parser.add_option("-i",
"--merge-introns",
dest="merge_introns",
action="store_true",
help="merge and output all introns within a "
"gene. The output will contain "
"all intronic regions within a gene. Single exon genes "
"are skipped. "
"The input needs to be sorted by gene. "
"[default=%default].")
parser.add_option("-g",
"--set-transcript-to-gene",
"--set-transcript2gene",
dest="set_transcript2gene",
action="store_true",
help="set the transcript_id to the "
"gene_id [default=%default].")
parser.add_option("--set-protein-to-transcript",
dest="set_protein2transcript",
action="store_true",
help="set the protein_id to the "
"transcript_id [default=%default].")
parser.add_option("--add-protein-id",
dest="add_protein_id",
type="string",
help="add a protein_id for each transcript_id. "
"The argument is a filename containing a mapping "
"between "
"transcript_id to protein_id [default=%default].")
parser.add_option("-G",
"--set-gene-to-transcript",
"--set-gene2transcript",
dest="set_gene2transcript",
action="store_true",
help="set the gene_id to the "
"transcript_id [default=%default].")
parser.add_option("-d",
"--set-score2distance",
dest="set_score2distance",
action="store_true",
help="set the score field for each feature to the "
"distance to "
"transcription start site [default=%default].")
parser.add_option("--exons2introns",
dest="exons2introns",
action="store_true",
help="for each gene build an 'intronic' transcript "
"containing the union of all intronic regions "
"of all transcripts in a gene."
"The features are labeled as 'intron'."
"The input needs to be sorted by gene. "
"[default=%default].")
parser.add_option("-f",
"--filter",
dest="filter",
type="choice",
choices=("gene", "transcript", "longest-gene",
"longest-transcript",
"representative-transcript"),
help="apply a filter to the input file. Available "
"filters are: "
"'gene': filter by gene_id, "
"'transcript': filter by transcript_id, "
"'longest-gene': output the longest gene for "
"overlapping genes ,"
"'longest-transcript': output the longest "
"transcript per gene,"
"'representative-transcript': output the "
"representative transcript per gene. "
"The representative transcript is the transcript "
"that shares most exons with "
"the other transcripts in a gene. "
"The input needs to be sorted by gene. "
"[default=%default].")
parser.add_option("-r",
"--rename",
dest="rename",
type="choice",
choices=("gene", "transcript"),
help="rename genes or transcripts with a map "
"given by the option `--apply`. "
"Those that can not be renamed are removed "
"[default=%default].")
parser.add_option("--renumber-genes",
dest="renumber_genes",
type="string",
help="renumber genes according to the given pattern. "
"[default=%default].")
parser.add_option("--renumber-transcripts",
dest="renumber_transcripts",
type="string",
help="renumber transcripts according to the "
"given pattern. "
"[default=%default].")
parser.add_option("-a",
"--apply",
dest="filename_filter",
type="string",
metavar="tsv",
help="filename of ids to map/filter [default=%default].")
parser.add_option("--invert-filter",
dest="invert_filter",
action="store_true",
help="when using --filter, invert selection "
"(like grep -v). "
"[default=%default].")
parser.add_option("--sample-size",
dest="sample_size",
type="int",
help="extract a random sample of size # if the option "
"'--filter' is set[default=%default].")
parser.add_option("--intron-min-length",
dest="intron_min_length",
type="int",
help="minimum length for introns (for --exons2introns) "
"[default=%default].")
parser.add_option("--min-exons-length",
dest="min_exons_length",
type="int",
help="minimum length for gene (sum of exons) "
"(--sample-size) [default=%default].")
parser.add_option(
"--intron-border",
dest="intron_border",
type="int",
help="number of residues to exclude at intron at either end "
"(--exons2introns) [default=%default].")
parser.add_option("--transcripts2genes",
dest="transcripts2genes",
action="store_true",
help="cluster overlapping transcripts into genes.")
parser.add_option("--reset-strand",
dest="reset_strand",
action="store_true",
help="remove strandedness of features (set to '.') when "
"using --transcripts2genes"
"[default=%default].")
parser.add_option("--remove-overlapping",
dest="remove_overlapping",
type="string",
metavar="gff",
help="remove all transcripts that overlap intervals "
"in a gff-formatted file."
"The comparison ignores strand "
"[default=%default].")
parser.add_option("--permit-duplicates",
dest="strict",
action="store_false",
help="permit duplicate genes. "
"[default=%default]")
parser.add_option("--remove-duplicates",
dest="remove_duplicates",
type="choice",
choices=("gene", "transcript", "ucsc", "coordinates"),
help="remove duplicates by gene/transcript. "
"If ``ucsc`` is chosen, transcripts ending on _dup# are "
"removed. This is necessary to remove duplicate entries "
"that are next to each other in the sort order "
"[%default]")
parser.add_option("--rename-duplicates",
dest="rename_duplicates",
action="store_true",
help="rename duplicate gene_ids and transcript_ids by "
"addition of a numerical suffix")
parser.set_defaults(
sort=None,
merge_exons=False,
join_exons=False,
merge_exons_distance=0,
merge_transcripts=False,
set_score2distance=False,
set_gene2transcript=False,
set_transcript2gene=False,
set_protein2transcript=False,
add_protein_id=None,
filename_filter=None,
filter=None,
exons2introns=None,
merge_genes=False,
intron_border=None,
intron_min_length=None,
sample_size=0,
min_exons_length=0,
transripts2genes=False,
reset_strand=False,
with_utr=False,
invert_filter=False,
remove_duplicates=None,
remove_overlapping=None,
renumber_genes=None,
unset_genes=None,
renumber_transcripts=None,
strict=True,
intersect_transcripts=False,
rename_duplicates=False,
)
(options, args) = E.Start(parser, argv=argv)
ninput, noutput, nfeatures, ndiscarded = 0, 0, 0, 0
if options.set_transcript2gene:
for gff in GTF.iterator(options.stdin):
ninput += 1
gff.setAttribute("transcript_id", gff.gene_id)
options.stdout.write("%s\n" % str(gff))
noutput += 1
nfeatures += 1
elif options.remove_duplicates:
counts = collections.defaultdict(int)
if options.remove_duplicates == "ucsc":
store = []
remove = set()
f = lambda x: x[0].transcript_id
gffs = GTF.transcript_iterator(GTF.iterator(options.stdin),
strict=False)
outf = lambda x: "\n".join([str(y) for y in x])
for entry in gffs:
ninput += 1
store.append(entry)
id = f(entry)
if "_dup" in id:
remove.add(re.sub("_dup\d+", "", id))
remove.add(id)
for entry in store:
id = f(entry)
if id not in remove:
options.stdout.write(outf(entry) + "\n")
noutput += 1
else:
ndiscarded += 1
E.info("discarded duplicates for %s" % (id))
else:
if options.remove_duplicates == "gene":
gffs = GTF.gene_iterator(GTF.iterator(options.stdin),
strict=False)
f = lambda x: x[0][0].gene_id
outf = lambda x: "\n".join(
["\n".join([str(y) for y in xx]) for xx in x])
elif options.remove_duplicates == "transcript":
gffs = GTF.transcript_iterator(GTF.iterator(options.stdin),
strict=False)
f = lambda x: x[0].transcript_id
outf = lambda x: "\n".join([str(y) for y in x])
elif options.remove_duplicates == "coordinates":
gffs = GTF.chunk_iterator(GTF.iterator(options.stdin))
f = lambda x: x[0].contig + "_" + \
str(x[0].start) + "-" + str(x[0].end)
outf = lambda x: "\n".join([str(y) for y in x])
store = []
for entry in gffs:
ninput += 1
store.append(entry)
id = f(entry)
counts[id] += 1
# Assumes GTF file sorted by contig then start
last_id = ""
if options.remove_duplicates == "coordinates":
for entry in store:
id = f(entry)
if id == last_id:
ndiscarded += 1
E.info("discarded duplicates for %s: %i" %
(id, counts[id]))
else:
options.stdout.write(outf(entry) + "\n")
noutput += 1
last_id = id
else:
for entry in store:
id = f(entry)
if counts[id] == 1:
options.stdout.write(outf(entry) + "\n")
noutput += 1
else:
ndiscarded += 1
E.info("discarded duplicates for %s: %i" %
(id, counts[id]))
elif options.sort:
for gff in GTF.iterator_sorted(GTF.iterator(options.stdin),
sort_order=options.sort):
ninput += 1
options.stdout.write("%s\n" % str(gff))
noutput += 1
nfeatures += 1
elif options.set_gene2transcript:
for gff in GTF.iterator(options.stdin):
ninput += 1
gff.setAttribute("gene_id", gff.transcript_id)
options.stdout.write("%s\n" % str(gff))
noutput += 1
nfeatures += 1
elif options.set_protein2transcript:
for gff in GTF.iterator(options.stdin):
ninput += 1
gff.setAttribute("protein_id", gff.transcript_id)
options.stdout.write("%s\n" % str(gff))
noutput += 1
nfeatures += 1
elif options.add_protein_id:
transcript2protein = IOTools.readMap(open(options.add_protein_id, "r"))
missing = set()
for gff in GTF.iterator(options.stdin):
ninput += 1
if gff.transcript_id not in transcript2protein:
if gff.transcript_id not in missing:
E.debug(("removing transcript '%s' due to "
"missing protein id") % gff.transcript_id)
missing.add(gff.transcript_id)
ndiscarded += 1
continue
gff.setAttribute("protein_id",
transcript2protein[gff.transcript_id])
options.stdout.write("%s\n" % str(gff))
noutput += 1
nfeatures += 1
E.info("transcripts removed due to missing protein ids: %i" %
len(missing))
elif options.join_exons:
for exons in GTF.transcript_iterator(GTF.iterator(options.stdin)):
ninput += 1
strand = Genomics.convertStrand(exons[0].strand)
contig = exons[0].contig
transid = exons[0].transcript_id
geneid = exons[0].gene_id
biotype = exons[0].source
all_start, all_end = min([x.start for x in exons
]), max([x.end for x in exons])
y = GTF.Entry()
y.contig = contig
y.source = biotype
y.feature = "transcript"
y.start = all_start
y.end = all_end
y.strand = strand
y.transcript_id = transid
y.gene_id = geneid
options.stdout.write("%s\n" % str(y))
elif options.merge_genes:
# merges overlapping genes
#
gffs = GTF.iterator_sorted_chunks(GTF.flat_gene_iterator(
GTF.iterator(options.stdin)),
sort_by="contig-strand-start")
def iterate_chunks(gff_chunks):
last = gff_chunks.next()
to_join = [last]
for gffs in gff_chunks:
d = gffs[0].start - last[-1].end
if gffs[0].contig == last[0].contig and \
gffs[0].strand == last[0].strand:
assert gffs[0].start >= last[0].start, \
("input file should be sorted by contig, strand "
"and position: d=%i:\nlast=\n%s\nthis=\n%s\n") % \
(d,
"\n".join([str(x) for x in last]),
"\n".join([str(x) for x in gffs]))
if gffs[0].contig != last[0].contig or \
gffs[0].strand != last[0].strand or \
d > 0:
yield to_join
to_join = []
last = gffs
to_join.append(gffs)
yield to_join
raise StopIteration
for chunks in iterate_chunks(gffs):
ninput += 1
if len(chunks) > 1:
gene_id = "merged_%s" % chunks[0][0].gene_id
transcript_id = "merged_%s" % chunks[0][0].transcript_id
info = ",".join([x[0].gene_id for x in chunks])
else:
gene_id = chunks[0][0].gene_id
transcript_id = chunks[0][0].transcript_id
info = None
intervals = []
for c in chunks:
intervals += [(x.start, x.end) for x in c]
intervals = Intervals.combine(intervals)
# take single strand
strand = chunks[0][0].strand
for start, end in intervals:
y = GTF.Entry()
y.fromGTF(chunks[0][0], gene_id, transcript_id)
y.start = start
y.end = end
y.strand = strand
if info:
y.addAttribute("merged", info)
options.stdout.write("%s\n" % str(y))
nfeatures += 1
noutput += 1
elif options.renumber_genes:
map_old2new = {}
for gtf in GTF.iterator(options.stdin):
ninput += 1
if gtf.gene_id not in map_old2new:
map_old2new[gtf.gene_id] = options.renumber_genes % (
len(map_old2new) + 1)
gtf.setAttribute("gene_id", map_old2new[gtf.gene_id])
options.stdout.write("%s\n" % str(gtf))
noutput += 1
elif options.unset_genes:
map_old2new = {}
for gtf in GTF.iterator(options.stdin):
ninput += 1
key = gtf.transcript_id
if key not in map_old2new:
map_old2new[key] = options.unset_genes % (len(map_old2new) + 1)
gtf.setAttribute("gene_id", map_old2new[key])
options.stdout.write("%s\n" % str(gtf))
noutput += 1
elif options.renumber_transcripts:
map_old2new = {}
for gtf in GTF.iterator(options.stdin):
ninput += 1
key = (gtf.gene_id, gtf.transcript_id)
if key not in map_old2new:
map_old2new[key] = options.renumber_transcripts % (
len(map_old2new) + 1)
gtf.setAttribute("transcript_id", map_old2new[key])
options.stdout.write("%s\n" % str(gtf))
noutput += 1
elif options.transcripts2genes:
transcripts = set()
genes = set()
reset_strand = options.reset_strand
for gtfs in GTF.iterator_transcripts2genes(GTF.iterator(
options.stdin)):
ninput += 1
for gtf in gtfs:
if reset_strand:
gtf.strand = "."
options.stdout.write("%s\n" % str(gtf))
transcripts.add(gtf.transcript_id)
genes.add(gtf.gene_id)
nfeatures += 1
noutput += 1
E.info("transcripts2genes: transcripts=%i, genes=%i" %
(len(transcripts), len(genes)))
elif options.rename:
map_old2new = IOTools.readMap(open(options.filename_filter, "r"))
if options.rename == "transcript":
is_gene_id = False
elif options.rename == "gene":
is_gene_id = True
for gff in GTF.iterator(options.stdin):
ninput += 1
if is_gene_id:
if gff.gene_id in map_old2new:
gff.setAttribute("gene_id", map_old2new[gff.gene_id])
else:
E.debug("removing missing gene_id %s" % gff.gene_id)
ndiscarded += 1
continue
else:
if gff.transcript_id in map_old2new:
gff.setAttribute("transcript_id",
map_old2new[gff.transcript_id])
else:
E.debug("removing missing transcript_id %s" %
gff.transcript_id)
ndiscarded += 1
continue
noutput += 1
options.stdout.write("%s\n" % str(gff))
elif options.filter:
keep_genes = set()
if options.filter == "longest-gene":
iterator = GTF.flat_gene_iterator(GTF.iterator(options.stdin))
coords = []
gffs = []
for gff in iterator:
gff.sort(key=lambda x: x.start)
coords.append((gff[0].contig, min([x.start for x in gff]),
max([x.end for x in gff]), gff[0].gene_id))
gffs.append(gff)
coords.sort()
last_contig = None
max_end = 0
longest_gene_id = None
longest_length = None
for contig, start, end, gene_id in coords:
ninput += 1
if contig != last_contig or start >= max_end:
if longest_gene_id:
keep_genes.add(longest_gene_id)
longest_gene_id = gene_id
longest_length = end - start
max_end = end
else:
if end - start > longest_length:
longest_length, longest_gene_id = end - start, gene_id
last_contig = contig
max_end = max(max_end, end)
keep_genes.add(longest_gene_id)
invert = options.invert_filter
for gff in gffs:
keep = gff[0].gene_id in keep_genes
if (keep and not invert) or (not keep and invert):
noutput += 1
for g in gff:
nfeatures += 1
options.stdout.write("%s\n" % g)
else:
ndiscarded += 1
elif options.filter in ("longest-transcript",
"representative-transcript"):
iterator = GTF.gene_iterator(GTF.iterator(options.stdin))
def selectLongestTranscript(gene):
r = []
for transcript in gene:
transcript.sort(key=lambda x: x.start)
length = transcript[-1].end - transcript[0].start
r.append((length, transcript))
r.sort()
return r[-1][1]
def selectRepresentativeTranscript(gene):
'''select a representative transcript.
The representative transcript represent the largest number
of exons over all transcripts.
'''
all_exons = []
for transcript in gene:
all_exons.extend([(x.start, x.end) for x in transcript
if x.feature == "exon"])
exon_counts = {}
for key, exons in itertools.groupby(all_exons):
exon_counts[key] = len(list(exons))
transcript_counts = []
for transcript in gene:
count = sum([
exon_counts[(x.start, x.end)] for x in transcript
if x.feature == "exon"
])
transcript_counts.append((count, transcript))
transcript_counts.sort()
return transcript_counts[-1][1]
if options.filter == "longest-transcript":
_select = selectLongestTranscript
elif options.filter == "representative-transcript":
_select = selectRepresentativeTranscript
for gene in iterator:
ninput += 1
# sort in order to make reproducible which
# gene is chosen.
transcript = _select(sorted(gene))
noutput += 1
for g in transcript:
nfeatures += 1
options.stdout.write("%s\n" % g)
elif options.filter in ("gene", "transcript"):
if options.filename_filter:
ids, nerrors = IOTools.ReadList(
open(options.filename_filter, "r"))
E.info("read %i ids" % len(ids))
ids = set(ids)
by_gene = options.filter == "gene"
by_transcript = options.filter == "transcript"
invert = options.invert_filter
reset_strand = options.reset_strand
for gff in GTF.iterator(options.stdin):
ninput += 1
keep = False
if by_gene:
keep = gff.gene_id in ids
if by_transcript:
keep = gff.transcript_id in ids
if (invert and keep) or (not invert and not keep):
continue
if reset_strand:
gff.strand = "."
options.stdout.write("%s\n" % str(gff))
nfeatures += 1
noutput += 1
elif options.sample_size:
if options.filter == "gene":
iterator = GTF.flat_gene_iterator(
GTF.iterator(options.stdin))
elif options.filter == "transcript":
iterator = GTF.transcript_iterator(
GTF.iterator(options.stdin))
if options.min_exons_length:
iterator = GTF.iterator_min_feature_length(
iterator,
min_length=options.min_exons_length,
feature="exon")
data = [x for x in iterator]
ninput = len(data)
if len(data) > options.sample_size:
data = random.sample(data, options.sample_size)
for d in data:
noutput += 1
for dd in d:
nfeatures += 1
options.stdout.write(str(dd) + "\n")
else:
assert False, "please supply either a filename "
"with ids to filter with (--apply) or a sample-size."
elif options.exons2introns:
for gffs in GTF.flat_gene_iterator(GTF.iterator(options.stdin)):
ninput += 1
cds_ranges = GTF.asRanges(gffs, "CDS")
exon_ranges = GTF.asRanges(gffs, "exon")
input_ranges = Intervals.combine(cds_ranges + exon_ranges)
if len(input_ranges) > 1:
last = input_ranges[0][1]
output_ranges = []
for start, end in input_ranges[1:]:
output_ranges.append((last, start))
last = end
if options.intron_border:
b = options.intron_border
output_ranges = [(x[0] + b, x[1] - b)
for x in output_ranges]
if options.intron_min_length:
l = options.intron_min_length
output_ranges = [
x for x in output_ranges if x[1] - x[0] > l
]
for start, end in output_ranges:
entry = GTF.Entry()
entry.copy(gffs[0])
entry.clearAttributes()
entry.transcript_id = "merged"
entry.feature = "intron"
entry.start = start
entry.end = end
options.stdout.write("%s\n" % str(entry))
nfeatures += 1
noutput += 1
else:
ndiscarded += 1
elif options.set_score2distance:
for gffs in GTF.transcript_iterator(GTF.iterator(options.stdin)):
ninput += 1
strand = Genomics.convertStrand(gffs[0].strand)
all_start, all_end = min([x.start for x in gffs
]), max([x.end for x in gffs])
if strand != ".":
t = 0
if strand == "-":
gffs.reverse()
for gff in gffs:
gff.score = t
t += gff.end - gff.start
if strand == "-":
gffs.reverse()
for gff in gffs:
options.stdout.write("%s\n" % str(gff))
nfeatures += 1
noutput += 1
elif options.remove_overlapping:
index = GTF.readAndIndex(
GTF.iterator(IOTools.openFile(options.remove_overlapping, "r")))
for gffs in GTF.transcript_iterator(GTF.iterator(options.stdin)):
ninput += 1
found = False
for e in gffs:
if index.contains(e.contig, e.start, e.end):
found = True
break
if found:
ndiscarded += 1
else:
noutput += 1
for e in gffs:
nfeatures += 1
options.stdout.write("%s\n" % str(e))
elif options.intersect_transcripts:
for gffs in GTF.gene_iterator(GTF.iterator(options.stdin),
strict=options.strict):
ninput += 1
r = []
for g in gffs:
if options.with_utr:
ranges = GTF.asRanges(g, "exon")
else:
ranges = GTF.asRanges(g, "CDS")
r.append(ranges)
result = r[0]
for x in r[1:]:
result = Intervals.intersect(result, x)
entry = GTF.Entry()
entry.copy(gffs[0][0])
entry.clearAttributes()
entry.transcript_id = "merged"
entry.feature = "exon"
for start, end in result:
entry.start = start
entry.end = end
options.stdout.write("%s\n" % str(entry))
nfeatures += 1
noutput += 1
elif options.rename_duplicates:
gene_ids = list()
transcript_ids = list()
gtfs = list()
for gtf in GTF.iterator(options.stdin):
gtfs.append(gtf)
if gtf.feature == "CDS":
gene_ids.append(gtf.gene_id)
transcript_ids.append(gtf.transcript_id)
dup_gene = [item for item in set(gene_ids) if gene_ids.count(item) > 1]
dup_transcript = [
item for item in set(transcript_ids)
if transcript_ids.count(item) > 1
]
E.info("Number of duplicated gene_ids: %i" % len(dup_gene))
E.info("Number of duplicated transcript_ids: %i" % len(dup_transcript))
gene_dict = dict(zip(dup_gene, ([0] * len(dup_gene))))
transcript_dict = dict(zip(dup_transcript,
([0] * len(dup_transcript))))
for gtf in gtfs:
if gtf.feature == "CDS":
if gtf.gene_id in dup_gene:
gene_dict[gtf.gene_id] = gene_dict[gtf.gene_id] + 1
gtf.setAttribute(
'gene_id',
gtf.gene_id + "." + str(gene_dict[gtf.gene_id]))
if gtf.transcript_id in dup_transcript:
transcript_dict[gtf.transcript_id] = \
transcript_dict[gtf.transcript_id] + 1
gtf.setAttribute(
'transcript_id', gtf.transcript_id + "." +
str(transcript_dict[gtf.transcript_id]))
options.stdout.write("%s\n" % gtf)
else:
for gffs in GTF.flat_gene_iterator(GTF.iterator(options.stdin),
strict=options.strict):
ninput += 1
cds_ranges = GTF.asRanges(gffs, "CDS")
exon_ranges = GTF.asRanges(gffs, "exon")
# sanity checks
strands = set([x.strand for x in gffs])
contigs = set([x.contig for x in gffs])
if len(strands) > 1:
raise ValueError(
"can not merge gene '%s' on multiple strands: %s" %
(gffs[0].gene_id, str(strands)))
if len(contigs) > 1:
raise ValueError(
"can not merge gene '%s' on multiple contigs: %s" %
(gffs[0].gene_id, str(contigs)))
strand = Genomics.convertStrand(gffs[0].strand)
if cds_ranges and options.with_utr:
cds_start, cds_end = cds_ranges[0][0], cds_ranges[-1][1]
midpoint = (cds_end - cds_start) / 2 + cds_start
utr_ranges = []
for start, end in Intervals.truncate(exon_ranges, cds_ranges):
if end - start > 3:
if strand == ".":
feature = "UTR"
elif strand == "+":
if start < midpoint:
feature = "UTR5"
else:
feature = "UTR3"
elif strand == "-":
if start < midpoint:
feature = "UTR3"
else:
feature = "UTR5"
utr_ranges.append((feature, start, end))
output_feature = "CDS"
output_ranges = cds_ranges
else:
output_feature = "exon"
output_ranges = exon_ranges
utr_ranges = []
result = []
if options.merge_exons:
# need to combine per feature - skip
# utr_ranges = Intervals.combineAtDistance(
# utr_ranges,
# options.merge_exons_distance)
output_ranges = Intervals.combineAtDistance(
output_ranges, options.merge_exons_distance)
for feature, start, end in utr_ranges:
entry = GTF.Entry()
entry.copy(gffs[0])
entry.clearAttributes()
entry.feature = feature
entry.transcript_id = "merged"
entry.start = start
entry.end = end
result.append(entry)
for start, end in output_ranges:
entry = GTF.Entry()
entry.copy(gffs[0])
entry.clearAttributes()
entry.transcript_id = "merged"
entry.feature = output_feature
entry.start = start
entry.end = end
result.append(entry)
elif options.merge_transcripts:
entry = GTF.Entry()
entry.copy(gffs[0])
entry.clearAttributes()
entry.transcript_id = entry.gene_id
entry.start = output_ranges[0][0]
entry.end = output_ranges[-1][1]
result.append(entry)
elif options.merge_introns:
if len(output_ranges) >= 2:
entry = GTF.Entry()
entry.copy(gffs[0])
entry.clearAttributes()
entry.transcript_id = entry.gene_id
entry.start = output_ranges[0][1]
entry.end = output_ranges[-1][0]
result.append(entry)
else:
ndiscarded += 1
continue
result.sort(key=lambda x: x.start)
for x in result:
options.stdout.write("%s\n" % str(x))
nfeatures += 1
noutput += 1
E.info("ninput=%i, noutput=%i, nfeatures=%i, ndiscarded=%i" %
(ninput, noutput, nfeatures, ndiscarded))
E.Stop()
def main( argv = None ):
"""script main.
parses command line options in sys.argv, unless *argv* is given.
"""
if argv == None: argv = sys.argv
parser = E.OptionParser( version = "%prog version: $Id: peptides2cds.py 2890 2010-04-07 08:58:54Z andreas $")
parser.add_option("-p", "--peptides", dest="filename_peptides", type="string",
help="filename with peptide sequences [%default]." )
parser.add_option("-c", "--cds", "--cdnas", dest="filename_cdna", type="string",
help="filename with cdna sequences [%default]." )
parser.add_option("-m", "--map", dest="filename_map", type="string",
help="filename with map of peptide identifiers to cdna identifiers [%default]." )
parser.add_option( "--output-identifier", dest="output_identifier", type="choice",
choices=("cdna", "peptide"),
help="output identifier to use [%default]." )
parser.add_option("-f", "--output-format=", dest="output_format", type="choice",
choices=("alignment", "fasta"),
help="output format.")
parser.set_defaults(
peptides=None,
filename_cdna = None,
output_format="alignment",
filename_map = None,
stop_codons = ("TAG", "TAA", "TGA"),
output_identifier = "peptide",
)
(options, args) = E.Start( parser, add_pipe_options = True )
if not options.filename_cdna:
raise ValueError("please supply filename with cds sequences.")
if options.filename_peptides:
infile = open(options.filename_peptides, "r")
E.info("reading from %s" % options.filename_peptides)
else:
E.info("reading from stdin")
infile = sys.stdin
if options.filename_map:
E.info( "reading map" )
map_peptide2cds = IOTools.readMap( IOTools.openFile( options.filename_map, "r" ) )
E.info( "read map for %i identifiers" % len(map_peptide2cds) )
else:
map_peptide2cds = {}
E.info( "reading cds sequences" )
cds_sequences = Genomics.ReadPeptideSequences( IOTools.openFile(options.filename_cdna, "r") )
E.info( "read %i cds sequences" % len(cds_sequences))
ninput, noutput = 0, 0
nskipped, nnosequence = 0, 0
# iterate over peptide sequences
iterator = FastaIterator.FastaIterator( infile )
use_cds_id = options.output_identifier == "cds"
for cur_record in iterator:
ninput += 1
peptide_identifier = re.split("\s+", cur_record.title)[0]
cds_identifier = map_peptide2cds.get( peptide_identifier, peptide_identifier )
if cds_identifier not in cds_sequences:
nnosequence += 1
continue
p = cur_record.sequence
c = cds_sequences[cds_identifier]
E.debug("processing %s: laa=%i (without gaps=%i), lna=%i" % (peptide_identifier, len(p), len(re.sub("-", "", p)), len(c)))
try:
map_p2c = getMapPeptide2Cds( p, c, options )
except ValueError:
nskipped += 1
continue
if use_cds_id:
identifier = cds_identifier
else:
identifier = peptide_identifier
if options.output_format =="alignment":
options.stdout.write("\t".join( map(str, (identifier, alignlib_lite.py_AlignmentFormatEmissions( map_p2c ),
len(cur_record.sequence), len(cds_sequences[identifier])) ) )+"\n")
elif options.output_format == "fasta":
map_p2c.switchRowCol()
alignatum = alignlib_lite.py_makeAlignatum( c )
alignatum.mapOnAlignment( map_p2c, len(p) * 3 )
s = alignatum.getString()
if len(s) != len(p) * 3:
raise ValueError ("incomplete aligned string for %s: %s, cds=%s" % (cur_record.title, s, c ))
options.stdout.write( ">%s\n%s\n" % (identifier, s ))
noutput += 1
sys.stdout.flush()
E.info( "ninput=%i, noutput=%i, nnosequence=%i, nskipped=%i" % (ninput, noutput, nnosequence, nskipped) )
E.Stop()
def main(argv=None):
"""script main.
parses command line options in sys.argv, unless *argv* is given.
"""
if not argv:
argv = sys.argv
# setup command line parser
parser = E.OptionParser(version="%prog version: $Id$",
usage=globals()["__doc__"])
parser.add_option(
"-g", "--gtf-file", dest="filename_gtf", type="string",
help="filename with gene models in gtf format [%default]")
parser.add_option(
"-m", "--filename-mismapped", dest="filename_mismapped", type="string",
help="output bam file for mismapped reads [%default]")
parser.add_option(
"-j", "--junctions-bed-file", dest="filename_junctions", type="string",
help="bam file with reads mapped across junctions [%default]")
parser.add_option(
"-r", "--filename-regions", dest="filename_regions", type="string",
help="filename with regions to remove in bed format [%default]")
parser.add_option(
"-t", "--transcripts-gtf-file", dest="filename_transcriptome",
type="string",
help="bam file with reads mapped against transcripts [%default]")
parser.add_option(
"-p", "--map-tsv-file", dest="filename_map", type="string",
help="filename mapping transcript numbers (used by "
"--filename-transciptome) to transcript names "
"(used by --filename-gtf) [%default]")
parser.add_option(
"-s", "--filename-stats", dest="filename_stats", type="string",
help="filename to output stats to [%default]")
parser.add_option(
"-o", "--colour",
dest="colour_mismatches", action="store_true",
help="mismatches will use colour differences (CM tag) [%default]")
parser.add_option(
"-i", "--ignore-mismatches",
dest="ignore_mismatches", action="store_true",
help="ignore mismatches [%default]")
parser.add_option(
"-c", "--remove-contigs", dest="remove_contigs", type="string",
help="','-separated list of contigs to remove [%default]")
parser.add_option(
"-f", "--force-output", dest="force", action="store_true",
help="force overwriting of existing files [%default]")
parser.add_option("-u", "--unique", dest="unique", action="store_true",
help="remove reads not matching uniquely [%default]")
parser.add_option("--output-sam", dest="output_sam", action="store_true",
help="output in sam format [%default]")
parser.set_defaults(
filename_gtf=None,
filename_mismapped=None,
filename_junctions=None,
filename_transcriptome=None,
filename_map=None,
remove_contigs=None,
force=False,
unique=False,
colour_mismatches=False,
ignore_mismatches=False,
output_sam=False,
filename_table=None,
)
# add common options (-h/--help, ...) and parse command line
(options, args) = E.Start(parser, argv=argv)
if len(args) != 1:
raise ValueError("please supply one bam file")
bamfile_genome = args[0]
genome_samfile = pysam.Samfile(bamfile_genome, "rb")
if options.remove_contigs:
options.remove_contigs = options.remove_contigs.split(",")
if options.filename_map:
E.info("reading map")
id_map = IOTools.readMap(
IOTools.openFile(options.filename_map), has_header=True)
id_map = dict([(y, x) for x, y in id_map.iteritems()])
else:
id_map = None
transcripts = {}
if options.filename_gtf:
E.info("indexing geneset")
mapped, missed = 0, 0
for gtf in GTF.transcript_iterator(
GTF.iterator(IOTools.openFile(options.filename_gtf))):
gtf.sort(key=lambda x: x.start)
transcript_id = gtf[0].transcript_id
if id_map:
try:
transcript_id = id_map[transcript_id]
mapped += 1
except KeyError:
missed += 1
continue
transcripts[transcript_id] = gtf
E.info("read %i transcripts from geneset (%i mapped, %i missed)" %
(len(transcripts), mapped, missed))
regions_to_remove = None
if options.filename_regions:
E.info("indexing regions")
regions_to_remove = IndexedGenome.Simple()
for bed in Bed.iterator(IOTools.openFile(options.filename_regions)):
regions_to_remove.add(bed.contig, bed.start, bed.end)
E.info("read %i regions" % len(regions_to_remove))
if options.filename_transcriptome:
transcripts_samfile = pysam.Samfile(options.filename_transcriptome,
"rb")
else:
transcripts_samfile = None
if options.output_sam:
output_samfile = pysam.Samfile("-", "wh", template=genome_samfile)
else:
output_samfile = pysam.Samfile("-", "wb", template=genome_samfile)
if options.filename_mismapped:
if not options.force and os.path.exists(options.filename_mismapped):
raise IOError("output file %s already exists" %
options.filename_mismapped)
output_mismapped = pysam.Samfile(options.filename_mismapped,
"wb",
template=genome_samfile)
else:
output_mismapped = None
if options.filename_junctions:
junctions_samfile = pysam.Samfile(options.filename_junctions,
"rb")
else:
junctions_samfile = None
c = _bams2bam.filter(genome_samfile,
output_samfile,
output_mismapped,
transcripts_samfile,
junctions_samfile,
transcripts,
regions=regions_to_remove,
unique=options.unique,
remove_contigs=options.remove_contigs,
colour_mismatches=options.colour_mismatches,
ignore_mismatches=options.ignore_mismatches,
ignore_transcripts=transcripts_samfile is None,
ignore_junctions=junctions_samfile is None)
if options.filename_stats:
outf = IOTools.openFile(options.filename_stats, "w")
outf.write("category\tcounts\n%s\n" % c.asTable())
outf.close()
if options.filename_transcriptome:
transcripts_samfile.close()
genome_samfile.close()
output_samfile.close()
if output_mismapped:
output_mismapped.close()
# write footer and output benchmark information.
E.Stop()
def main(argv=None):
if not argv:
argv = sys.argv
parser = E.OptionParser(version="%prog version: $Id$", usage=globals()["__doc__"])
parser.add_option(
"--merge-exons-distance",
dest="merge_exons_distance",
type="int",
help="distance in nucleotides between " "exons to be merged [%default].",
)
parser.add_option(
"--pattern-identifier",
dest="pattern",
type="string",
help="pattern to use for renaming genes/transcripts. "
"The pattern should contain a %i, for example "
"--pattern-identifier=ENSG%010i [%default].",
)
parser.add_option(
"--sort-order",
dest="sort_order",
type="choice",
choices=("gene", "gene+transcript", "transcript", "position", "contig+gene", "position+gene", "gene+position"),
help="sort input data [%default].",
)
parser.add_option(
"-u",
"--with-utr",
dest="with_utr",
action="store_true",
help="include utr in merged transcripts " "[%default].",
)
parser.add_option(
"--filter-method",
dest="filter_method",
type="choice",
choices=(
"gene",
"transcript",
"longest-gene",
"longest-transcript",
"representative-transcript",
"proteincoding",
"lincrna",
),
help="Filter method to apply. Available filters are: "
"'gene': filter by gene_id given in ``--map-tsv-file``, "
"'transcript': filter by transcript_id given in ``--map-tsv-file``, "
"'longest-gene': output the longest gene for overlapping genes ,"
"'longest-transcript': output the longest transcript per gene,"
"'representative-transcript': output the representative transcript "
"per gene. The representative transcript is the transcript "
"that shares most exons with other transcripts in a gene. "
"The input needs to be sorted by gene. "
"'proteincoding': only output protein coding features. "
"'lincrna': only output lincRNA features. "
"[%default].",
)
parser.add_option(
"-a",
"--map-tsv-file",
dest="filename_filter",
type="string",
metavar="tsv",
help="filename of ids to map/filter [%default].",
)
parser.add_option(
"--gff-file",
dest="filename_gff",
type="string",
metavar="GFF",
help="second filename of features (see --remove-overlapping) " "[%default]",
)
parser.add_option(
"--invert-filter",
dest="invert_filter",
action="store_true",
help="when using --filter, invert selection " "(like grep -v). " "[%default].",
)
parser.add_option(
"--sample-size",
dest="sample_size",
type="int",
help="extract a random sample of size # if the option "
"'--method=filter --filter-method' is set "
"[%default].",
)
parser.add_option(
"--intron-min-length",
dest="intron_min_length",
type="int",
help="minimum length for introns (for --exons-file2introns) " "[%default].",
)
parser.add_option(
"--min-exons-length",
dest="min_exons_length",
type="int",
help="minimum length for gene (sum of exons) " "(--sam-fileple-size) [%default].",
)
parser.add_option(
"--intron-border",
dest="intron_border",
type="int",
help="number of residues to exclude at intron at either end " "(--exons-file2introns) [%default].",
)
parser.add_option(
"--ignore-strand",
dest="ignore_strand",
action="store_true",
help="remove strandedness of features (set to '.') when "
"using ``transcripts2genes`` or ``filter``"
"[%default].",
)
parser.add_option(
"--permit-duplicates", dest="strict", action="store_false", help="permit duplicate genes. " "[%default]"
)
parser.add_option(
"--duplicate-feature",
dest="duplicate_feature",
type="choice",
choices=("gene", "transcript", "both", "ucsc", "coordinates"),
help="remove duplicates by gene/transcript. "
"If ``ucsc`` is chosen, transcripts ending on _dup# are "
"removed. This is necessary to remove duplicate entries "
"that are next to each other in the sort order "
"[%default]",
)
parser.add_option(
"-m",
"--method",
dest="method",
type="choice",
action="append",
choices=(
"add-protein-id",
"exons2introns",
"filter",
"find-retained-introns",
"genes-to-unique-chunks",
"intersect-transcripts",
"join-exons",
"merge-exons",
"merge-transcripts",
"merge-genes",
"merge-introns",
"remove-overlapping",
"remove-duplicates",
"rename-genes",
"rename-transcripts",
"rename-duplicates",
"renumber-genes",
"renumber-transcripts",
"set-transcript-to-gene",
"set-gene-to-transcript",
"set-protein-to-transcript",
"set-score-to-distance",
"set-gene_biotype-to-source",
"sort",
"transcript2genes",
"unset-genes",
),
help="Method to apply [%default]." "Please only select one.",
)
parser.set_defaults(
sort_order="gene",
filter_method="gene",
pattern="%i",
merge_exons_distance=0,
filename_filter=None,
intron_border=None,
intron_min_length=None,
sample_size=0,
min_exons_length=0,
ignore_strand=False,
with_utr=False,
invert_filter=False,
duplicate_feature=None,
strict=True,
method=None,
)
(options, args) = E.Start(parser, argv=argv)
ninput, noutput, nfeatures, ndiscarded = 0, 0, 0, 0
if options.method is None:
raise ValueError("please specify a --method")
if len(options.method) > 1:
raise ValueError("multiple --method arguements specified")
else:
options.method = options.method[0]
if options.method == "set-transcript-to-gene":
for gff in GTF.iterator(options.stdin):
ninput += 1
gff.setAttribute("transcript_id", gff.gene_id)
options.stdout.write("%s\n" % str(gff))
noutput += 1
nfeatures += 1
elif options.method == "set-gene_biotype-to-source":
for gff in GTF.iterator(options.stdin):
ninput += 1
if "gene_biotype" not in gff:
gff.setAttribute("gene_biotype", gff.source)
options.stdout.write("%s\n" % str(gff))
noutput += 1
nfeatures += 1
elif options.method == "remove-duplicates":
counts = collections.defaultdict(int)
if options.duplicate_feature == "ucsc":
store = []
remove = set()
f = lambda x: x[0].transcript_id
gffs = GTF.transcript_iterator(GTF.iterator(options.stdin), strict=False)
outf = lambda x: "\n".join([str(y) for y in x])
for entry in gffs:
ninput += 1
store.append(entry)
id = f(entry)
if "_dup" in id:
remove.add(re.sub("_dup\d+", "", id))
remove.add(id)
for entry in store:
id = f(entry)
if id not in remove:
options.stdout.write(outf(entry) + "\n")
noutput += 1
else:
ndiscarded += 1
E.info("discarded duplicates for %s" % (id))
else:
if options.duplicate_feature == "gene":
gffs = GTF.gene_iterator(GTF.iterator(options.stdin), strict=False)
f = lambda x: x[0][0].gene_id
outf = lambda x: "\n".join(["\n".join([str(y) for y in xx]) for xx in x])
elif options.duplicate_feature == "transcript":
gffs = GTF.transcript_iterator(GTF.iterator(options.stdin), strict=False)
f = lambda x: x[0].transcript_id
outf = lambda x: "\n".join([str(y) for y in x])
elif options.duplicate_feature == "coordinates":
gffs = GTF.chunk_iterator(GTF.iterator(options.stdin))
f = lambda x: x[0].contig + "_" + str(x[0].start) + "-" + str(x[0].end)
outf = lambda x: "\n".join([str(y) for y in x])
store = []
for entry in gffs:
ninput += 1
store.append(entry)
id = f(entry)
counts[id] += 1
# Assumes GTF file sorted by contig then start
last_id = ""
if options.duplicate_feature == "coordinates":
for entry in store:
id = f(entry)
if id == last_id:
ndiscarded += 1
E.info("discarded duplicates for %s: %i" % (id, counts[id]))
else:
options.stdout.write(outf(entry) + "\n")
noutput += 1
last_id = id
else:
for entry in store:
id = f(entry)
if counts[id] == 1:
options.stdout.write(outf(entry) + "\n")
noutput += 1
else:
ndiscarded += 1
E.info("discarded duplicates for %s: %i" % (id, counts[id]))
elif "sort" == options.method:
for gff in GTF.iterator_sorted(GTF.iterator(options.stdin), sort_order=options.sort_order):
ninput += 1
options.stdout.write("%s\n" % str(gff))
noutput += 1
nfeatures += 1
elif "set-gene-to-transcript" == options.method:
for gff in GTF.iterator(options.stdin):
ninput += 1
gff.setAttribute("gene_id", gff.transcript_id)
options.stdout.write("%s\n" % str(gff))
noutput += 1
nfeatures += 1
elif "set-protein-to-transcript" == options.method:
for gff in GTF.iterator(options.stdin):
ninput += 1
gff.setAttribute("protein_id", gff.transcript_id)
options.stdout.write("%s\n" % str(gff))
noutput += 1
nfeatures += 1
elif "add-protein-id" == options.method:
transcript2protein = IOTools.readMap(IOTools.openFile(options.filename_filter, "r"))
missing = set()
for gff in GTF.iterator(options.stdin):
ninput += 1
if gff.transcript_id not in transcript2protein:
if gff.transcript_id not in missing:
E.debug(("removing transcript '%s' due to " "missing protein id") % gff.transcript_id)
missing.add(gff.transcript_id)
ndiscarded += 1
continue
gff.setAttribute("protein_id", transcript2protein[gff.transcript_id])
options.stdout.write("%s\n" % str(gff))
noutput += 1
nfeatures += 1
E.info("transcripts removed due to missing protein ids: %i" % len(missing))
elif "join-exons" == options.method:
for exons in GTF.transcript_iterator(GTF.iterator(options.stdin)):
ninput += 1
strand = Genomics.convertStrand(exons[0].strand)
contig = exons[0].contig
transid = exons[0].transcript_id
geneid = exons[0].gene_id
biotype = exons[0].source
all_start, all_end = min([x.start for x in exons]), max([x.end for x in exons])
y = GTF.Entry()
y.contig = contig
y.source = biotype
y.feature = "transcript"
y.start = all_start
y.end = all_end
y.strand = strand
y.transcript_id = transid
y.gene_id = geneid
options.stdout.write("%s\n" % str(y))
elif "merge-genes" == options.method:
# merges overlapping genes
#
gffs = GTF.iterator_sorted_chunks(
GTF.flat_gene_iterator(GTF.iterator(options.stdin)), sort_by="contig-strand-start"
)
def iterate_chunks(gff_chunks):
last = gff_chunks.next()
to_join = [last]
for gffs in gff_chunks:
d = gffs[0].start - last[-1].end
if gffs[0].contig == last[0].contig and gffs[0].strand == last[0].strand:
assert gffs[0].start >= last[0].start, (
"input file should be sorted by contig, strand " "and position: d=%i:\nlast=\n%s\nthis=\n%s\n"
) % (d, "\n".join([str(x) for x in last]), "\n".join([str(x) for x in gffs]))
if gffs[0].contig != last[0].contig or gffs[0].strand != last[0].strand or d > 0:
yield to_join
to_join = []
last = gffs
to_join.append(gffs)
yield to_join
raise StopIteration
for chunks in iterate_chunks(gffs):
ninput += 1
if len(chunks) > 1:
gene_id = "merged_%s" % chunks[0][0].gene_id
transcript_id = "merged_%s" % chunks[0][0].transcript_id
info = ",".join([x[0].gene_id for x in chunks])
else:
gene_id = chunks[0][0].gene_id
transcript_id = chunks[0][0].transcript_id
info = None
intervals = []
for c in chunks:
intervals += [(x.start, x.end) for x in c]
intervals = Intervals.combine(intervals)
# take single strand
strand = chunks[0][0].strand
for start, end in intervals:
y = GTF.Entry()
y.fromGTF(chunks[0][0], gene_id, transcript_id)
y.start = start
y.end = end
y.strand = strand
if info:
y.addAttribute("merged", info)
options.stdout.write("%s\n" % str(y))
nfeatures += 1
noutput += 1
elif options.method == "renumber-genes":
map_old2new = {}
for gtf in GTF.iterator(options.stdin):
ninput += 1
if gtf.gene_id not in map_old2new:
map_old2new[gtf.gene_id] = options.pattern % (len(map_old2new) + 1)
gtf.setAttribute("gene_id", map_old2new[gtf.gene_id])
options.stdout.write("%s\n" % str(gtf))
noutput += 1
elif options.method == "unset-genes":
map_old2new = {}
for gtf in GTF.iterator(options.stdin):
ninput += 1
key = gtf.transcript_id
if key not in map_old2new:
map_old2new[key] = options.pattern % (len(map_old2new) + 1)
gtf.setAttribute("gene_id", map_old2new[key])
options.stdout.write("%s\n" % str(gtf))
noutput += 1
elif options.method == "renumber-transcripts":
map_old2new = {}
for gtf in GTF.iterator(options.stdin):
ninput += 1
key = (gtf.gene_id, gtf.transcript_id)
if key not in map_old2new:
map_old2new[key] = options.pattern % (len(map_old2new) + 1)
gtf.setAttribute("transcript_id", map_old2new[key])
options.stdout.write("%s\n" % str(gtf))
noutput += 1
elif options.method == "transcripts2genes":
transcripts = set()
genes = set()
ignore_strand = options.ignore_strand
for gtfs in GTF.iterator_transcripts2genes(GTF.iterator(options.stdin)):
ninput += 1
for gtf in gtfs:
if ignore_strand:
gtf.strand = "."
options.stdout.write("%s\n" % str(gtf))
transcripts.add(gtf.transcript_id)
genes.add(gtf.gene_id)
nfeatures += 1
noutput += 1
E.info("transcripts2genes: transcripts=%i, genes=%i" % (len(transcripts), len(genes)))
elif options.method in ("rename-genes", "rename-transcripts"):
map_old2new = IOTools.readMap(IOTools.openFile(options.filename_filter, "r"))
if options.method == "rename-transcripts":
is_gene_id = False
elif options.method == "rename-genes":
is_gene_id = True
for gff in GTF.iterator(options.stdin):
ninput += 1
if is_gene_id:
if gff.gene_id in map_old2new:
gff.setAttribute("gene_id", map_old2new[gff.gene_id])
else:
E.debug("removing missing gene_id %s" % gff.gene_id)
ndiscarded += 1
continue
else:
if gff.transcript_id in map_old2new:
gff.setAttribute("transcript_id", map_old2new[gff.transcript_id])
else:
E.debug("removing missing transcript_id %s" % gff.transcript_id)
ndiscarded += 1
continue
noutput += 1
options.stdout.write("%s\n" % str(gff))
elif options.method == "filter":
keep_genes = set()
if options.filter_method == "longest-gene":
iterator = GTF.flat_gene_iterator(GTF.iterator(options.stdin))
coords = []
gffs = []
for gff in iterator:
gff.sort(key=lambda x: x.start)
coords.append((gff[0].contig, min([x.start for x in gff]), max([x.end for x in gff]), gff[0].gene_id))
gffs.append(gff)
coords.sort()
last_contig = None
max_end = 0
longest_gene_id = None
longest_length = None
for contig, start, end, gene_id in coords:
ninput += 1
if contig != last_contig or start >= max_end:
if longest_gene_id:
keep_genes.add(longest_gene_id)
longest_gene_id = gene_id
longest_length = end - start
max_end = end
else:
if end - start > longest_length:
longest_length, longest_gene_id = end - start, gene_id
last_contig = contig
max_end = max(max_end, end)
keep_genes.add(longest_gene_id)
invert = options.invert_filter
for gff in gffs:
keep = gff[0].gene_id in keep_genes
if (keep and not invert) or (not keep and invert):
noutput += 1
for g in gff:
nfeatures += 1
options.stdout.write("%s\n" % g)
else:
ndiscarded += 1
elif options.filter_method in ("longest-transcript", "representative-transcript"):
iterator = GTF.gene_iterator(GTF.iterator(options.stdin))
def selectLongestTranscript(gene):
r = []
for transcript in gene:
transcript.sort(key=lambda x: x.start)
length = transcript[-1].end - transcript[0].start
r.append((length, transcript))
r.sort()
return r[-1][1]
def selectRepresentativeTranscript(gene):
"""select a representative transcript.
The representative transcript represent the largest number
of exons over all transcripts.
"""
all_exons = []
for transcript in gene:
all_exons.extend([(x.start, x.end) for x in transcript if x.feature == "exon"])
exon_counts = {}
for key, exons in itertools.groupby(all_exons):
exon_counts[key] = len(list(exons))
transcript_counts = []
for transcript in gene:
count = sum([exon_counts[(x.start, x.end)] for x in transcript if x.feature == "exon"])
# add transcript id to sort to provide a stable
# segmentation.
transcript_counts.append((count, transcript[0].transcript_id, transcript))
transcript_counts.sort()
return transcript_counts[-1][-1]
if options.filter_method == "longest-transcript":
_select = selectLongestTranscript
elif options.filter_method == "representative-transcript":
_select = selectRepresentativeTranscript
for gene in iterator:
ninput += 1
# sort in order to make reproducible which
# gene is chosen.
transcript = _select(sorted(gene))
noutput += 1
for g in transcript:
nfeatures += 1
options.stdout.write("%s\n" % g)
elif options.filter_method in ("gene", "transcript"):
if options.filename_filter:
ids, nerrors = IOTools.ReadList(IOTools.openFile(options.filename_filter, "r"))
E.info("read %i ids" % len(ids))
ids = set(ids)
by_gene = options.filter_method == "gene"
by_transcript = options.filter_method == "transcript"
invert = options.invert_filter
ignore_strand = options.ignore_strand
for gff in GTF.iterator(options.stdin):
ninput += 1
keep = False
if by_gene:
keep = gff.gene_id in ids
if by_transcript:
keep = gff.transcript_id in ids
if (invert and keep) or (not invert and not keep):
continue
if ignore_strand:
gff.strand = "."
options.stdout.write("%s\n" % str(gff))
nfeatures += 1
noutput += 1
elif options.sample_size:
if options.filter_method == "gene":
iterator = GTF.flat_gene_iterator(GTF.iterator(options.stdin))
elif options.filter_method == "transcript":
iterator = GTF.transcript_iterator(GTF.iterator(options.stdin))
if options.min_exons_length:
iterator = GTF.iterator_min_feature_length(
iterator, min_length=options.min_exons_length, feature="exon"
)
data = [x for x in iterator]
ninput = len(data)
if len(data) > options.sample_size:
data = random.sample(data, options.sample_size)
for d in data:
noutput += 1
for dd in d:
nfeatures += 1
options.stdout.write(str(dd) + "\n")
else:
assert False, "please supply either a filename "
"with ids to filter with (--map-tsv-file) or a sample-size."
elif options.filter_method in ("proteincoding", "lincrna", "processed-pseudogene"):
# extract entries by transcript/gene biotype.
# This filter uses a test on the source field (ENSEMBL pre v78)
# a regular expression on the attributes (ENSEMBL >= v78).
tag = {
"proteincoding": "protein_coding",
"processed-pseudogene": "processed_pseudogene",
"lincrna": "lincRNA",
}[options.filter_method]
rx = re.compile('"%s"' % tag)
if not options.invert_filter:
f = lambda x: x.source == tag or rx.search(x.attributes)
else:
f = lambda x: x.source != tag and not rx.search(x.attributes)
for gff in GTF.iterator(options.stdin):
ninput += 1
if f(gff):
options.stdout.write(str(gff) + "\n")
noutput += 1
else:
ndiscarded += 1
elif options.method == "exons2introns":
for gffs in GTF.flat_gene_iterator(GTF.iterator(options.stdin)):
ninput += 1
cds_ranges = GTF.asRanges(gffs, "CDS")
exon_ranges = GTF.asRanges(gffs, "exon")
input_ranges = Intervals.combine(cds_ranges + exon_ranges)
if len(input_ranges) > 1:
last = input_ranges[0][1]
output_ranges = []
for start, end in input_ranges[1:]:
output_ranges.append((last, start))
last = end
if options.intron_border:
b = options.intron_border
output_ranges = [(x[0] + b, x[1] - b) for x in output_ranges]
if options.intron_min_length:
l = options.intron_min_length
output_ranges = [x for x in output_ranges if x[1] - x[0] > l]
for start, end in output_ranges:
entry = GTF.Entry()
entry.copy(gffs[0])
entry.clearAttributes()
entry.transcript_id = "merged"
entry.feature = "intron"
entry.start = start
entry.end = end
options.stdout.write("%s\n" % str(entry))
nfeatures += 1
noutput += 1
else:
ndiscarded += 1
elif options.method == "set-score-to-distance":
for gffs in GTF.transcript_iterator(GTF.iterator(options.stdin)):
ninput += 1
strand = Genomics.convertStrand(gffs[0].strand)
all_start, all_end = min([x.start for x in gffs]), max([x.end for x in gffs])
if strand != ".":
t = 0
if strand == "-":
gffs.reverse()
for gff in gffs:
gff.score = t
t += gff.end - gff.start
if strand == "-":
gffs.reverse()
for gff in gffs:
options.stdout.write("%s\n" % str(gff))
nfeatures += 1
noutput += 1
elif options.method == "remove-overlapping":
index = GTF.readAndIndex(GTF.iterator(IOTools.openFile(options.filename_gff, "r")))
for gffs in GTF.transcript_iterator(GTF.iterator(options.stdin)):
ninput += 1
found = False
for e in gffs:
if index.contains(e.contig, e.start, e.end):
found = True
break
if found:
ndiscarded += 1
else:
noutput += 1
for e in gffs:
nfeatures += 1
options.stdout.write("%s\n" % str(e))
elif options.method == "intersect-transcripts":
for gffs in GTF.gene_iterator(GTF.iterator(options.stdin), strict=options.strict):
ninput += 1
r = []
for g in gffs:
if options.with_utr:
ranges = GTF.asRanges(g, "exon")
else:
ranges = GTF.asRanges(g, "CDS")
r.append(ranges)
result = r[0]
for x in r[1:]:
result = Intervals.intersect(result, x)
entry = GTF.Entry()
entry.copy(gffs[0][0])
entry.clearAttributes()
entry.transcript_id = "merged"
entry.feature = "exon"
for start, end in result:
entry.start = start
entry.end = end
options.stdout.write("%s\n" % str(entry))
nfeatures += 1
noutput += 1
elif "rename-duplicates" == options.method:
# note: this will only rename entries with "CDS" in feature column
assert options.duplicate_feature in ["gene", "transcript", "both"], (
"for renaming duplicates, --duplicate-feature must be set to one " "of 'gene', transcript' or 'both'"
)
gene_ids = list()
transcript_ids = list()
gtfs = list()
for gtf in GTF.iterator(options.stdin):
gtfs.append(gtf)
if gtf.feature == "CDS":
gene_ids.append(gtf.gene_id)
transcript_ids.append(gtf.transcript_id)
dup_gene = [item for item in set(gene_ids) if gene_ids.count(item) > 1]
dup_transcript = [item for item in set(transcript_ids) if transcript_ids.count(item) > 1]
E.info("Number of duplicated gene_ids: %i" % len(dup_gene))
E.info("Number of duplicated transcript_ids: %i" % len(dup_transcript))
gene_dict = dict(zip(dup_gene, ([0] * len(dup_gene))))
transcript_dict = dict(zip(dup_transcript, ([0] * len(dup_transcript))))
for gtf in gtfs:
if gtf.feature == "CDS":
if options.duplicate_feature in ["both", "gene"]:
if gtf.gene_id in dup_gene:
gene_dict[gtf.gene_id] = gene_dict[gtf.gene_id] + 1
gtf.setAttribute("gene_id", gtf.gene_id + "." + str(gene_dict[gtf.gene_id]))
if options.duplicate_feature in ["both", "transcript"]:
if gtf.transcript_id in dup_transcript:
transcript_dict[gtf.transcript_id] = transcript_dict[gtf.transcript_id] + 1
gtf.setAttribute(
"transcript_id", gtf.transcript_id + "." + str(transcript_dict[gtf.transcript_id])
)
options.stdout.write("%s\n" % gtf)
elif options.method in ("merge-exons", "merge-introns", "merge-transcripts"):
for gffs in GTF.flat_gene_iterator(GTF.iterator(options.stdin), strict=options.strict):
ninput += 1
cds_ranges = GTF.asRanges(gffs, "CDS")
exon_ranges = GTF.asRanges(gffs, "exon")
# sanity checks
strands = set([x.strand for x in gffs])
contigs = set([x.contig for x in gffs])
if len(strands) > 1:
raise ValueError("can not merge gene '%s' on multiple strands: %s" % (gffs[0].gene_id, str(strands)))
if len(contigs) > 1:
raise ValueError("can not merge gene '%s' on multiple contigs: %s" % (gffs[0].gene_id, str(contigs)))
strand = Genomics.convertStrand(gffs[0].strand)
if cds_ranges and options.with_utr:
cds_start, cds_end = cds_ranges[0][0], cds_ranges[-1][1]
midpoint = (cds_end - cds_start) / 2 + cds_start
utr_ranges = []
for start, end in Intervals.truncate(exon_ranges, cds_ranges):
if end - start > 3:
if strand == ".":
feature = "UTR"
elif strand == "+":
if start < midpoint:
feature = "UTR5"
else:
feature = "UTR3"
elif strand == "-":
if start < midpoint:
feature = "UTR3"
else:
feature = "UTR5"
utr_ranges.append((feature, start, end))
output_feature = "CDS"
output_ranges = cds_ranges
else:
output_feature = "exon"
output_ranges = exon_ranges
utr_ranges = []
result = []
try:
biotypes = [x["gene_biotype"] for x in gffs]
biotype = ":".join(set(biotypes))
except (KeyError, AttributeError):
biotype = None
if options.method == "merge-exons":
# need to combine per feature - skip
# utr_ranges = Intervals.combineAtDistance(
# utr_ranges,
# options.merge_exons_distance)
output_ranges = Intervals.combineAtDistance(output_ranges, options.merge_exons_distance)
for feature, start, end in utr_ranges:
entry = GTF.Entry()
entry.copy(gffs[0])
entry.clearAttributes()
entry.feature = feature
entry.transcript_id = "merged"
if biotype:
entry.addAttribute("gene_biotype", biotype)
entry.start = start
entry.end = end
result.append(entry)
for start, end in output_ranges:
entry = GTF.Entry()
entry.copy(gffs[0])
entry.clearAttributes()
entry.transcript_id = "merged"
if biotype:
entry.addAttribute("gene_biotype", biotype)
entry.feature = output_feature
entry.start = start
entry.end = end
result.append(entry)
elif options.method == "merge-transcripts":
entry = GTF.Entry()
entry.copy(gffs[0])
entry.clearAttributes()
entry.transcript_id = entry.gene_id
if biotype:
entry.addAttribute("gene_biotype", biotype)
entry.start = output_ranges[0][0]
entry.end = output_ranges[-1][1]
result.append(entry)
elif options.method == "merge-introns":
if len(output_ranges) >= 2:
entry = GTF.Entry()
entry.copy(gffs[0])
entry.clearAttributes()
entry.transcript_id = entry.gene_id
if biotype:
entry.addAttribute("gene_biotype", biotype)
entry.start = output_ranges[0][1]
entry.end = output_ranges[-1][0]
result.append(entry)
else:
ndiscarded += 1
continue
result.sort(key=lambda x: x.start)
for x in result:
options.stdout.write("%s\n" % str(x))
nfeatures += 1
noutput += 1
elif options.method == "find-retained-introns":
for gene in GTF.gene_iterator(GTF.iterator(options.stdin)):
ninput += 1
found_any = False
for intron in find_retained_introns(gene):
found_any = True
options.stdout.write("%s\n" % str(intron))
nfeatures += 1
if found_any:
noutput += 1
elif options.method == "genes-to-unique-chunks":
for gene in GTF.flat_gene_iterator(GTF.iterator(options.stdin)):
ninput += 1
for exon in gene_to_blocks(gene):
options.stdout.write("%s\n" % str(exon))
nfeatures += 1
noutput += 1
else:
raise ValueError("unknown method '%s'" % options.method)
E.info("ninput=%i, noutput=%i, nfeatures=%i, ndiscarded=%i" % (ninput, noutput, nfeatures, ndiscarded))
E.Stop()
def main():
parser = E.OptionParser(
version=
"%prog version: $Id: psl2gff.py 2781 2009-09-10 11:33:14Z andreas $",
usage=globals()["__doc__"])
parser.add_option("-a",
"--as-gtf",
dest="as_gtf",
action="store_true",
help="output as gtf.")
parser.add_option(
"-s",
"--filename-strand",
dest="filename_strand",
type="string",
help="set strand information according to file [default=%DEFAULT].")
parser.set_defaults(as_gtf=False, filename_strand=None, test=None)
(options, args) = E.Start(parser, add_pipe_options=True)
####################################
if options.filename_strand:
map_id2strand = IOTools.readMap(open(options.filename_strand, "r"))
else:
map_id2strand = {}
iterator = Blat.BlatIterator(sys.stdin)
ninput, noutput, nskipped = 0, 0, 0
if options.as_gtf:
gff = GTF.Entry()
else:
gff = GTF.Entry()
gff.source = "psl"
gff.feature = "exon"
ids = {}
while 1:
if options.test and ninput >= options.test:
break
match = iterator.next()
if match is None:
break
ninput += 1
if match.mQueryId not in ids:
ids[match.mQueryId] = 1
id = match.mQueryId
else:
id = match.mQueryId + ":%i" % ids[match.mQueryId]
ids[match.mQueryId] += 1
if options.as_gtf:
gff.contig = match.mSbjctId
gff.gene_id = id
gff.transcript_id = id
else:
gff.contig = match.mSbjctId
gff.clearAttributes()
gff.addAttribute("gene_id", id)
if id in map_id2strand:
gff.strand = map_id2strand[id]
else:
gff.strand = match.strand
for qstart, sstart, size in match.getBlocks():
gff.start = sstart
gff.end = sstart + size
options.stdout.write(str(gff) + "\n")
noutput += 1
E.info("ninput=%i, noutput=%i, nskipped=%i" % (ninput, noutput, nskipped))
E.Stop()
def main(argv=None):
"""script main.
parses command line options in sys.argv, unless *argv* is given.
"""
if argv is None:
argv = sys.argv
# setup command line parser
parser = E.OptionParser(version="%prog version: $Id$",
usage=globals()["__doc__"])
parser.add_option("-s", "--suffix", dest="suffixes",
action="append",
type="string",
help="mapping of suffix [%default]")
parser.add_option("-m", "--map", dest="filename_map",
type="string",
help="filename containing a mapping of filenames "
"to destinations [%default]")
parser.add_option("-u", "--no-sort", dest="do_sort",
action="store_false",
help="do not sort filenames before grouping "
"[%default]")
parser.add_option("-n", "--dry-run", dest="dry_run",
action="store_true",
help="dry run - do not merge "
"[%default]")
parser.set_defaults(
filename_map=None,
do_sort=True,
dry_run=False,
suffixes=[])
# add common options (-h/--help, ...) and parse command line
(options, args) = E.Start(parser, argv=argv)
if options.filename_map:
map_regex2dest = IOTools.readMap(
IOTools.openFile(options.filename_map))
map_regex2dest = dict([(re.compile(x), y) for x, y in
list(map_regex2dest.items())])
map_suffix2dest = {}
for suffix in options.suffixes:
src, dest = suffix.split("=")
map_suffix2dest[src.strip()] = dest.strip()
filenames = args
if options.do_sort:
filenames.sort()
dest2src = collections.defaultdict(list)
for filename in filenames:
dests = []
for regex, dest in list(map_regex2dest.items()):
if regex.search(filename):
dests.append(dest)
if len(dests) == 0:
raise ValueError("no destination found for %s" % filename)
elif len(dests) > 1:
raise ValueError(
"multiple destinations found for %s: %s " %
(filename, dests))
dest = dests[0]
# implement suffix mapping, note that
# suffixes can extend beyond an extension
for suffix, new_suffix in list(map_suffix2dest.items()):
if filename.endswith(suffix):
if suffix in map_suffix2dest:
dest = dest + map_suffix2dest[suffix]
break
dest2src[dest].append(filename)
for dest, srcs in sorted(dest2src.items()):
E.info("merging: %s <- %s" % (dest, srcs))
if options.dry_run:
continue
E.run('cat %s > %s' % (" ".join(srcs),
dest))
# write footer and output benchmark information.
E.Stop()
