def main(args=None):
vinfo = sys.version_info
if not (vinfo >= (2, 7)):
raise SystemError(
"Python interpreter version >= 2.7 required, " "found %d.%d instead." % (vinfo.major, vinfo.minor)
)
if args is None:
parser = get_argument_parser()
args = parser.parse_args()
expression_file = args.expression_file
entrez2gene_file = args.entrez2gene_file
gene_file = args.gene_file
output_file = args.output_file
strip_affy_suffix = args.strip_affy_suffix
log_file = args.log_file
quiet = args.quiet
verbose = args.verbose
# configure root logger
logger = misc.get_logger(log_file=log_file, quiet=quiet, verbose=verbose)
# read data
genome = ExpGenome.read_tsv(gene_file)
matrix = ExpMatrix.read_tsv(expression_file)
e2g = dict(misc.read_all(entrez2gene_file))
entrez = matrix.genes
if strip_affy_suffix:
# remove "_at" suffix from Entrez IDs
entrez = [e[:-3] for e in entrez]
logger.debug(str(entrez[:3]))
# check that Entrez IDs are unique
assert len(entrez) == len(set(entrez))
# convert Entrez IDs to gene names
f = 0
genes = []
X = []
# g = None
for i, e in enumerate(entrez):
# print e
try:
g = e2g[e]
except KeyError:
f += 1
else:
# check if there are multiple entrez IDs pointing to the same gene
# assert g not in genes
genes.append(g)
X.append(matrix.X[i, :])
assert len(genes) == len(set(genes))
if f > 0:
logger.warning(
"Failed to convert %d / %d entrez IDs " "to gene symbols (%.1f%%).",
f,
matrix.p,
100 * (f / float(matrix.p)),
)
# filter for known protein-coding genes
X = np.float64(X)
p = X.shape[0]
logger.debug(str(X.shape))
sel = np.zeros(p, dtype=np.bool_)
for i in range(p):
if genes[i] in genome:
sel[i] = True
sel = np.nonzero(sel)[0]
genes = [genes[i] for i in sel]
X = X[sel, :]
f = p - sel.size
if f > 0:
logger.warning(
"Failed to find %d / %d gene symbols in list of " "protein-coding genes (%.1f%%)",
f,
p,
100 * (f / float(p)),
)
# generate new matrix (this automatically sorts the genes alphabetically)
logger.debug("Genes: %d, Samples: %d, matrix: %s", len(genes), len(matrix.samples), str(X.shape))
matrix_conv = ExpMatrix(genes=genes, samples=matrix.samples, X=X)
# write output file
matrix_conv.write_tsv(output_file)
return 0
def main(args=None):
"""Extract GO annotations and store in tab-delimited text file.
Parameters
----------
args: argparse.Namespace object, optional
The argument values. If not specified, the values will be obtained by
parsing the command line arguments using the `argparse` module.
Returns
-------
int
Exit code (0 if no error occurred).
Raises
------
SystemError
If the version of the Python interpreter is not >= 2.7.
"""
vinfo = sys.version_info
if not (vinfo >= (2, 7)):
raise SystemError('Python interpreter version >= 2.7 required, '
'found %d.%d instead.' % (vinfo.major, vinfo.minor))
if args is None:
parser = get_argument_parser()
args = parser.parse_args()
gene_file = args.gene_file
gene_ontology_file = args.gene_ontology_file
goa_association_file = args.goa_association_file
output_file = args.output_file
evidence_codes = args.evidence_codes
min_genes = args.min_genes_per_term
max_genes = args.max_genes_per_term
part_of_cc_only = args.part_of_cc_only
# logging parameters
log_file = args.log_file
quiet = args.quiet
verbose = args.verbose
# configure root logger
logger = misc.get_logger(log_file=log_file, quiet=quiet, verbose=verbose)
logger.info('Selected evidence codes: %s', ', '.join(evidence_codes))
logger.info('Min. number of genes per gene set: %d', min_genes)
logger.info('Max. number of genes per gene set: %d', max_genes)
# checks
assert os.path.isfile(gene_file)
assert os.path.isfile(gene_ontology_file)
assert os.path.isfile(goa_association_file)
# configure root logger
log_stream = sys.stdout
if output_file == '-':
# if we print output to stdout, redirect log messages to stderr
log_stream = sys.stderr
logger = misc.get_logger(log_stream=log_stream,
log_file=log_file,
quiet=quiet,
verbose=verbose)
# extract protein-coding genes from Ensembl GTF file
exp_genome = ExpGenome.read_tsv(gene_file)
# parse Gene Ontology
gene_ontology = GeneOntology.read_obo(gene_ontology_file)
# parse UniProt-GOA gene association file
with gzip.open(goa_association_file, 'rt', encoding='ascii') as fh:
go_annotations = ontology.parse_gaf(fh,
gene_ontology,
ev_codes=evidence_codes,
genome=exp_genome)
# extract GO-based gene sets
gene_sets = ontology.get_goa_gene_sets(go_annotations)
logger.info('Generated %d GO-derived gene sets', len(gene_sets))
# filter gene sets based on size
if min_genes > 0:
old_size = len(gene_sets)
gene_sets = GeneSetCollection(gs for gs in gene_sets
if gs.size >= min_genes)
logger.info('Excluded %d gene sets with too few genes.',
old_size - len(gene_sets))
if max_genes > 0:
old_size = len(gene_sets)
gene_sets = GeneSetCollection(gs for gs in gene_sets
if gs.size <= max_genes)
logger.info('Excluded %d gene sets with too many genes.',
old_size - len(gene_sets))
# writing output file
gene_sets.write_tsv(output_file)
logger.info('Wrote %s GO-derived gene sets to output file "%s".',
len(gene_sets), output_file)
return 0
def my_genome(my_genome_file):
genome = ExpGenome.read_tsv(my_genome_file)
return genome
def test_tsv(tmpdir, my_genome):
tmp_file = str(tmpdir.join('_genome.tsv'))
# print(type(_genome.exp_genes[0]))
my_genome.write_tsv(tmp_file)
other = ExpGenome.read_tsv(tmp_file)
assert my_genome == other
