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()
gopca_file = args.gopca_file
output_file = args.output_file
#sig_max_len = args.sig_max_len
#sig_reverse_order = args.sig_reverse_order
#sample_cluster_metric = args.sample_cluster_metric
#no_sample_clustering = args.no_sample_clustering
# configure root logger
log_file = args.log_file
quiet = args.quiet
verbose = args.verbose
logger = misc.get_logger(log_file=log_file, quiet=quiet,
verbose=verbose)
result = util.read_gopca_result(gopca_file)
sig_matrix = util.read_gopca_result(gopca_file)
sig_labels = [sig.get_label(include_id=False)
for sig in sig_matrix.signatures]
matrix = ExpMatrix(genes=sig_labels, samples=sig_matrix.samples,
X=sig_matrix.X)
matrix.index.name = 'Signatures'
#signatures = result.signatures
#sig_labels = [sig.get_label(max_name_length=sig_max_len, include_id=False)
# for sig in signatures]
#samples = list(result.samples)
# generate expression matrix
#E = ExpMatrix(genes=sig_labels, samples=samples, X=sig_matrix.X)
# clustering of signatures (rows)
#E, _ = cluster.cluster_genes(E, reverse=sig_reverse_order)
exp_logger = logging.getLogger(expression.__name__)
exp_logger.setLevel(logging.WARNING)
matrix.write_tsv(output_file)
exp_logger.setLevel(logging.NOTSET)
logger.info('Wrote %d x %d signature matrix to "%s".',
matrix.p, matrix.n, output_file)
return 0
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):
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 = ExpGeneTable.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
