def lisa_multi(args):
log = Log(target=sys.stderr, verbose=args.verbose)
lisa = FromGenes(args.species,
**extract_kwargs(args, INSTANTIATION_KWARGS),
log=log)
query_dict = {
os.path.basename(query.name): query.readlines()
for query in args.query_lists
}
results_summary = []
all_passed = True
for query_name, query_list in query_dict.items():
with log.section('Modeling {}:'.format(str(query_name))):
try:
results, metadata = lisa.predict(
query_list, **extract_kwargs(args, PREDICTION_KWARGS))
top_TFs_unique = save_and_get_top_TFs(args, query_name,
results, metadata)
results_summary.append((query_name, top_TFs_unique))
except AssertionError as err:
all_passed = False
log.append('ERROR: ' + str(err))
print_results_multi(results_summary)
if not all_passed:
raise MultiError('One or more genelists raised an error')
def lisa_deseq(args):
log = Log(target=sys.stderr, verbose=args.verbose)
lisa = FromGenes(args.species,
**extract_kwargs(args, INSTANTIATION_KWARGS),
log=log)
up_genes, down_genes = parse_deseq_file(args.deseq_file,
lfc_cutoff=args.lfc_cutoff,
pval_cutoff=args.pval_cutoff,
sep=args.sep)
results_summary = []
all_passed = True
for prefix, query_list in zip(['up-regulated', 'down-regulated'],
[up_genes, down_genes]):
with log.section('Modeling {}:'.format(str(prefix))):
try:
results, metadata = lisa.predict(
query_list, **extract_kwargs(args, PREDICTION_KWARGS))
top_TFs_unique = save_and_get_top_TFs(args, prefix, results,
metadata)
results_summary.append((prefix, top_TFs_unique))
except AssertionError as err:
all_passed = False
log.append('ERROR: ' + str(err))
print_results_multi(results_summary)
if not all_passed:
raise MultiError('One or more genelists raised an error')
def convert_bigwig(cls, bigwig, species, bigwig_cmd_path):
log = Log()
genome = DataInterface.load_genome(species, cls.window_size)
coverage_array = np.zeros(len(genome))
log.append('Converting BigWig file to coverage array ...')
if not os.path.exists(cls._get_genome_bin_path(species)):
log.append('Writing bins ...')
cls._write_genome_bins(species)
try:
temp = tempfile.NamedTemporaryFile('w', delete=False)
temp.close()
process = subprocess.run([bigwig_cmd_path, bigwig, cls._get_genome_bin_path(species), temp.name], capture_output=True)
if process.returncode == 0:
with open(temp.name, 'r') as cmd_output:
for line in cmd_output:
fields = line.strip().split('\t')
coverage_array[int(fields[0])] = fields[4]
return coverage_array
else:
raise AssertionError(process.stderr.decode('utf-8'))
finally:
os.remove(temp.name)
def __init__(self,
species,
window_size=1000,
download_if_not_exists=True,
make_new=False,
log=None,
path=None,
load_genes=True):
self.species = species
self.window_size = int(window_size)
if log is None:
self.log = Log()
else:
self.log = log
if path is None:
self.path = self.get_dataset_path(self.species, self.window_size)
else:
self.path = path
if make_new:
h5.File(self.path, 'w').close()
elif not os.path.isfile(self.path):
if download_if_not_exists and path is None:
self.download_data()
else:
h5.File(self.path, 'w').close()
#___ LOAD GENE DATA FROM PACKAGE _____
self.genome = self.load_genome(self.species, self.window_size)
if load_genes:
self.load_genes()
def convert_bigwig(cls, bigwig, species, log=None):
if log is None:
log = Log()
genome = DataInterface.load_genome(species, cls.window_size)
coverage_array = np.zeros(len(genome))
log.append('Converting BigWig file to coverage array ...')
bar = LoadingBar('Progress', len(genome) // 1000 + 1, cold_start=True)
try:
coverage_bw = bw.open(bigwig)
log.append(bar, update_line=True)
for i, window in enumerate(genome.list_windows()):
if window.chromosome in coverage_bw.chroms():
mean_coverage = coverage_bw.stats(*window.to_tuple())[0]
coverage_array[i] = mean_coverage
if i % 1000 == 0:
log.append(bar, update_line=True)
return np.nan_to_num(coverage_array)
finally:
coverage_bw.close()
def main(species, motif_bed, window_size, gamma_threshold=0.95):
genome = DataInterface.load_genome(species, window_size)
log = Log(target=stderr)
factor_name = None
window_nums, scores = [], []
with gzip.open(motif_bed, 'rb') as f:
bed = f.readlines()
bar = LoadingBar('Binning {} motif hits'.format(str(len(bed))),
len(bed),
cold_start=True)
for i, line in enumerate(bed):
chrom, start, end, factor, relscore, log_pval, strand = line.decode(
'utf-8').strip().split('\t')
if i == 0:
factor_name = factor
try:
hit_windows = genome.get_region_windows(
Region(chrom, start, end))
window_nums.extend(hit_windows)
scores.extend([float(log_pval) / 100] * len(hit_windows))
except BadRegionError:
pass
log.append(bar, update_line=True)
log.append('')
log.append('Done')
hits = sparse.csc_matrix((scores, window_nums, [0, len(window_nums)]),
shape=(len(genome), 1)).tocoo().tocsc()
sample_hit_scores = np.random.choice(np.array(hits.todense()).reshape(-1),
size=10000)
min_bin_score = gamma(*gamma.fit(sample_hit_scores)).ppf(gamma_threshold)
hit_indices = hits.indices[(hits.data >= min_bin_score) & (hits.data > 0)]
return hit_indices, factor_name
def using_bigwig(cls,
species,
query_genes,
bigwig_path,
rp_map='enhanced_10K',
isd_method='chipseq',
background_list=[],
background_strategy='all',
num_background_genes=3000,
seed=2556,
verbose=4,
log=None):
'''
*classmethod*
**lisa.FromCoverage.using_bigwig** (species, query_genes, bigwig_path, rp_map = 'basic', rp_decay = 10000, isd_method = 'chipseq', background_list = [], background_strategy = 'all', num_background_genes = 3000, seed = 2556, header = False, verbose = 4, log = None)
Run LISA FromCoverage test using a bigwig coverage file.
Parameters:
species: {'hg38', 'mm10'}
query_genes (list):
Genes-of-interest, in either Symbol of RefSeqID format. Must provide between 20 to 500 genes.
bigwig_path (str):
Path to bigwig file
Returns:
results (lisa.core.utils.LISA_Results):
With each key representing a table column, sorted by "summary_p_value" field. The dictionary can be passed directly to a the pandas constructor: ``results_df = pd.DataFrame(results.to_dict())``.
metadata (dict):
Test metadata. Includes query genes provided and background genes that were selected.
'''
if log is None:
log = Log()
coverage_array = cls.convert_bigwig(bigwig_path, species, log=log)
return cls(species, coverage_array, rp_map = rp_map, isd_method=isd_method, verbose=verbose, log=log)\
.predict(query_genes, background_list=background_list, background_strategy=background_strategy, num_background_genes=num_background_genes,
seed=seed)