Secure your code as it's written. Use Snyk Code to scan source code in minutes - no build needed - and fix issues immediately.
def run(data, gmt, cls, permutation_type='phenotype', method='signal_to_noise', permution_num=1000):
prefix = gp.__name__ + "."
for importer, modname, ispkg in pkgutil.iter_modules(gp.__path__, prefix):
if modname == "gseapy.gsea":
module = __import__(modname, fromlist="dummy")
vs = gp.__version__.split(".")
if int(vs[0]) == 0 and int(vs[1]) < 9:
module.ranking_metric = GSEA._ranking_metric
else:
module.ranking_metric = GSEA._ranking_metric2
gp.algorithm.ranking_metric = GSEA._ranking_metric
res = gp.gsea(data, gmt, cls, permutation_type=permutation_type, permutation_num=permution_num,
outdir=os.path.join(os.path.dirname(os.path.realpath(__file__)), 'images'), method=method)
return GSEA(res.res2d, data, gmt, cls)
def run(self):
"""GSEA main procedure"""
assert self.permutation_type in ["phenotype", "gene_set"]
assert self.min_size <= self.max_size
# Start Analysis
self._logger.info("Parsing data files for GSEA.............................")
# phenotype labels parsing
phenoPos, phenoNeg, cls_vector = gsea_cls_parser(self.classes)
# select correct expression genes and values.
dat = self.load_data(cls_vector)
# data frame must have length > 1
assert len(dat) > 1
# ranking metrics calculation.
dat2 = ranking_metric(df=dat, method=self.method, pos=phenoPos, neg=phenoNeg,
classes=cls_vector, ascending=self.ascending)
self.ranking = dat2
# filtering out gene sets and build gene sets dictionary
gmt = self.load_gmt(gene_list=dat2.index.values, gmt=self.gene_sets)
self._logger.info("%04d gene_sets used for further statistical testing....."% len(gmt))
self._logger.info("Start to run GSEA...Might take a while..................")
# cpu numbers
self._set_cores()
# compute ES, NES, pval, FDR, RES
dataset = dat if self.permutation_type =='phenotype' else dat2
gsea_results,hit_ind,rank_ES, subsets = gsea_compute_tensor(data=dataset, gmt=gmt, n=self.permutation_num,
weighted_score_type=self.weighted_score_type,
permutation_type=self.permutation_type,
method=self.method,
pheno_pos=phenoPos, pheno_neg=phenoNeg,
| fdr: FDR,
| size: gene set size,
| matched_size: genes matched to the data,
| genes: gene names from the data set }
"""
assert len(data) > 1
assert permutation_type in ["phenotype", "gene_set"]
data = pd.read_table(data)
classes = gsea_cls_parser(cls)[2]
gmt = gsea_gmt_parser(gene_sets)
gmt.sort()
#Ecompute ES, NES, pval, FDR, RES
if rank_metric is None:
dat = ranking_metric(data,method= method,classes = classes ,ascending=ascending)
results,hit_ind,RES = gsea_compute(data = dat, gene_list = None,rankings = None,
n=permutation_n,gmt = gmt, weighted_score_type=weighted_score_type,
permutation_type=permutation_type)
else:
dat = pd.read_table(rank_metric)
results,hit_ind,RES = gsea_compute(data = None, gene_list = rank_metric['gene_name'],rankings = rank_metric['rank'].values,
n=permutation_n,gmt = gmt, weighted_score_type=weighted_score_type,
permutation_type=permutation_type)
res = {}
for gs, gseale in zip(gmt.keys(), list(results)):
rdict = {}
rdict['es'] = gseale[0]
rdict['nes'] = gseale[1]
rdict['pval'] = gseale[2]