Secure your code as it's written. Use Snyk Code to scan source code in minutes - no build needed - and fix issues immediately.
assert self.min_size <= self.max_size
mkdirs(self.outdir)
self.resultsOnSamples = OrderedDict()
outdir = self.outdir
# iter through each sample
for name, ser in df.iteritems():
self.outdir = os.path.join(outdir, str(name))
self._logger.info("Run Sample: %s " % name)
mkdirs(self.outdir)
# sort ranking values from high to low or reverse
dat2 = ser.sort_values(ascending=self.ascending)
# reset integer index, or caused unwanted problems
# df.reset_index(drop=True, inplace=True)
# compute ES, NES, pval, FDR, RES
gsea_results, hit_ind,rank_ES, subsets = gsea_compute(data=dat2, n=self.permutation_num, gmt=gmt,
weighted_score_type=self.weighted_score_type,
permutation_type='gene_set', method=None,
pheno_pos='', pheno_neg='',
classes=None, ascending=self.ascending,
processes=self._processes,
seed=self.seed, single=True, scale=self.scale)
# write file
res_zip = zip(subsets, list(gsea_results), hit_ind, rank_ES)
self._save_results(zipdata=res_zip, outdir=self.outdir, module=self.module,
gmt=gmt, rank_metric=dat2, permutation_type="gene_sets")
self.resultsOnSamples[name] = self.res2d.es
# plotting
if self._noplot: continue
self._logger.info("Plotting Sample: %s \n" % name)
self._plotting(rank_metric=dat2, results=self.results,
| 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]
rdict['fdr'] = gseale[3]
# parsing rankings
dat2 = self._load_ranking(self.rnk)
assert len(dat2) > 1
# cpu numbers
self._set_cores()
# Start Analysis
self._logger.info("Parsing data files for GSEA.............................")
# 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..................")
# compute ES, NES, pval, FDR, RES
gsea_results, hit_ind,rank_ES, subsets = gsea_compute(data=dat2, n=self.permutation_num, gmt=gmt,
weighted_score_type=self.weighted_score_type,
permutation_type='gene_set', method=None,
pheno_pos=self.pheno_pos, pheno_neg=self.pheno_neg,
classes=None, ascending=self.ascending,
processes=self._processes, seed=self.seed)
self._logger.info("Start to generate gseapy reports, and produce figures...")
res_zip = zip(subsets, list(gsea_results), hit_ind, rank_ES)
self._save_results(zipdata=res_zip, outdir=self.outdir, module=self.module,
gmt=gmt, rank_metric=dat2, permutation_type="gene_sets")
# Plotting
if not self._noplot:
self._plotting(rank_metric=dat2, results=self.results,
graph_num=self.graph_num, outdir=self.outdir,
figsize=self.figsize, format=self.format,
pheno_pos=self.pheno_pos, pheno_neg=self.pheno_neg)