def run(self):
"""GSEA main procedure"""
assert self.method in ['signal_to_noise', 's2n', 'abs_signal_to_noise', 'abs_s2n',
't_test', 'ratio_of_classes', 'diff_of_classes', 'log2_ratio_of_classes']
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, cls_dict = 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_dict, 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,
classes=cls_vector, ascending=self.ascending,
processes=self._processes, seed=self.seed)
self._logger.info("Start to generate GSEApy reports and 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=self.permutation_type)
# reorder datarame for heatmap
self._heatmat(df=dat.loc[dat2.index], classes=cls_vector,
pheno_pos=phenoPos, pheno_neg=phenoNeg)
# 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=phenoPos, pheno_neg=phenoNeg)
self._logger.info("Congratulations. GSEApy ran successfully.................\n")
if self._outdir is None:
self._tmpdir.cleanup()
return
def run(self):
"""GSEA main procedure"""
assert self.permutation_type in ["phenotype", "gene_set"]
assert self.min_size <= self.max_size
if isinstance(self.data, pd.DataFrame):
df = self.data.copy()
elif os.path.isfile(self.data):
df = pd.read_table(self.data, comment='#')
else:
raise Exception('Error parsing gene expression dataframe!')
sys.exit(1)
#data frame must have lenght > 1
assert len(df) > 1
# creat output dirs
mkdirs(self.outdir)
logger = self._log_init(
module=self.module,
log_level=logging.INFO if self.verbose else logging.WARNING)
#Start Analysis
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.__drop_dat(df, cls_vector)
#ranking metrics calculation.
dat2 = ranking_metric(df=dat,
method=self.method,
phenoPos=phenoPos,
phenoNeg=phenoNeg,
classes=cls_vector,
ascending=self.ascending)
#filtering out gene sets and build gene sets dictionary
gmt = gsea_gmt_parser(self.gene_sets,
min_size=self.min_size,
max_size=self.max_size,
gene_list=dat2['gene_name'].values)
logger.info(
"%04d gene_sets used for further statistical testing....." %
len(gmt))
logger.info("Start to run GSEA...Might take a while..................")
#cpu numbers
self._set_cores()
#compute ES, NES, pval, FDR, RES
gsea_results, hit_ind, rank_ES, subsets = gsea_compute(
data=dat,
n=self.permutation_num,
gmt=gmt,
weighted_score_type=self.weighted_score_type,
permutation_type=self.permutation_type,
method=self.method,
phenoPos=phenoPos,
phenoNeg=phenoNeg,
classes=cls_vector,
ascending=self.ascending,
seed=self.seed,
processes=self._processes)
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
heat_dat = dat.loc[dat2.gene_name]
self._plotting(rank_metric=dat2,
results=self.results,
res2d=self.res2d,
graph_num=self.graph_num,
outdir=self.outdir,
figsize=self.figsize,
format=self.format,
module=self.module,
data=heat_dat,
classes=cls_vector,
phenoPos=phenoPos,
phenoNeg=phenoNeg)
logger.info("Congratulations. GSEApy run successfully................")
return
