def run(self):
"""main replot function"""
assert self.min_size <= self.max_size
import glob
from bs4 import BeautifulSoup
#parsing files.......
try:
results_path = glob.glob(self.indir + '*/edb/results.edb')[0]
rank_path = glob.glob(self.indir + '*/edb/*.rnk')[0]
gene_set_path = glob.glob(self.indir + '*/edb/gene_sets.gmt')[0]
except IndexError as e:
logger.debug(e)
logger.error("Could not locate GSEA files in the given directory!")
sys.exit(1)
#extract sample names from .cls file
cls_path = glob.glob(self.indir + '*/edb/*.cls')
if cls_path:
phenoPos, phenoNeg, classes = gsea_cls_parser(cls_path[0])
else:
# logic for prerank results
phenoPos, phenoNeg = '', ''
#start reploting
self.gene_sets = gene_set_path
mkdirs(self.outdir)
logger = self._log_init(
module=self.module,
log_level=logging.INFO if self.verbose else logging.WARNING)
#obtain gene sets
gene_set_dict = gsea_gmt_parser(gene_set_path,
min_size=self.min_size,
max_size=self.max_size)
#obtain rank_metrics
rank_metric = self._rank_metric(rank_path)
correl_vector = rank_metric['rank'].values
gene_list = rank_metric['gene_name']
#extract each enriment term in the results.edb files and plot.
database = BeautifulSoup(open(results_path), features='xml')
length = len(database.findAll('DTG'))
for idx in range(length):
#extract statistical resutls from results.edb file
enrich_term, hit_ind, nes, pval, fdr = gsea_edb_parser(
results_path, index=idx)
gene_set = gene_set_dict.get(enrich_term)
#calculate enrichment score
RES = enrichment_score(
gene_list=gene_list,
gene_set=gene_set,
weighted_score_type=self.weighted_score_type,
correl_vector=correl_vector)[2]
#plotting
gsea_plot(rank_metric, enrich_term, hit_ind, nes, pval, fdr, RES,
phenoPos, phenoNeg, self.figsize, self.format,
self.outdir, self.module)
logger.info(
"Congratulations! Your plots have been reproduced successfully!")
def run(self):
"""main replot function"""
assert self.min_size <= self.max_size
assert self.fignum > 0
import glob
from bs4 import BeautifulSoup
# parsing files.......
try:
results_path = glob.glob(self.indir + '*/edb/results.edb')[0]
rank_path = glob.glob(self.indir + '*/edb/*.rnk')[0]
gene_set_path = glob.glob(self.indir + '*/edb/gene_sets.gmt')[0]
except IndexError as e:
sys.stderr.write(
"Could not locate GSEA files in the given directory!")
sys.exit(1)
# extract sample names from .cls file
cls_path = glob.glob(self.indir + '*/edb/*.cls')
if cls_path:
phenoPos, phenoNeg, classes = gsea_cls_parser(cls_path[0])
else:
# logic for prerank results
phenoPos, phenoNeg = '', ''
# start reploting
self.gene_sets = gene_set_path
# obtain gene sets
gene_set_dict = self.parse_gmt(gmt=gene_set_path)
# obtain rank_metrics
rank_metric = self._load_ranking(rank_path)
correl_vector = rank_metric.values
gene_list = rank_metric.index.values
# extract each enriment term in the results.edb files and plot.
database = BeautifulSoup(open(results_path), features='xml')
length = len(database.findAll('DTG'))
fig_num = self.fignum if self.fignum <= length else length
for idx in range(fig_num):
# extract statistical resutls from results.edb file
enrich_term, hit_ind, nes, pval, fdr = gsea_edb_parser(
results_path, index=idx)
gene_set = gene_set_dict.get(enrich_term)
# calculate enrichment score
RES = enrichment_score(
gene_list=gene_list,
correl_vector=correl_vector,
gene_set=gene_set,
weighted_score_type=self.weighted_score_type,
nperm=0)[-1]
# plotting
gsea_plot(rank_metric, enrich_term, hit_ind, nes, pval, fdr, RES,
phenoPos, phenoNeg, self.figsize, self.format,
self.outdir, self.module)
self._logger.info(
"Congratulations! Your plots have been reproduced successfully!\n")
def runSamples(self, df, gmt=None):
"""Single Sample GSEA workflow.
multiprocessing utility on samples.
"""
# df.index.values are gene_names
# Save each sample results to odict
self.resultsOnSamples = OrderedDict()
outdir = self.outdir
# run ssgsea for gct expression matrix
#multi-threading
subsets = sorted(gmt.keys())
tempes=[]
names=[]
rankings=[]
pool = Pool(processes=self._processes)
for name, ser in df.iteritems():
#prepare input
dat = ser.sort_values(ascending=self.ascending)
rankings.append(dat)
names.append(name)
genes_sorted, cor_vec = dat.index.values, dat.values
rs = np.random.RandomState(self.seed)
# apply_async
tempes.append(pool.apply_async(enrichment_score_tensor,
args=(genes_sorted, cor_vec, gmt,
self.weighted_score_type,
self.permutation_num, rs, True,
self.scale)))
pool.close()
pool.join()
# save results and plotting
for i, temp in enumerate(tempes):
name, rnk = names[i], rankings[i]
self._logger.info("Calculate Enrichment Score for Sample: %s "%name)
es, esnull, hit_ind, RES = temp.get()
# create results subdir
self.outdir= os.path.join(outdir, str(name))
mkdirs(self.outdir)
# save results
self.resultsOnSamples[name] = pd.Series(data=es, index=subsets, name=name)
# plotting
if self._noplot: continue
self._logger.info("Plotting Sample: %s \n" % name)
for i, term in enumerate(subsets):
gsea_plot(rnk,term, hit_ind[i], es[i], 1, 1, RES[i],
'', '', self.figsize, self.format,
self.outdir, module=self.module)
# save es, nes to file
self._save(outdir)
return
