def save_enrichment_set():
lib = gp.get_library_name('Human')
lib = lib[53]
files = [("gcn-hom-hom", "enrich/gcn-hom-hom.csv"),
("gcn-hom-onto", "enrich/gcn-hom-onto.csv"),
("gcn-onto-onto", "enrich/gcn-onto-onto.csv"),
("gae-hom-hom", "enrich/gae-hom-hom.csv"),
("gae-hom-onto", "enrich/gae-hom-onto.csv"),
("gae-onto-onto", "enrich/gae-onto-onto.csv")]
enrich_set = {}
for key, file in files:
print(file)
cluster_data = read_file(file)
for i in cluster_data:
print(len(cluster_data[i][2]))
try:
enr = gp.enrichr(gene_list=list(cluster_data[i][2])[:1000], gene_sets=lib, organism='Human', cutoff=0.05).results
name = key + "-" + str(i)
term = enr['Term'].to_list()
enrich_set[name] = term
# print(i)
print(enr)
except:
pass
write_file("enrich-cluster/full_result_dic.csv", enrich_set)
def save_enrichment(x):
lib = gp.get_library_name('Human')
with open('gensets.txt', 'w') as f:
for item in range(len(lib)):
f.write("%s %s\n" % (item, lib[item]))
# lib = lib[49: 54]
lib = lib[53]
files = [(1, x+"/gcn-hom-hom.csv"), (2, x+"/gcn-hom-onto.csv"),
(3, x+"/gcn-onto-onto.csv"), (4, x+"/gae-hom-hom.csv"),
(5, x+"/gae-hom-onto.csv"), (6, x+"/gae-onto-onto.csv")]
df = pd.DataFrame()
writer = pd.ExcelWriter('enrich-cluster/full-results.xlsx')
for key, file in files:
print(file)
cluster_data = read_file_2(file)
for i in cluster_data:
try:
enr = gp.enrichr(gene_list=list(cluster_data[i][2]), gene_sets=lib, organism='Human', cutoff=0.05).results
except:
pass
enr['model'] = key
enr['cluster'] = i
df = df.append(enr)
df = df[(df['P-value'] < 0.05)]
df.to_excel(writer, sheet_name="sheet1")
writer.save()
def enrichment_analysis(self, library, output):
"""
Saves the results of enrichment analysis
Attributes:
-----------
library - Enrichr library to be used. Recommendations:
- 'GO_Molecular_Function_2018'
- 'GO_Biological_Process_2018'
- 'GO_Cellular_Component_2018'
for more options check available libraries by typing gseapy.get_library_name()
output - directory name where results should be saved
"""
libs = gseapy.get_library_name()
assert library in libs, "the library is not available, check gseapy.get_library_name() for available options"
assert (self.convert == True) or (
self.origID == "symbol"
), "EnrichR accepts only gene names as an input, thus please set 'convert' to True and indicate the original gene ID"
genes1_name = [self.mapping[x] for x in self.genes1]
genes2_name = [self.mapping[x] for x in self.genes2]
all_genes_names = genes1_name + genes2_name
res = gseapy.enrichr(gene_list=all_genes_names,
description='pathway',
gene_sets=library,
cutoff=0.05,
outdir=output)
return (res.results)
def __init__(self, **kwargs):
super().__init__(**kwargs)
if not self.path.exists():
print(self.__doc__)
import gseapy
self.libraries = gseapy.get_library_name()
import pandas as pd
import gseapy as gp
import requests
import sleep
import matplotlib.pyplot as plt
from gseapy.parser import Biomart
from gseapy.plot import barplot, dotplot
gene_list = pd.read_csv("/Users/sunxueyan/Downloads/GSEApy-master/tests/data/gene_list.txt",header=None, sep="\t")
gene_list1 = pd.read_csv("/Users/sunxueyan/Downloads/non_geneID.csv")
gene_list1.head()
glist = gene_list1.squeeze().str.strip().tolist()
names = gp.get_library_name() # default: Human
s = requests.session()
s.keep_alive = False
enr = gp.enrichr(gene_list="/Users/sunxueyan/Downloads/GSEApy-master/tests/data/gene_list.txt",
# or gene_list=glist
description='',
gene_sets=['KEGG_2019_Human'],
outdir='test/enrichr_kegg',
cutoff=0.5 # test dataset, use lower value from range(0,1)
)
if __name__ == '__main__':
parser = argparse.ArgumentParser()
parser.add_argument("cls_file", help="Path to a cls file", type=str)
parser.add_argument(
"gct_file",
help="Path to a gmt-like file with second line discarded",
type=str)
parser.add_argument("-g",
"--gene_set",
help="Gene set name"
" (default: %(default)s)",
type=str,
choices=gp.get_library_name(),
default='KEGG_2016')
parser.add_argument("-p",
"--permutation_type",
help="Type of permutation used within GSEA"
" (default: %(default)s)",
type=str,
choices=['gene_set', 'phenotype'],
default='phenotype')
parser.add_argument("-o",
"--output_dir",
help="Path to output_dir"
" (default: %(default)s)",
type=str,
from EnrichmentAnalysis.enrichment_utils import read_file, read_file_2, write_file
def reduce_genesets():
sample = read_file("enrich_red/gae-hom-hom.csv")
red = read_file("enrich_red/selected_genesets.csv")
temp = {}
for i in red:
if i in sample:
temp[i] = red[i]
write_file("enrich_red/selected_genesets.csv", temp)
# reduce_genesets()
lib = gp.get_library_name('Human')[53]
files = [("gae-hom-hom", 1, 1), ("gae-hom-onto", 1, 2),
("gae-onto-onto", 2, 3), ("jcd-hom-hom", 1, 4),
("jcd-onto-onto", 2, 5)]
data_desc = read_file_2("data\ms-project\data-description.csv")
for i in files:
file_name = "enrich_red/" + i[0] + ".csv"
file = read_file(file_name)
# if i[1] == 1:
# neigh = read_file_2("data/ms-project/neig_len_hom.csv")
# else:
# neigh = read_file_2("data/ms-project/neig_len_onto.csv")
if i[2] == 1:
rank = read_file_2(
