'''
Created on May 5, 2020
@author: ywkim
'''
from sys import argv
from src.germline_analyses import get_list_from_csv, enrichment_test
if __name__ == '__main__':
input_file1 = argv[1]
input_file2 = argv[2]
l1 = get_list_from_csv(input_file1, 'Gene', sep='\t')
l2 = get_list_from_csv(input_file2, 'Gene', sep='\t')
# n_total = len(list(set(l1+l2)))
n_overlap, p, overlap = enrichment_test(l1, l2, 17039)
print(len(l1), len(l2))
print(n_overlap, p)
print(overlap)
import matplotlib.pyplot as plt
if __name__ == '__main__':
output_folder = str(Path().absolute()) + '/output_ADSP_discovery/'
gene_file = output_folder + 'iDEAL_genelist.txt'
comparison = 'APOE2_AD_v_APOE4_HC'
# gene_file = output_folder + 'pathogenic.txt'
# comparison = 'APOE2_ADvHC_pathogenic'
# gene_file = output_folder + 'protective.txt'
# comparison = 'APOE4_HCvAD_protective'
gene_list = get_list_from_csv(gene_file, 'Gene', sep='\t')
# these are gene x patient matrices
ADe2 = get_matrix_subset(output_folder,
'sum_ea_matrix_ADe2.tsv',
gene_list,
sep='\t',
index_col=0)
ADe4 = get_matrix_subset(output_folder,
'sum_ea_matrix_ADe4.tsv',
gene_list,
sep='\t',
index_col=0)
HCe4 = get_matrix_subset(output_folder,
'sum_ea_matrix_HCe4.tsv',
gene_list,
except HTTPError:
time.sleep(5)
Entrez.email = '*****@*****.**'
handle = Entrez.esearch(db='pubmed',
sort='relevance',
retstart=rs,
retmax='100000',
retmode='xml',
term=term_)
results = Entrez.read(handle)
return results
if __name__ == '__main__':
input_folder = str(Path().absolute()) + '/input/'
output_folder = str(Path().absolute()) + '/output_ADSP_discovery/'
drugs_file = input_folder + 'iDEAL_drugs_list.txt'
drugs_list = get_list_from_csv(drugs_file, 'Drug', sep='\t')
outputFile = output_folder + 'iDEAL_drugs_pubmed.txt'
with open(outputFile, 'w') as f:
writer = csv.writer(f, delimiter='\t')
writer.writerow(['Drug', 'PMID_count', 'PMID'])
for idx, drug in enumerate(drugs_list):
print(drug)
id_list = search(drug, 0)['IdList']
writer.writerow([drug, len(id_list), id_list])
from src.germline_analyses import get_list_from_csv
def venn_diagram(list1, list2, label1, label2, title, filename):
venn = venn2([set(list1), set(list2)], set_labels=(label1, label2), set_colors=('red', 'skyblue'), alpha=0.7)
venn2_circles([set(list1), set(list2)])
for text in venn.set_labels:
text.set_fontsize(14)
for text in venn.subset_labels:
text.set_fontsize(16)
plt.title(title)
plt.savefig(new_ideal_folder + filename + '.png', dpi=200, transparent=True)
plt.clf()
if __name__ == '__main__':
new_ideal_folder = '/Users/ywkim/Desktop/Projects/GermlineProject/ADSP/updated_iDEAL/'
old_ideal_folder = '/Users/ywkim/Desktop/Projects/GermlineProject/ADSP/RVEA/new2018/RVEA_BaylorPass_' \
'nonHisWhite_2v4_h5py_STARTLOSS100/'
new_pathogenic_list = get_list_from_csv(new_ideal_folder + 'pathogenic.tsv', 'Gene', sep='\t')
new_protective_list = get_list_from_csv(new_ideal_folder + 'protective.tsv', 'Gene', sep='\t')
old_pathogenic_list = get_list_from_csv(old_ideal_folder + 'pathogenic.txt', 'Gene', sep='\t')
old_protective_list = get_list_from_csv(old_ideal_folder + 'protective.txt', 'Gene', sep='\t')
#'''
venn_diagram(old_pathogenic_list, new_pathogenic_list, 'Old ver', 'New ver', 'APOE2-AD genes',
'APOE2_AD_genes_comparison')
venn_diagram(old_protective_list, new_protective_list, 'Old ver', 'New ver', 'APOE4-HC genes',
'APOE4_HC_genes_comparison')
#'''
cases = ADe2 + ADe3 + ADe4
controls = HCe2 + HCe3 + HCe4
trauma_folder = '/media/vision/ExtraDrive1/Exome/ADSP_discovery/all_short_name/'
output_folder = '/home/vision/Documents/GermlineProject/ADSP/iDEAL_updated_test_2019/'
EAListCase = []
EAListControl = []
# gene_file = output_folder + 'iDEAL_genelist.txt'
# candidate = get_list_from_csv(gene_file, 'Gene', sep='\t')
pathogenic_file = output_folder + 'pathogenic.txt'
protective_file = output_folder + 'protective.txt'
pathogenic_gene = get_list_from_csv(pathogenic_file, 'Gene', sep='\t')
protective_gene = get_list_from_csv(protective_file, 'Gene', sep='\t')
ptCounter = 0
for filename in os.listdir(trauma_folder):
ptFile = (os.path.join(trauma_folder, filename))
if filename in cases:
processGermlineFile(ptFile, EAListCase, pathogenic_gene)
elif filename in controls:
processGermlineFile(ptFile, EAListControl, pathogenic_gene)
ptCounter += 1
print(ptCounter)
getHistogram(EAListCase, EAListControl, 'pathogenic_CaseControl')
file1 = open(output_folder + 'pathogenic_case_control_kstest.txt', 'w')
for idx, output_list in enumerate(output_lists):
gene = gene_list[idx]
variant = variant_list[idx]
# info = [gene, variant] + output_list
info = output_list
writer.writerow(info)
if __name__ == '__main__':
input_folder = str(Path().absolute()) + '/input/'
output_folder = str(Path().absolute()) + '/output_ADSP_discovery/'
variant_file = input_folder + 'top_protective_variants.txt'
# variant_file = input_folder + 'top_pathogenic_variants.txt'
gene_list = get_list_from_csv(variant_file, 'Gene', sep='\t')
variant_list = get_list_from_csv(variant_file, 'Sub', sep='\t')
trauma_folder = '/media/vision/ExtraDrive1/Exome/ADSP_discovery/all_short_name/'
sift_list = []
pph2_list = []
cadd_list = []
for idx, gene in enumerate(gene_list):
variant = variant_list[idx]
flag = 0
print(gene, variant)
pt_counter = 0
for filename in os.listdir(trauma_folder):
ptFile = (os.path.join(trauma_folder, filename))
flag = get_variant_info(ptFile, gene, variant, flag)