def main():
parser = argparse.ArgumentParser()
parser.add_argument('--cancerType', dest='type',\
help='Cancer type to be collected')
parser.add_argument('--getData',dest='get', action='store_true',\
default=False,help='Set flag to get all data')
opts = parser.parse_args()
if opts.get:
for ds in ['brca', 'ccrcc', 'colon', 'ovarian', 'endometrial', 'luad']:
cptac.download(dataset=ds)
if opts.type.lower() == 'brca':
dat = cptac.Brca()
elif opts.type.lower() == 'ccrcc':
dat = cptac.Ccrcc()
elif opts.type.lower() == 'coad':
dat = cptac.Colon()
elif opts.type.lower() == 'ovca':
dat = cptac.Ovarian()
elif opts.type.lower() == 'luad':
dat = cptac.Luad()
elif opts.type.lower() == 'endometrial':
dat = cptac.Endometrial()
else:
exit()
df = dat.get_phosphoproteomics()
pdf = dat.get_proteomics()
# df.columns = [' '.join(col).strip() for col in df.columns.values]
df.to_csv(path_or_buf="phos_file.tsv", sep='\t')
pdf.to_csv(path_or_buf='prot_file.tsv', sep='\t')
def compute_regression(input_cancer_type):
if input_cancer_type == "CCRCC":
cancer = cptac.Ccrcc()
elif input_cancer_type == "Endometrial":
cancer = cptac.Endometrial()
elif input_cancer_type == "LUAD":
cancer = cptac.Luad()
elif input_cancer_type == "HNSCC":
cancer = cptac.Hnscc()
elif input_cancer_type == "LSCC":
cancer = cptac.Lscc()
elif input_cancer_type == "PDAC":
cancer = cptac.Pdac()
df = dc.get_prot_trans_df(cancer)
results = df.groupby('Gene').apply(regression)
reg_df = pd.DataFrame(list(results))
reg_df.index = results.index
reg_df.reset_index(inplace=True)
reg_df = reg_df.dropna()
reg_df['interaction_FDR'] = ssm.fdrcorrection(
reg_df['interaction_pval'])[1]
reg_df['condition_FDR'] = ssm.fdrcorrection(reg_df['condition_pval'])[1]
reg_df['intercept_FDR'] = ssm.fdrcorrection(reg_df['intercept_pval'])[1]
reg_df['Cancer'] = [input_cancer_type] * len(reg_df)
file_name = input_cancer_type + '_regressions.csv'
reg_df.to_csv(file_name, index=False)
def load_cancers(include_pdac=False):
ccrcc = cptac.Ccrcc()
en = cptac.Endometrial()
luad = cptac.Luad()
hnscc = cptac.Hnscc()
lscc = cptac.Lscc()
cancers = [ccrcc, en, luad, hnscc, lscc]
cancer_names = ['CCRCC', 'Endometrial', 'LUAD', 'HNSCC', 'LSCC']
if include_pdac:
pdac = cptac.Pdac()
cancers.append(pdac)
cancer_names.append('PDAC')
return cancers, cancer_names
def getDataForCancer(ctype):
if ctype.lower() == 'brca':
dat = cptac.Brca()
elif ctype.lower() == 'ccrcc':
dat = cptac.Ccrcc()
elif ctype.lower() == 'coad':
dat = cptac.Colon()
elif ctype.lower() == 'ovca':
dat = cptac.Ovarian()
elif ctype.lower() == 'luad':
dat = cptac.Luad()
elif ctype.lower() == 'endometrial':
dat = cptac.Endometrial()
else:
exit()
return dat
def __init__(self):
cptac.download(dataset="endometrial", version='latest')
# cptac.download(dataset="brca", version='latest')
# cptac.download(dataset="gbm", version='latest')
# cptac.download(dataset="hsncc", version='latest')
# cptac.download(dataset="luad", version='latest')
cptac.download(dataset="ovarian", version='latest')
cptac.download(dataset="ccrcc", version='latest')
cptac.download(dataset="colon", version='latest')
self.en = cptac.Endometrial()
# self.brca = cptac.Brca()
# self.gbm = cptac.Gbm()
# self.hsncc = cptac.Hnscc()
# self.luad= cptac.Luad()
self.ovarian = cptac.Ovarian()
self.ccrcc = cptac.Ccrcc()
self.colon = cptac.Colon()
# self.datasets = list(self.en,self.brca,self.gbm,self.hsncc,self.luad,self.ovarian,self.ccrcc)
self.datasets = list([self.en, self.ovarian, self.ccrcc, self.colon])
def cptacData():
'''
We need to collect and load CPTAC data
'''
print("Loading cptac datasets")
#we need to make sure all datasets are downloaded
##here are the cancers that are available without login information
allcans = ['brca', 'ccrcc', 'colon', 'ovarian', 'luad',\
#'hnscc','gbm','lscc',\
'endometrial']
print("Downloading cptac data")
for ct in allcans:
cptac.download(dataset=ct)
#then we load them into a dictionary
fdict = {'brca':cptac.Brca(), 'ccrcc':cptac.Ccrcc(),\
'colon':cptac.Colon(), 'ovarian':cptac.Ovarian(),\
#'hnscc':cptac.Hnscc(),'gbm':cptac.Gbm(), 'lscc':cptac.Lscc(),\
'endometrial':cptac.Endometrial(), 'luad':cptac.Luad()}
return fdict
def test_get_frequently_mutated_renal_01_cutoff():
rc = cptac.Ccrcc()
print('Running get_frequently_mutated...')
df = ut.get_frequently_mutated(rc, cutoff=0.01)
dimensions = (1106, 4)
headers = ['Gene', 'Unique_Samples_Mut', 'Missense_Mut', 'Truncation_Mut']
# test genes names
test_coord_names = ((11, 0), (992, 0), (1080, 0))
test_vals_names = ('ABCC3', 'TTN', 'ZNF532')
total_tumors = 110
# test no missense
test_coord_ABCC3 = ((11, 1), (11, 2), (11, 3))
test_vals_ABCC3 = (2 / total_tumors, 0 / total_tumors, 2 / total_tumors)
# test no truncation and close to cutoff
test_coord_ZNF532 = ((1080, 1), (1080, 2), (1080, 3))
test_vals_ZNF532 = (2 / total_tumors, 2 / total_tumors, 0 / total_tumors)
# test miss and trunc equal to unique_samples_mutated
test_coord_NAV3 = ((611, 1), (611, 2), (611, 3))
test_vals_NAV3 = (7 / total_tumors, 5 / total_tumors, 2 / total_tumors)
# check that silent mutations are not counted (TTN has many silent mutations)
# and missense and trucation not equal to unique_samples_mutated
test_coord_TTN = ((992, 1), (992, 2), (992, 3))
test_vals_TTN = (13 / total_tumors, 10 / total_tumors, 4 / total_tumors)
# common test and highest count
test_coord_VHL = ((1019, 1), (1019, 2), (1019, 3))
test_vals_VHL = (82 / total_tumors, 33 / total_tumors, 49 / total_tumors)
test_coord_vals = [(test_coord_names, test_vals_names),
(test_coord_ABCC3, test_vals_ABCC3),
(test_coord_ZNF532, test_vals_ZNF532),
(test_coord_NAV3, test_vals_NAV3),
(test_coord_TTN, test_vals_TTN),
(test_coord_VHL, test_vals_VHL)]
for coord, val in test_coord_vals:
PASS = check_getter(df, dimensions, headers, coord, val)
print_test_result(PASS)
def test_get_frequently_mutated_renal_default_cutoff():
rc = cptac.Ccrcc()
print('Running get_frequently_mutated...')
df = ut.get_frequently_mutated(rc)
dimensions = (6, 4)
headers = ['Gene', 'Unique_Samples_Mut', 'Missense_Mut', 'Truncation_Mut']
# test genes names
test_coord_names = ((0, 0), (2, 0), (4, 0))
test_vals_names = ('BAP1', 'PBRM1', 'TTN')
total_tumors = 110
# test miss and trunc equal to unique_samples_mutated
test_coord_BAP1 = ((0, 1), (0, 2), (0, 3))
test_vals_BAP1 = (17 / total_tumors, 7 / total_tumors, 10 / total_tumors)
# test high truncation, low missense count
test_coord_PBRM1 = ((2, 1), (2, 2), (2, 3))
test_vals_PBRM1 = (44 / total_tumors, 8 / total_tumors, 37 / total_tumors)
# check that silent mutations are not counted (TTN has many silent mutations)
# and missense and trucation not equal to unique_samples_mutated
test_coord_TTN = ((4, 1), (4, 2), (4, 3))
test_vals_TTN = (13 / total_tumors, 10 / total_tumors, 4 / total_tumors)
# test close to cutoff
test_coord_SETD2 = ((3, 1), (3, 2), (3, 3))
test_vals_SETD2 = (15 / total_tumors, 2 / total_tumors, 13 / total_tumors)
# common test and highest count
test_coord_VHL = ((5, 1), (5, 2), (5, 3))
test_vals_VHL = (82 / total_tumors, 33 / total_tumors, 49 / total_tumors)
test_coord_vals = [(test_coord_names, test_vals_names),
(test_coord_BAP1, test_vals_BAP1),
(test_coord_PBRM1, test_vals_PBRM1),
(test_coord_TTN, test_vals_TTN),
(test_coord_SETD2, test_vals_SETD2),
(test_coord_VHL, test_vals_VHL)]
for coord, vals in test_coord_vals:
PASS = check_getter(df, dimensions, headers, coord, vals)
print_test_result(PASS)
warnings.filterwarnings('ignore')
currentdir = os.path.dirname(
os.path.realpath('Make_Cancer_Delta_Corr_and_P_Value_Dataframe'))
parentdir = os.path.dirname(currentdir)
parentdir = os.path.dirname(parentdir)
sys.path.append(parentdir)
import Delta_Correlation as dc
input_cancer_type = sys.argv[1]
mutated_gene = sys.argv[2]
input_permutation_number = int(sys.argv[3])
cutoff = 15
if input_cancer_type == "CCRCC":
cancer = cptac.Ccrcc()
elif input_cancer_type == "Endometrial":
cancer = cptac.Endometrial()
cutoff = 10
elif input_cancer_type == "LUAD":
cancer = cptac.Luad()
elif input_cancer_type == "HNSCC":
cancer = cptac.Hnscc()
elif input_cancer_type == "LSCC":
cancer = cptac.Lscc()
elif input_cancer_type == "PDAC":
cancer = cptac.Pdac()
mutation_df = cancer.get_somatic_mutation()
mutation_df = mutation_df[mutation_df.Gene == mutated_gene]
mutation_df = mutation_df[mutation_df.Mutation != 'Silent']
test_coord_1 = ((index_1, 1), (index_2, 1), (index_3, 1)) # C3N-01515
test_vals_1 = ('No_Mutation', 'No_Mutation', 'No_Mutation')
# Test Del
test_coord_2 = ((index_4, 1), (index_5, 1), (index_6, 1))
test_vals_2 = ('Deletion', 'Deletion', 'Deletion')
# Test Amp
test_coord_3 = ((index_7, 1), (index_8, 1), (index_9, 1))
test_vals_3 = ('Amplification', 'Amplification', 'Amplification')
test_coord_vals = [(test_coord_1, test_vals_1),
(test_coord_2, test_vals_2),
(test_coord_3, test_vals_3)]
for coord, vals in test_coord_vals:
PASS = check_getter(df, dimensions, headers, coord, vals)
print_test_result(PASS)
k = cptac.Ccrcc()
g = cptac.Gbm()
h = cptac.Hnscc()
print("\nRunning tests:\n")
test_genotype_ccrcc_KRAS()
test_genotype_gbm_KRAS()
test_genotype_hnscc_KRAS()
print("Version:", cptac.version())
import numpy as np
import math
import pandas as pd
#import statistics
# import parse_correlations_dataframe as get_corr
import copy
import csv
# import get_correlations
import cptac.utils as ut
import warnings
warnings.filterwarnings("ignore")
input_cancer_type = sys.argv[1]
if input_cancer_type == "ccrcc":
ccrcc = cptac.Ccrcc()
cancer_list = [ccrcc]
elif input_cancer_type == "en":
en = cptac.Endometrial()
cancer_list = [en]
elif input_cancer_type == "luad":
luad = cptac.Luad()
cancer_list = [luad]
elif input_cancer_type == "hnscc":
hnscc = cptac.Hnscc()
cancer_list = [hnscc]
elif input_cancer_type == "lscc":
lscc = cptac.Lscc()
cancer_list = [lscc]
# brca = cptac.Brca()
# ccrcc = cptac.Ccrcc()