Created
May 14, 2018 20:01
-
-
Save fxia22/e6d96a3a9a89e813cb9169005d729ba8 to your computer and use it in GitHub Desktop.
process_ukbb
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
import os | |
import numpy as np | |
import matplotlib.pyplot as plt | |
import sys | |
from tqdm import tqdm | |
import pandas as pd | |
main_ukbb_file = sys.argv[1] | |
other_ukbb_files = sys.argv[1:] | |
nl = 0 | |
lines = [] | |
with open(main_ukbb_file) as f: | |
for line in tqdm(f): | |
if line[:2] == '1:': | |
lines.append(line.strip().split('\t')) | |
nl += 1 | |
name = [item[0] for item in lines] | |
pval = [float(item[-1]) for item in lines] | |
print(len(name)) | |
d = pd.read_csv('chr1phastcon.txt') | |
phastcon = np.array(d).flatten() | |
state = [] | |
with open('wgEncodeAwgSegmentationChromhmmGm12878.bed') as f: | |
for line in f: | |
state.append(line.split()[3]) | |
state = sorted(list(set(state))) | |
print(state) | |
chrom_state = np.zeros(250000000, ) | |
state_dict = dict(zip(state, range(len(state)))) | |
with open('wgEncodeAwgSegmentationChromhmmGm12878.bed') as f: | |
for line in tqdm(f): | |
ls = line.split() | |
if ls[0] != 'chr1': | |
break | |
start = int(ls[1]) | |
end = int(ls[2]) | |
state = ls[3] | |
chrom_state[start:end] = state_dict[state] | |
x = np.zeros((len(name), 2)) | |
p = np.zeros((len(name), )) | |
for i in tqdm(range(len(name))): | |
pos = int(name[i].split(':')[1]) | |
x[i,0] = chrom_state[pos] | |
x[i,1] = phastcon[pos] | |
p[i] = pval[i] | |
with open('{}.csv'.format(main_ukbb_file.split('.')[0]), 'w') as f: | |
f.write('x1, x2, p_value, h\n') | |
for i in range(x.shape[0]): | |
f.write("{}, {}, {}, {}\n".format(x[i, 0], x[i, 1], p[i], np.nan)) |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment