def set_1bp_list():
chromLens = genutils.read_chrom_len(chromLenFile)
counts = {}
for chromName in chromLens:
counts[chromName] = []
# if chromName != "chr1":
# continue
for i in range(0,chromLens[chromName] + 1):
counts[chromName].append("")
return counts
def set_1bp_list():
chromLens = genutils.read_chrom_len(chromLenFile)
counts = {}
for chromName in chromLens:
counts[chromName] = []
# if chromName != "chr1":
# continue
for i in range(0, chromLens[chromName] + 1):
counts[chromName].append("")
return counts
# Used for NA19240
import argparse
import os
import signal
import glob
import pandas as pd
import numpy as np
import math
from NGS_utils import *
import pickle
import subprocess
import genutils
chromLenFile = '/home/jmkidd/kidd-lab/genomes/hg19/hg19-EBV-fos-ecoli/hg19.fa.fai'
chromLens = genutils.read_chrom_len(chromLenFile)
chromOrder = get_chromOrder("human")
def create_snp_list(all_var_file):
f = open(all_var_file, "r")
snp_pos = []
snp_geno = []
snp_phase = []
for line in f:
line = line.strip().split("\t")
chr = line[0]
# if chr != "chr1" and chr!="chr2":
# break
if chr != CHROM and chromOrder[chr] < chromOrder[CHROM]:
continue
c = l.split()[0] chromOrder[c] = i return chromOrder def get_chromList(): # chromLenFile = '/home/jmkidd/kidd-lab/genomes/hg19/hg19-EBV-fos-ecoli/hg19.fa.fai' chromLenFile = '/home/jmkidd/kidd-lab/genomes/hg18/genome-index/hg18.fa.fai' chr_list=[] inFile = open(chromLenFile,'r') for i,l in enumerate(inFile): l = l.rstrip() c = l.split()[0] chr_list.append(c) return chr_list chromLenFile = '/home/jmkidd/kidd-lab/genomes/hg19/hg19-EBV-fos-ecoli/hg19.fa.fai' chromLens = genutils.read_chrom_len(chromLenFile) class BedIterator: def __init__(self, filename): if filename[-2:]=='gz': self.file = gzip.open(filename, "r") else: self.file = open(filename, "r") def __iter__(self): return self def __next__(self): return self.next() def next(self): line = next(self.file) fields = line.rstrip().split() return tuple(fields)
def find_clone_cov(pool_name, sample_name):
windowFile = '/home/jmkidd/kidd-lab-scratch/shiya-projects/indian_Jacob/script/new_genome_window.txt'
windowSize = 1000.0 # assume each window is 1000 unmasked bp
chromLenFile = '/home/jmkidd/kidd-lab/genomes/hg19/hg19-EBV-fos-ecoli/hg19.fa.fai'
chromLens = genutils.read_chrom_len(chromLenFile)
coverage = {}
counts = {}
pos1 = {}
pos2 = {}
print 'Initializing chrom lists'
for chromName in chromLens:
counts[chromName] = []
coverage[chromName] = []
pos1[chromName] = []
pos2[chromName] = []
f = open(windowFile, 'r')
for line in f:
line = line.rstrip()
line = line.split("\t")
c = line[0]
if c == "EBV" or c == "eColiK12" or c == "pCC1FOS":
continue
b = int(line[1])
e = int(line[2])
counts[c].append(0)
coverage[c].append(0)
pos1[c].append(b)
pos2[c].append(e)
outDirBase = '/home/jmkidd/kidd-lab/jmkidd-projects/additional-fosmid-pools/results/pools/%s/' % (
sample_name)
poolNames = pool_name.keys()
poolNames.sort()
minLen = 10000
minDP = 0.25
for pool in poolNames:
baseDir = outDirBase + pool + '/'
cloneFileName = baseDir + pool + '.markdup.clone'
inFileName = cloneFileName + '.sel.%i.%.2f' % (minLen, minDP)
f = open(inFileName, 'r')
for line in f:
line = line.rstrip()
line = line.split()
if line[0] == 'track':
continue
chr = line[0]
start = int(line[1])
end = int(line[2])
cov = float(line[3])
size = int(line[4]) / 1000
find1 = find_pos(start - 1, pos1[chr])
find2 = find_pos(end, pos2[chr])
if find1 >= 0:
for j in range(find1, find2 + 1):
if j < len(counts[chr]):
counts[chr][j] += 1
coverage[chr][j] += cov
else:
print line, find1, find2, len(counts[chr])
else:
print 'not found', chr, start
'''
f=open(windowFile,'r')
i = 0
outFile = open("wgs_clone_coverage.txt","w")
old_c="chr1"
for line in f:
line = line.rstrip()
line = line.split("\t")
c = line[0]
if c!=old_c:
i = 0
old_c = c
if c=="EBV" or c=="eColiK12" or c=="pCC1FOS":
continue
b = int(line[1]) + 1 #make them all 1 based
e = int(line[2])
outFile.write('%s\t%i\t%i\t%f\t%i\n' % (c,b,e,coverage[c][i],counts[c][i]))
i +=1
dbfile=open('NA19240_wgs_clone_coverage_pickle','wb')
pickle.dump(counts,dbfile)
pickle.dump(coverage,dbfile)
'''
return counts, coverage
def find_clone_cov(pool_name,sample_name):
windowFile = '/home/jmkidd/kidd-lab-scratch/shiya-projects/indian_Jacob/script/new_genome_window.txt'
windowSize = 1000.0 # assume each window is 1000 unmasked bp
chromLenFile = '/home/jmkidd/kidd-lab/genomes/hg19/hg19-EBV-fos-ecoli/hg19.fa.fai'
chromLens = genutils.read_chrom_len(chromLenFile)
coverage = {}
counts = {}
pos1 = {}
pos2 = {}
print 'Initializing chrom lists'
for chromName in chromLens:
counts[chromName] = []
coverage[chromName] = []
pos1[chromName]=[]
pos2[chromName]=[]
f=open(windowFile,'r')
for line in f:
line = line.rstrip()
line = line.split("\t")
c = line[0]
if c=="EBV" or c=="eColiK12" or c=="pCC1FOS":
continue
b = int(line[1])
e = int(line[2])
counts[c].append(0)
coverage[c].append(0)
pos1[c].append(b)
pos2[c].append(e)
outDirBase= '/home/jmkidd/kidd-lab/jmkidd-projects/additional-fosmid-pools/results/pools/%s/' %(sample_name)
poolNames = pool_name.keys()
poolNames.sort()
minLen = 10000
minDP = 0.25
for pool in poolNames:
baseDir = outDirBase+pool + '/'
cloneFileName = baseDir + pool + '.markdup.clone'
inFileName = cloneFileName + '.sel.%i.%.2f' % (minLen,minDP)
f = open(inFileName,'r')
for line in f:
line = line.rstrip()
line = line.split()
if line[0] == 'track':
continue
chr = line[0]
start = int(line[1])
end = int(line[2])
cov = float(line[3])
size = int(line[4])/1000
find1 = find_pos(start-1,pos1[chr])
find2 = find_pos(end,pos2[chr])
if find1>=0:
for j in range(find1,find2+1):
if j < len(counts[chr]):
counts[chr][j]+=1
coverage[chr][j]+=cov
else:
print line,find1,find2,len(counts[chr])
else:
print 'not found',chr,start
'''
f=open(windowFile,'r')
i = 0
outFile = open("wgs_clone_coverage.txt","w")
old_c="chr1"
for line in f:
line = line.rstrip()
line = line.split("\t")
c = line[0]
if c!=old_c:
i = 0
old_c = c
if c=="EBV" or c=="eColiK12" or c=="pCC1FOS":
continue
b = int(line[1]) + 1 #make them all 1 based
e = int(line[2])
outFile.write('%s\t%i\t%i\t%f\t%i\n' % (c,b,e,coverage[c][i],counts[c][i]))
i +=1
dbfile=open('NA19240_wgs_clone_coverage_pickle','wb')
pickle.dump(counts,dbfile)
pickle.dump(coverage,dbfile)
'''
return counts,coverage