Supplemental Methods

Custom scripts

# Remove reads mapping to E. coli
#!bin/python

import os

FILES = (each for each in os.listdir(os.getcwd()) if each.endswith('.sam'))

for instance in FILES:
	FILE = open(instance)
	R1 = open('%s_R1_001_val_1.fq' %(instance.strip('.sam')))
	R2 = open('%s_R2_001_val_2.fq' %(instance.strip('.sam')))
	FilteredR1 = open('%s_Filtered_R1.fq' %(instance.strip('.sam')), 'a')
	FilteredR2 = open('%s_Filtered_R2.fq' %(instance.strip('.sam')), 'a')
	
	R1Dict = {}
	RList = []
	line = R1.readline()
	R1Barcode = line.split()[1]
	while line:
		RList.append(line.split()[0])
		R1Dict[line.split()[0]] = R1.readline()+R1.readline()+R1.readline()
		line = R1.readline()
	
	R2Dict = {}
	line = R2.readline()
	R2Barcode = line.split()[1]
	while line:
		R2Dict[line.split()[0]] = R2.readline()+R2.readline()+R2.readline()
		line = R2.readline()

	for line in FILE:
		if line[0] != '@':
			if int(line.split()[4]) >= 30:
				try:
					RList.remove('@'+line.split()[0])
				except ValueError:
					pass

	for seq in RList:
		FilteredR1.write(seq+' '+R1Barcode+'\n'+R1Dict[seq])
		FilteredR2.write(seq+' '+R2Barcode+'\n'+R2Dict[seq])

	FILE.close()
	R1.close()
	R2.close()
	FilteredR1.close()
	FilteredR2.close()		





#Split reads into subsets for assembly
#!bin/python

import os

FILES = (each for each in os.listdir(os.getcwd()) if each.endswith('.fastq'))

for instance in FILES:
	k = 1
	n = 1
	FILE = open(instance)
	OUT = open('%s_%s.fastq' %(instance.split('.')[0], str(k)), 'a')
	for line in FILE:
		if n <= 20000000:
			OUT.write(line)
			n += 1
		else:
			k += 1
			n = 2
			OUT.close()
			OUT = open('%s_%s.fastq' %(instance.split('.')[0], str(k)), 'a')
			OUT.write(line)
	FILE.close()
	OUT.close()