Jaccard_index/codescript/rtg_pairs.py

import itertools
import pandas as pd
import sys,argparse,os

parser = argparse.ArgumentParser(description="this script is to preform combination on vcf files, get any two of them for next jaccard index calculation")

parser.add_argument('-vcf', '--vcffile', type=str, help='input vcf file',  required=True)

args = parser.parse_args()

# Rename input:
vcf_input = args.vcffile


file = pd.read_csv(vcf_input,header=None,sep='\t')
com = list(itertools.combinations(file[0],2))

outfile = open('rtg_pairs.txt','w')

for pair in com:
	# prepare a
	one = pair[0].strip().split('/')
	file_a = one[len(one)-1]
	a = one[len(one)-1].replace('.normed.vcf.gz','')
	strings_a = a.strip().split('_')
	sequenceTechA = strings_a[0] + strings_a[1]
	sequenceSiteA = strings_a[2]
	sampleA = strings_a[3]
	repA = strings_a[4]
#	analysisSiteA = strings_a[8]
#	pipelineA = strings_a[9] + strings_a[10]

	# prepare b
	two = pair[1].strip().split('/')
	file_b = two[len(two)-1]
	b = two[len(two)-1].replace('.normed.vcf.gz','')
	strings_b = b.strip().split('_')
	sequenceTechB = strings_b[0] + strings_b[1]
	sequenceSiteB = strings_b[2]
	sampleB = strings_b[3]
	repB = strings_b[4]
#	analysisSiteB = strings_b[8]
#	pipelineB = strings_b[9] + strings_b[10]

	folder = a + '-' + b
	## add annotation
	# sequencing technology
	if (sequenceTechA != sequenceTechB) and (sequenceSiteA == sequenceSiteB) and (sampleA == sampleB):
		outline = file_a + '\t' + file_b + '\t' + folder + '\t' + 'sequenceTech' + '\n'
		outfile.write(outline)
	# sequencing site
	elif (sequenceTechA == sequenceTechB) and (sequenceSiteA != sequenceSiteB) and (sampleA == sampleB):
		outline = file_a + '\t' + file_b + '\t' + folder + '\t' + 'sequenceSite' + '\n'
		outfile.write(outline)
	# sample
	elif (sequenceTechA == sequenceTechB) and (sequenceSiteA == sequenceSiteB) and (sampleA != sampleB):
		outline = file_a + '\t' + file_b + '\t' + folder + '\t' + 'Sample' + '\n'
		outfile.write(outline)	
	# replicate
	elif (sequenceTechA == sequenceTechB) and (sequenceSiteA == sequenceSiteB) and (sampleA == sampleB) and (repA != repB):
		outline = file_a + '\t' + file_b + '\t' + folder + '\t' + 'replicate' + '\n'
		outfile.write(outline)		
	# analysis site
#	elif (sequenceTechA == sequenceTechB) and (sequenceSiteA == sequenceSiteB) and (sampleA == sampleB):
#		outline = pair[0] + '\t' + pair[1] + '\t' + folder + '\t' + 'analysisSite' + '\n'
#		outfile.write(outline)	
	# pipeline
#	elif (sequenceTechA == sequenceTechB) and (sequenceSiteA == sequenceSiteB) and (sampleA == sampleB) and (analysisSiteA == analysisSiteB) and (pipelineA != pipelineB):
#		outline = pair[0] + '\t' + pair[1] + '\t' + folder + '\t' + 'pipeline' + '\n'
#		outfile.write(outline)	
	else:
		pass

outfile.close()