comparison script_imgt.py @ 5:048f8cdbb6d2 draft default tip

Uploaded

4:aa4b95abef11

parser = argparse.ArgumentParser()
parser.add_argument("--input", help="Excel input file containing one or more sheets where column G has the gene annotation, H has the sequence id and J has the sequence")
parser.add_argument("--ref", help="Reference file")
parser.add_argument("--output", help="Output file")

args = parser.parse_args()

refdic = dict()
with open(args.ref, 'r') as ref:

currentSeq = ""
currentId = ""
with open(args.input, 'r') as i:
	with open(args.output, 'w') as o:
		o.write(">>>IMGT\n")
		outputdic = dict()
		for line in i.readlines()[1:]:
			linesplt = line.split("\t")
			ref = filterGene(linesplt[1], vPattern)
			if not ref or not linesplt[2].rstrip():

5:048f8cdbb6d2

parser = argparse.ArgumentParser()
parser.add_argument("--input", help="Excel input file containing one or more sheets where column G has the gene annotation, H has the sequence id and J has the sequence")
parser.add_argument("--ref", help="Reference file")
parser.add_argument("--output", help="Output file")
parser.add_argument("--id", help="ID to be used at the '>>>' line in the output")

args = parser.parse_args()

refdic = dict()
with open(args.ref, 'r') as ref:

currentSeq = ""
currentId = ""
with open(args.input, 'r') as i:
	with open(args.output, 'a') as o:
		o.write(">>>" + args.id + "\n")
		outputdic = dict()
		for line in i.readlines()[1:]:
			linesplt = line.split("\t")
			ref = filterGene(linesplt[1], vPattern)
			if not ref or not linesplt[2].rstrip():