comparison UMI_riboseq_processing/UMI.py @ 3:d27375bc4a1c draft

Uploaded
author triasteran
date Mon, 20 Jun 2022 08:02:35 +0000
parents 6958515efa76
children a580e700aac3
comparison
equal deleted inserted replaced
2:6958515efa76 3:d27375bc4a1c
17 for lines in grouper(f, chunk_size, ""): #for every chunk_sized chunk 17 for lines in grouper(f, chunk_size, ""): #for every chunk_sized chunk
18 header = lines[0] 18 header = lines[0]
19 seq = lines[1] 19 seq = lines[1]
20 sep = lines[2] 20 sep = lines[2]
21 qual = lines[3] 21 qual = lines[3]
22 trimmed_seq = seq[2:-5]+"\n" # fooprint + barcode 22 trimmed_seq = seq[2:-6]+"\n" # fooprint + barcode
23 UMI = seq[0:2]+seq[-5:].strip('\n') #7nt in total; 5'NN and last 3'NNNNN 23 UMI = seq[0:2]+seq.rstrip()[-5:] #7nt in total; 5'NN and last 3'NNNNN
24 split_header = header.split(" ") 24 split_header = header.split(" ")
25 new_header = split_header[0]+"_"+UMI+" "+split_header[1] 25 new_header = split_header[0]+"_"+UMI+" "+split_header[1]
26 if qual[-1:] == "\n": 26 if qual[-1:] == "\n":
27 new_qual = qual[2:-5]+"\n" 27 new_qual = qual[2:-6]+"\n"
28 else: 28 else:
29 new_qual = qual[2:-5] 29 new_qual = qual[2:-6]
30 output.write(new_header) 30 output.write(new_header)
31 output.write(trimmed_seq) 31 output.write(trimmed_seq)
32 output.write(sep) 32 output.write(sep)
33 output.write(new_qual) 33 output.write(new_qual)
34 34