Mercurial > repos > jackcurragh > ribogalaxy_get_chrom_sizes

comparison get_chrom_sizes/calculating_chrom.sizes.py @ 21:cc021a23613b draft

Find changesets by keywords (author, files, the commit message), revision number or hash, or revset expression.
Uploaded
author jackcurragh
date Wed, 18 May 2022 08:47:20 +0000
parents 06c2eaff31e5
children feeee18b0084
comparison
equal deleted inserted replaced
20:147706e55621 21:cc021a23613b
2 # adapted from https://bioexpressblog.wordpress.com/2014/04/15/calculate-length-of-all-sequences-in-an-multi-fasta-file/ 2 # adapted from https://bioexpressblog.wordpress.com/2014/04/15/calculate-length-of-all-sequences-in-an-multi-fasta-file/
3 from sys import argv 3 from sys import argv
4 # python calculating_chrom.sizes.py genome_input.fa output.chrom.sizes 4 # python calculating_chrom.sizes.py genome_input.fa output.chrom.sizes
5 fasta_source = str(argv[1]) 5 fasta_source = str(argv[1])
6 prefix = str(argv[2]) 6 prefix = str(argv[2])
7 # output = str(argv[3])
8 genome = str(argv[3]) 7 genome = str(argv[3])
9 builtin = str(argv[4]) 8 builtin = str(argv[4])
9 output = str(argv[5])
10 10
11 # genome = 'test-data/test.fasta' 11 # genome = 'test-data/test.fasta'
12 # output = "test-data/test_chrom.sizes" 12 # output = "test-data/test_chrom.sizes"
13 if fasta_source == 'builtin': 13 if fasta_source == 'builtin':
14 genome = builtin 14 genome = builtin
28 record[1] += len(sequence) 28 record[1] += len(sequence)
29 29
30 if record not in records: 30 if record not in records:
31 records.append(record) 31 records.append(record)
32 32
33
34
33 for seq_record in records: 35 for seq_record in records:
34 if prefix != 'none': 36 if prefix != 'none':
35 output_line = f"{prefix}{seq_record[0]}\t{seq_record[1]}\n" 37 output_line = f"{prefix}{seq_record[0]}\t{seq_record[1]}\n"
36 else: 38 else:
37 output_line = f"{seq_record[0]}\t{seq_record[1]}\n" 39 output_line = f"{seq_record[0]}\t{seq_record[1]}\n"