1
|
1 # input a genome file and return a file genome.chrom.sizes to be associated with the custom build (or just have it as an output to be used later in the history.
|
|
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
|
|
4 # python calculating_chrom.sizes.py genome_input.fa output.chrom.sizes
|
|
5 genome = str(argv[1])
|
|
6 output = str(argv[2])
|
|
7 # genome = 'test-data/test.fasta'
|
|
8 # output = "test-data/test_chrom.sizes"
|
|
9
|
|
10 chromSizesoutput = open(output,"w")
|
|
11
|
|
12 records = []
|
|
13 record = False
|
|
14 for line in open(genome, 'r').readlines():
|
|
15 if line[0] == '>':
|
|
16 if record:
|
|
17 records.append(record)
|
|
18 record = [line.strip("\n").split(' ')[0][1:], 0]
|
|
19
|
|
20 else:
|
|
21 sequence = line.strip('\n')
|
|
22 record[1] += len(sequence)
|
|
23
|
|
24 for seq_record in records:
|
|
25 output_line = '%s\t%i\n' % (seq_record[0], seq_record[1])
|
|
26 chromSizesoutput.write(output_line)
|
|
27
|
|
28 chromSizesoutput.close()
|