upstream-extended/community/tools/biopython/base_distribution.py
1#!/usr/bin/env python
2"""
3 Calculate the frequency of the nucleotides, the length and the GC-Content of a fastafile
4 Bjoern Gruening
5"""
6
7
8import sys
9
10from Bio import SeqIO
11
12
13def __main__():
14 input_file = open(sys.argv[1], "r")
15 output_file = open(sys.argv[2], "w")
16
17 output_file.write("Gene\tA\tC\tG\tT\tLength\tCG%\n")
18
19 for record in SeqIO.parse(input_file, "fasta"):
20 gene_name = record.name
21
22 Acount = record.seq.count("A") + record.seq.count("a")
23 Ccount = record.seq.count("C") + record.seq.count("c")
24 Gcount = record.seq.count("G") + record.seq.count("g")
25 Tcount = record.seq.count("T") + record.seq.count("t")
26
27 seq_length = len(record.seq)
28
29 GCcontent = float(Ccount + Gcount) / seq_length
30
31 output_line = "%s\t%i\t%i\t%i\t%i\t%i\t%f\n" % (
32 gene_name,
33 Acount,
34 Ccount,
35 Gcount,
36 Tcount,
37 seq_length,
38 GCcontent,
39 )
40
41 output_file.write(output_line)
42
43 output_file.close()
44 input_file.close()
45
46
47if __name__ == "__main__":
48 __main__()