allpy: 2ede0318ff95 allpy/fasta.py

allpy

Added virtual monomer types for undefined letters N and X, changed all previous such monomers to be considered modified

author	Daniil Alexeyevsky <me.dendik@gmail.com>
date	Fri, 21 Jan 2011 17:01:21 +0300
parents	6ad74e2ba3d2
children	695c8a42bf1e

line source

1 import util

3 def parse_file(file):

4 """Parse fasta file, remove spaces and newlines from sequence bodies.

6 Return a list of tuples (name, description, sequence_body).

7 """

8 sequences = []

9 for part in file.read().split("\n>"):

10 header, _, body = part.partition("\n")

11 header = header.lstrip(">").strip()

12 name, _, description = header.partition(" ")

13 name = name.strip()

14 description = description.strip()

15 body = util.remove_each(body, " \n\r\t\v")

16 sequences.append((name, description, body))

17 return sequences

19 def save_file(out_file, string, name, description='', long_line=70):

20 """ Saves given string to out_file in fasta_format

22 Splits long lines to substrings of length=long_line

23 To prevent this, set long_line=None

24 """

25 if description:

26 name += " " + description

27 out_file.write(">%s\n" % name)

28 if long_line:

29 for i in range(0, len(string) // long_line + 1):

30 out_file.write("%s \n" % string[i*long_line : i*long_line + long_line])

31 else:

32 out_file.write("%s \n" % string)

34 def determine_long_line(in_file):

35 """ Returns maximum sequence line length in fasta file """

36 sequences = in_file.read().split('>')

37 for sequence in sequences[1:]:

38 lines = sequence.split('\n')[1:]

39 if len(lines) >= 2:

40 return len(lines[0].strip())

41 return 70

43 # vim: set ts=4 sts=4 sw=4 et: