allpy: 38888b46c342 allpy/fasta.py

allpy

Added usecases from wiki to test/ directory

author	Daniil Alexeyevsky <me.dendik@gmail.com>
date	Fri, 17 Dec 2010 00:45:20 +0300
parents	316122b6b70e
children	01547d8d5c36

line source

1 def parse_file(file):

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

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

5 """

6 sequences = []

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

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

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

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

11 name = name.strip()

12 description = description.strip()

13 body = body.replace(" ", "").replace("\n", "")

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

15 return sequences

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

18 """ Saves given string to out_file in fasta_format

20 Splits long lines to substrings of length=long_line

21 To prevent this, set long_line=None

22 """

23 header = " ".join(filter(None, [name, description]))

24 out_file.write(">%s\n" % header)

25 if long_line:

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

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

28 else:

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

31 def determine_long_line(in_file):

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

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

34 for sequence in sequences[1:]:

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

36 if len(lines) >= 2:

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

38 return 70

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