allpy: 321c37706049 test/usecase1.py

allpy

Reconfigured extract_pfam.py to convert the whole Pfam

author	Daniil Alexeyevsky <dendik@kodomo.fbb.msu.ru>
date	Fri, 08 Jul 2011 20:03:55 +0400
parents	07b5351b0b56
children	ddf85d0a8924

line source

1 import sys

2 from allpy import protein

3 from allpy import processors

5 # Create sequences from string representation of sequence body

6 sequence_1 = protein.Sequence.from_string("mkstf", name="E2E4")

7 sequence_2 = protein.Sequence.from_string("mstkfff", description="Longer sequence")

9 # Create alignment from sequences

10 alignment = protein.Alignment()

11 alignment.append_sequence(sequence_1)

12 alignment.append_sequence(sequence_2)

13 alignment.realign(processors.Muscle())

15 # For each sequence, print number of gaps and non-gaps in alignment

16 for row in alignment.rows():

17 gaps = 0

18 monomers = 0

19 for column in alignment.columns:

20 if column in row:

21 monomers += 1

22 else:

23 gaps += 1

24 print "%s: %s gaps, %s non-gaps" % (row.sequence.name, gaps, monomers)

26 # Print number of gaps in each column

27 gaps = []

28 for column in alignment.columns:

29 column_gaps = 0

30 for sequence in alignment.sequences:

31 if sequence not in column:

32 column_gaps += 1

33 gaps.append(column_gaps)

34 print " ".join(map(str, gaps))

36 # Write alignment to file

37 alignment.to_file(sys.stdout)