comparison fasta_concatenate_by_species.py @ 2:c5311b7718d1 draft

"planemo upload for repository https://github.com/galaxyproject/tools-devteam/tree/master/tools/fasta_concatenate_by_species commit cd1ed08574b749eee2a3f6e6151dbb0c8ca15bbf"

1:d9f0a11824e9

#!/usr/bin/env python
#Dan Blankenberg
"""
Takes a Multiple Alignment FASTA file and concatenates 
sequences for each species, resulting in one sequence 
alignment per species.
"""

import sys, tempfile
from utils.maf_utilities import iter_fasta_alignment
from utils.odict import odict

def __main__():
    input_filename = sys.argv[1]
    output_filename = sys.argv[2]
    species = odict()
    cur_size = 0
    for components in iter_fasta_alignment( input_filename ):
        species_not_written = species.keys()
        for component in components:
            if component.species not in species:
                species[component.species] = tempfile.TemporaryFile()
                species[component.species].write( "-" * cur_size )
            species[component.species].write( component.text )
            try:
                species_not_written.remove( component.species )
            except ValueError:
                #this is a new species
                pass
        for spec in species_not_written:
            species[spec].write( "-" * len( components[0].text ) )
        cur_size += len( components[0].text )
    out = open( output_filename, 'wb' )
    for spec, f in species.iteritems():
        f.seek( 0 )
        out.write( ">%s\n%s\n" % ( spec, f.read() ) )
    out.close()

if __name__ == "__main__" : __main__()

2:c5311b7718d1

#!/usr/bin/env python
# Dan Blankenberg
"""
Takes a Multiple Alignment FASTA file and concatenates
sequences for each species, resulting in one sequence
alignment per species.
"""

import sys
import tempfile
from collections import OrderedDict

from utils.maf_utilities import iter_fasta_alignment


def __main__():
    input_filename = sys.argv[1]
    output_filename = sys.argv[2]
    species = OrderedDict()
    cur_size = 0
    for components in iter_fasta_alignment(input_filename):
        species_not_written = list(species.keys())
        for component in components:
            if component.species not in species:
                species[component.species] = tempfile.TemporaryFile(mode="r+")
                species[component.species].write("-" * cur_size)
            species[component.species].write(component.text)
            try:
                species_not_written.remove(component.species)
            except ValueError:
                # this is a new species
                pass
        for spec in species_not_written:
            species[spec].write("-" * len(components[0].text))
        cur_size += len(components[0].text)
    with open(output_filename, 'w') as out:
        for spec, f in species.items():
            f.seek(0)
            out.write(">%s\n%s\n" % (spec, f.read()))


if __name__ == "__main__":
    __main__()