comparison ensembl_longest_cds_per_gene.py @ 2:6cf9f7f6509c draft default tip

planemo upload for repository https://github.com/TGAC/earlham-galaxytools/tree/master/tools/ensembl_longest_cds_per_gene commit 651fae48371f845578753052c6fe173e3bb35670

1:a07680f3033a

"""
This script reads a CDS FASTA file from Ensembl and outputs a FASTA file with
only the longest CDS sequence for each gene. The header of the sequences in the
output file will be the transcript id without version.
"""
from __future__ import print_function

import collections
import optparse

def remove_id_version(s):
    """
    Remove the optional '.VERSION' from an Ensembl id.
    """
    return s.split('.')[0]


parser = optparse.OptionParser()
parser.add_option('-f', '--fasta', dest="input_fasta_filename",
                  help='CDS file in FASTA format from Ensembl')

gene_transcripts_dict = dict()

for entry in FASTAReader_gen(options.input_fasta_filename):
    transcript_id, rest = entry.header[1:].split(' ', 1)
    transcript_id = remove_id_version(transcript_id)
    gene_id = None
    for s in rest.split(' '):
        if s.startswith('gene:'):
            gene_id = remove_id_version(s[5:])
            break

# first one to appear in the FASTA file is selected
selected_transcript_ids = [max(transcript_id_lengths, key=lambda _: _[1])[0] for transcript_id_lengths in gene_transcripts_dict.values()]

with open(options.output_fasta_filename, 'w') as output_fasta_file:
    for entry in FASTAReader_gen(options.input_fasta_filename):
        transcript_id = remove_id_version(entry.header[1:].split(' ')[0])
        if transcript_id in selected_transcript_ids:
            output_fasta_file.write(">%s\n%s\n" % (transcript_id, entry.sequence))

2:6cf9f7f6509c

"""
This script reads a CDS FASTA file from Ensembl and outputs a FASTA file with
only the longest CDS sequence for each gene.
"""
from __future__ import print_function

import collections
import optparse

def remove_id_version(s):
    """
    Remove the optional '.VERSION' from an Ensembl id.
    """
    if s.startswith('ENS'):
        return s.split('.')[0]
    else:
        return s


parser = optparse.OptionParser()
parser.add_option('-f', '--fasta', dest="input_fasta_filename",
                  help='CDS file in FASTA format from Ensembl')

gene_transcripts_dict = dict()

for entry in FASTAReader_gen(options.input_fasta_filename):
    transcript_id, rest = entry.header[1:].split(' ', 1)
    gene_id = None
    for s in rest.split(' '):
        if s.startswith('gene:'):
            gene_id = remove_id_version(s[5:])
            break

# first one to appear in the FASTA file is selected
selected_transcript_ids = [max(transcript_id_lengths, key=lambda _: _[1])[0] for transcript_id_lengths in gene_transcripts_dict.values()]

with open(options.output_fasta_filename, 'w') as output_fasta_file:
    for entry in FASTAReader_gen(options.input_fasta_filename):
        transcript_id = entry.header[1:].split(' ')[0]
        if transcript_id in selected_transcript_ids:
            output_fasta_file.write("%s\n%s\n" % (entry.header, entry.sequence))