Example #1
0
#!/usr/bin/env python
__author__ = 'Sergei F. Kliver'
import argparse

from Routines import AnnotationsRoutines

parser = argparse.ArgumentParser()

parser.add_argument("-i",
                    "--input_gff",
                    action="store",
                    dest="input_gff",
                    help="Gff file with annotations to extract")
parser.add_argument("-o",
                    "--output_gff",
                    action="store",
                    dest="output_gff",
                    help="Output gff file with extracted transcripts")
parser.add_argument("-d",
                    "--ids_file",
                    action="store",
                    dest="ids_file",
                    help="File with ids of transcripts to extract")

args = parser.parse_args()

AnnotationsRoutines.extract_transcripts_by_ids(args.input_gff, args.ids_file,
                                               args.output_gff)
Example #2
0
    SequenceRoutines.extract_sequence_by_ids(
        output_pep, "%s.ids" %
        output_swissprot_pfam_or_hints_supported_transcripts_longest_pep_evidence,
        output_swissprot_pfam_or_hints_supported_transcripts_longest_pep)
    SequenceRoutines.extract_sequence_by_ids(
        output_pep, "%s.ids" %
        output_swissprot_pfam_and_hints_supported_transcripts_longest_pep_evidence,
        output_swissprot_pfam_and_hints_supported_transcripts_longest_pep)

    for id_file in output_swissprot_pfam_or_hints_supported_transcripts_ids, \
                   output_swissprot_pfam_and_hints_supported_transcripts_ids, \
                   "%s.ids" % output_swissprot_pfam_or_hints_supported_transcripts_longest_pep_evidence, \
                   "%s.ids" % output_swissprot_pfam_and_hints_supported_transcripts_longest_pep_evidence:
        out_pref = id_file[:-4]
        out_gff = "%s.gff" % out_pref
        AnnotationsRoutines.extract_transcripts_by_ids(output_gff, id_file,
                                                       out_gff)
        for suffix in ".trimmed.cds", ".transcript":
            SequenceRoutines.extract_sequence_by_ids(
                "%s%s" % (args.output, suffix), id_file,
                "%s%s" % (out_pref, suffix))

    HMMER3.intersect_ids_from_files(
        output_swissprot_pfam_or_hints_supported_transcripts_ids,
        cds_with_inframe_stop_codons_ids,
        output_swissprot_pfam_or_hints_supported_transcripts_inframe_stop_ids,
        mode="common")

    HMMER3.intersect_ids_from_files(
        output_swissprot_pfam_and_hints_supported_transcripts_ids,
        cds_with_inframe_stop_codons_ids,
        output_swissprot_pfam_and_hints_supported_transcripts_inframe_stop_ids,