comparison gstf_preparation.py @ 10:e8e75a79de59 draft

"planemo upload for repository https://github.com/TGAC/earlham-galaxytools/tree/master/tools/gstf_preparation commit 9c8611fee927883f50bc6955771aa69df1ce8457"

9:f4acbfe8d6fe

from __future__ import print_function

import json
import optparse
import sqlite3
import sys

version = "0.4.0"
gene_count = 0

    if parent_dict is not None and 'Parent' in d:
        # a 3' UTR can be split among multiple exons
        # a 5' UTR can be split among multiple exons
        # a CDS can be part of multiple transcripts
        for parent in d['Parent'].split(','):
            if parent not in parent_dict:
                parent_dict[parent] = [d]
            else:
                parent_dict[parent].append(d)
    return d


def add_gene_to_dict(cols, species, gene_dict):
    global gene_count

        gene_count = gene_count + 1


def add_transcript_to_dict(cols, species, transcript_dict):
    transcript = feature_to_dict(cols)
    transcript.update({
        'object_type': 'Transcript',
        'seq_region_name': cols[0],
        'species': species,
    })

    parser.add_option('-l', action='store_true', default=False, dest='longestCDS', help='Keep only the longest CDS per gene')
    parser.add_option('--headers', action='store_true', default=False, help='Change the header line of the FASTA sequences to the >TranscriptId_species format')
    parser.add_option('--regions', default="", help='Comma-separated list of region IDs for which FASTA sequences should be filtered')
    parser.add_option('-o', '--output', help='Path of the output SQLite file')
    parser.add_option('--of', help='Path of the output FASTA file')
    parser.add_option('--ff', help='Path of the filtered sequences output FASTA file')

    options, args = parser.parse_args()
    if args:
        raise Exception('Use options to provide inputs')

            if options.longestCDS:
                found_gene_transcript = True
            else:
                break

            if gene_id in gene_transcripts_dict:
                gene_transcripts_dict[gene_id].append((transcript_id, len(entry.sequence)))
            else:
                gene_transcripts_dict[gene_id] = [(transcript_id, len(entry.sequence))]

    if options.longestCDS:
        # For each gene, select the transcript with the longest sequence.
        # If more than one transcripts have the same longest sequence for a
        # gene, the first one to appear in the FASTA file is selected

10:e8e75a79de59

from __future__ import print_function

import json
import optparse
import os
import sqlite3
import sys

version = "0.4.0"
gene_count = 0

    if parent_dict is not None and 'Parent' in d:
        # a 3' UTR can be split among multiple exons
        # a 5' UTR can be split among multiple exons
        # a CDS can be part of multiple transcripts
        for parent in d['Parent'].split(','):
            parent_dict.setdefault(parent, []).append(d)
    return d


def add_gene_to_dict(cols, species, gene_dict):
    global gene_count

        gene_count = gene_count + 1


def add_transcript_to_dict(cols, species, transcript_dict):
    transcript = feature_to_dict(cols)
    if 'biotype' in transcript and transcript['biotype'] != 'protein_coding':
        return
    transcript.update({
        'object_type': 'Transcript',
        'seq_region_name': cols[0],
        'species': species,
    })

    parser.add_option('-l', action='store_true', default=False, dest='longestCDS', help='Keep only the longest CDS per gene')
    parser.add_option('--headers', action='store_true', default=False, help='Change the header line of the FASTA sequences to the >TranscriptId_species format')
    parser.add_option('--regions', default="", help='Comma-separated list of region IDs for which FASTA sequences should be filtered')
    parser.add_option('-o', '--output', help='Path of the output SQLite file')
    parser.add_option('--of', help='Path of the output FASTA file')
    parser.add_option('--ff', default=os.devnull, help='Path of the filtered sequences output FASTA file')

    options, args = parser.parse_args()
    if args:
        raise Exception('Use options to provide inputs')

            if options.longestCDS:
                found_gene_transcript = True
            else:
                break

            gene_transcripts_dict.setdefault(gene_id, []).append((transcript_id, len(entry.sequence)))

    if options.longestCDS:
        # For each gene, select the transcript with the longest sequence.
        # If more than one transcripts have the same longest sequence for a
        # gene, the first one to appear in the FASTA file is selected