FastaSplitter_conf.pm 2.85 KB
Newer Older
1 2 3 4
=pod

=head1 NAME

5
    Bio::EnsEMBL::Hive::PipeConfig::FastaSplitter_conf
6 7 8 9 10

=head1 SYNOPSIS

    init_pipeline.pl Bio::EnsEMBL::Hive::PipeConfig::FastaSplitter_conf -inputfile reference.fasta -chunks_dir reference_chunks

11 12
=head1 LICENSE

13 14
    Copyright [1999-2015] Wellcome Trust Sanger Institute and the EMBL-European Bioinformatics Institute
    Copyright [2016] EMBL-European Bioinformatics Institute
15 16 17 18 19 20 21 22 23 24 25 26

    Licensed under the Apache License, Version 2.0 (the "License"); you may not use this file except in compliance with the License.
    You may obtain a copy of the License at

         http://www.apache.org/licenses/LICENSE-2.0

    Unless required by applicable law or agreed to in writing, software distributed under the License
    is distributed on an "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
    See the License for the specific language governing permissions and limitations under the License.

=head1 CONTACT

27
    Please subscribe to the Hive mailing list:  http://listserver.ebi.ac.uk/mailman/listinfo/ehive-users  to discuss Hive-related questions or to be notified of our updates
28

29 30
=cut

31

32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90
package Bio::EnsEMBL::Hive::PipeConfig::FastaSplitter_conf;

use strict;
use warnings;

use base ('Bio::EnsEMBL::Hive::PipeConfig::HiveGeneric_conf');  # All Hive databases configuration files should inherit from HiveGeneric, directly or indirectly


sub default_options {
    my ($self) = @_;
    return {
        %{ $self->SUPER::default_options() },               # inherit other stuff from the base class

        'pipeline_name' => 'split_fasta',                   # name used by the beekeeper to prefix job names on the farm

            # runnable-specific parameters' defaults:
        'max_chunk_length'  => 500000,
        'output_prefix'     => 'chunk_number_',
        'output_suffix'     => '.fasta',

        'chunks_dir'        => 'fasta_split_chunks',
    };
}


sub pipeline_create_commands {
    my ($self) = @_;
    return [
        @{$self->SUPER::pipeline_create_commands},  # inheriting database and hive tables' creation

        'mkdir -p '.$self->o('chunks_dir'),
    ];
}


sub pipeline_analyses {
    my ($self) = @_;
    return [
        {   -logic_name => 'split_fasta',
            -module     => 'Bio::EnsEMBL::Hive::RunnableDB::FastaFactory',
            -input_ids => [ {
                'inputfile'         => $self->o('inputfile'),
                'max_chunk_length'  => $self->o('max_chunk_length'),
                'output_prefix'     => $self->o('chunks_dir').'/'.$self->o('output_prefix'),
                'output_suffix'     => $self->o('output_suffix'),
            } ],
            -flow_into => {
                2 => [ 'align' ],   # will create a fan of jobs
            },
        },

        {   -logic_name    => 'align',
            -module        => 'Bio::EnsEMBL::Hive::RunnableDB::Dummy',
        },
    ];
}

1;