Mercurial > repos > yating-l > multi_fasta_glimmer_hmm

changeset 8:33c96cb0b3d8 draft

Find changesets by keywords (author, files, the commit message), revision number or hash, or revset expression.
planemo upload for repository https://github.com/remimarenco/multi_fasta_glimmerhmm.git commit 59eb9b27c7382ae4736eb7425615e4b575757378-dirty
author yating-l
date Wed, 03 May 2017 18:03:12 -0400
parents 0f39f40ef695
children 81383b1c05d9
files data_manager_conf.xml fetch_reference_data.py fetch_reference_data.xml tool_data_table_conf.xml.sample
diffstat 4 files changed, 0 insertions(+), 206 deletions(-) [+]
line wrap: on
line diff
--- a/data_manager_conf.xml	Wed May 03 15:15:36 2017 -0400
+++ /dev/null	Thu Jan 01 00:00:00 1970 +0000
@@ -1,18 +0,0 @@
-<?xml version="1.0"?>
-    <data_managers>
-        <data_manager tool_file="data_manager/fetch_reference_data.xml" id="fetch_reference_data"> 
-            <data_table name="glimmer_hmm_trained_dir">
-                <output>
-                    <column name="value" />
-                    <column name="name" />
-                    <column name="path" output_ref="out_file">
-                        <move type="file">
-                            <source>${path}</source>
-                            <target base="${GALAXY_DATA_MANAGER_DATA_PATH}">${name}/${path}</target>
-                        </move>
-                        <value_translation>${GALAXY_DATA_MANAGER_DATA_PATH}/${name}/${path}</value_translation>
-                    </column>
-                </output>
-            </data_table>
-        </data_manager>
-    </data_managers>
\ No newline at end of file
--- a/fetch_reference_data.py	Wed May 03 15:15:36 2017 -0400
+++ /dev/null	Thu Jan 01 00:00:00 1970 +0000
@@ -1,75 +0,0 @@
-#!/usr/bin/env python
-# ref: https://galaxyproject.org/admin/tools/data-managers/how-to/define/
-
-import sys
-import os
-import tempfile
-import shutil
-import argparse
-import urllib2
-import tarfile
-
-from galaxy.util.json import from_json_string, to_json_string
-
-CHUNK_SIZE = 2**20 #1mb
-
-def cleanup_before_exit(tmp_dir):
-    if tmp_dir and os.path.exists(tmp_dir):
-        shutil.rmtree(tmp_dir)
-
-def stop_err(msg):
-    sys.stderr.write(msg)
-    sys.exit(1)
-
-def get_reference_id_name(params):
-    genome_id = params['param_dict']['genome_id']
-    genome_name = params['param_dict']['genome_name']
-    return genome_id, genome_name
-
-def download_from_GlimmerHMM(data_manager_dict, params, target_directory, sequence_id, sequence_name ):
-    GlimmerHMM_DOWNLOAD_URL = 'ftp://ccb.jhu.edu/pub/software/glimmerhmm/GlimmerHMM-3.0.4.tar.gz'
-    GlimmerHMM_TRAINED_DIR = os.path.join('GlimmerHMM', 'trained_dir', sequence_id)
-    with tarfile.open('GlimmerHMM-3.0.4.tar', mode='r:*') as tar:
-        subdir = [
-          tarinfo for tarinfo in tar.getmembers()
-          if sequence_id in tarinfo.name
-        ]
-        tar.extractall(members=subdir)
-    glimmerhmm_trained_target_dir = os.path.join(target_directory, sequence_id)
-    shutil.copytree(GlimmerHMM_TRAINED_DIR, glimmerhmm_trained_target_dir)
-    data_table_entry = dict(value=sequence_id, name=sequence_name, path=glimmerhmm_trained_target_dir)
-    _add_data_table_entry(data_manager_dict, data_table_entry)
-
-    cleanup_before_exit(GlimmerHMM_TRAINED_DIR)
-
-def _add_data_table_entry( data_manager_dict, data_table_entry ):
-    data_manager_dict['data_tables'] = data_manager_dict.get( 'data_tables', {} )
-    data_manager_dict['data_tables']['reference_data'] = data_manager_dict['data_tables'].get('reference_data', [])
-    data_manager_dict['data_tables']['reference_data'].append( data_table_entry )
-    return data_manager_dict
-
-REFERENCE_SOURCE_TO_DOWNLOAD = dict(glimmerhmm=download_from_GlimmerHMM)
-
-def main():
-    #Parse Command Line
-    parser = argparse.ArgumentParser()
-    args = parser.parse_args()
-
-    filename = args[0]
-
-    params = from_json_string(open(filename).read())
-    target_directory = params['output_data'][0]['extra_files_path']
-    os.mkdir(target_directory)
-    data_manager_dict = {}
-
-    sequence_id, sequence_name = get_reference_id_name(params)
-
-    #Fetch the FASTA
-    REFERENCE_SOURCE_TO_DOWNLOAD[params['param_dict']['file_path']](data_manager_dict, params, target_directory, sequence_id, sequence_name)
-
-    #save info to json file
-    open(filename, 'wb').write(to_json_string(data_manager_dict))
-
-if __name__ == "__main__":
-    main()
-
--- a/fetch_reference_data.xml	Wed May 03 15:15:36 2017 -0400
+++ /dev/null	Thu Jan 01 00:00:00 1970 +0000
@@ -1,15 +0,0 @@
-<tool id="data_manager_fetch_reference_data" name="Referene Genome for GlimmerHMM" version="0.0.1" tool_type="manage_data">
-    <description>fetching reference data for GlimmerHMM</description>
-    <command interpreter="python">data_manager_fetch_reference_data.py "${out_file}"</command>
-    <inputs>
-        <param name="genome_id" type="text" label="Id of the reference genome" />
-        <param name="genome_name" type="text" label="Name of the reference genome" />
-        <param name="trained_dir" type="text" value="" label="Directory of the genome file" />
-    </inputs>
-    <outputs>
-        <data name="out_file" format="data_manager_json" />
-    </outputs>
-    <help>
-        Fetch trained data (reference genome) for GlimmerHMM
-    </help>
-</tool>
\ No newline at end of file
--- a/tool_data_table_conf.xml.sample	Wed May 03 15:15:36 2017 -0400
+++ /dev/null	Thu Jan 01 00:00:00 1970 +0000
@@ -1,98 +0,0 @@
-<!-- Use the file tool_data_table_conf.xml.oldlocstyle if you don't want to update your loc files as changed in revision 4550:535d276c92bc-->
-<tables>
-    <!-- Locations of all fasta files under genome directory -->
-    <table name="all_fasta" comment_char="#">
-        <columns>value, dbkey, name, path</columns>
-        <file path="tool-data/all_fasta.loc" />
-    </table>
-    <!-- Locations of indexes in the BFAST mapper format -->
-    <table name="bfast_indexes" comment_char="#">
-        <columns>value, dbkey, formats, name, path</columns>
-        <file path="tool-data/bfast_indexes.loc" />
-    </table>
-    <!-- Locations of protein (mega)blast databases -->
-    <table name="blastdb_p" comment_char="#">
-        <columns>value, name, path</columns>
-        <file path="tool-data/blastdb_p.loc" />
-    </table>
-    <!-- Locations of indexes in the BWA mapper format -->
-    <table name="bwa_indexes" comment_char="#">
-        <columns>value, dbkey, name, path</columns>
-        <file path="tool-data/bwa_index.loc" />
-    </table>
-    <!-- Locations of indexes in the BWA color-space mapper format -->
-    <table name="bwa_indexes_color" comment_char="#">
-        <columns>value, dbkey, name, path</columns>
-        <file path="tool-data/bwa_index_color.loc" />
-    </table>
-    <!-- Locations of MAF files that have been indexed with bx-python -->
-    <table name="indexed_maf_files">
-        <columns>name, value, dbkey, species</columns>
-        <file path="tool-data/maf_index.loc" />
-    </table>
-    <!-- Locations of fasta files appropriate for NGS simulation -->
-    <table name="ngs_sim_fasta" comment_char="#">
-        <columns>value, dbkey, name, path</columns>
-        <file path="tool-data/ngs_sim_fasta.loc" />
-    </table>
-    <!-- Locations of PerM base index files -->
-    <table name="perm_base_indexes" comment_char="#">
-        <columns>value, name, path</columns>
-        <file path="tool-data/perm_base_index.loc" />
-    </table>
-    <!-- Locations of PerM color-space index files -->
-    <table name="perm_color_indexes" comment_char="#">
-        <columns>value, name, path</columns>
-        <file path="tool-data/perm_color_index.loc" />
-    </table>
-    <!-- Location of Picard dict file and other files -->
-    <table name="picard_indexes" comment_char="#">
-        <columns>value, dbkey, name, path</columns>
-        <file path="tool-data/picard_index.loc" />
-    </table>
-    <!-- Location of SRMA dict file and other files -->
-    <table name="srma_indexes" comment_char="#">
-        <columns>value, dbkey, name, path</columns>
-        <file path="tool-data/picard_index.loc" />
-    </table>
-    <!-- Location of Mosaik files -->
-    <table name="mosaik_indexes" comment_char="#">
-        <columns>value, dbkey, name, path</columns>
-        <file path="tool-data/mosaik_index.loc" />
-    </table>
-    <!-- Locations of indexes in the 2bit format -->
-    <table name="twobit" comment_char="#">
-        <columns>value, path</columns>
-        <file path="tool-data/twobit.loc" />
-    </table>
-    <!-- Available IGV builds, loaded from URL -->
-    <table name="igv_broad_genomes" comment_char="#">
-        <columns>name, url, value</columns>
-        <file url="http://igv.broadinstitute.org/genomes/genomes.txt" />
-    </table>
-    <!-- Available liftOver chain file -->
-    <table name="liftOver" comment_char="#">
-        <columns>dbkey, name, value</columns>
-        <file path="tool-data/liftOver.loc" />
-    </table>
-    <!-- iobio bam servers -->
-    <table name="bam_iobio" comment_char="#">
-        <columns>value, name, url</columns>
-        <file path="tool-data/bam_iobio.loc" />
-    </table>
-    <!-- iobio vcf servers -->
-    <table name="vcf_iobio" comment_char="#">
-        <columns>value, name, url</columns>
-        <file path="tool-data/vcf_iobio.loc" />
-    </table>
-    <!-- simple biom servers -->
-    <table name="biom_simple_display" comment_char="#">
-        <columns>value, name, url</columns>
-        <file path="tool-data/biom_simple_display.loc" />
-    </table>
-    <!-- glimmer_hmm trained_dir -->
-    <table name="glimmer_hmm_trained_dir" comment_char="#">
-        <columns>value, name, path</columns>
-        <file path="tool-data/glimmer_hmm.loc" />
-    </table>
-</tables>