Mercurial > repos > devteam > data_manager_bwa_mem_index_builder

--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/.shed.yml	Wed Mar 18 15:18:49 2015 -0400
@@ -0,0 +1,4 @@
+# repository published to https://toolshed.g2.bx.psu.edu/repos/devteam/data_manager_bwa_mem_index_builder
+owner: devteam
+name: data_manager_bwa_mem_index_builder
+
--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/data_manager/bwa_mem_index_builder.py	Wed Mar 18 15:18:49 2015 -0400
@@ -0,0 +1,90 @@
+#!/usr/bin/env python
+#Dan Blankenberg
+
+import sys
+import os
+import tempfile
+import optparse
+import subprocess
+
+from json import loads, dumps
+
+
+CHUNK_SIZE = 2**20
+TWO_GB = 2**30*2
+
+DEFAULT_DATA_TABLE_NAME = "bwa_mem_indexes"
+
+def get_id_name( params, dbkey, fasta_description=None):
+    #TODO: ensure sequence_id is unique and does not already appear in location file
+    sequence_id = params['param_dict']['sequence_id']
+    if not sequence_id:
+        sequence_id = dbkey
+
+    sequence_name = params['param_dict']['sequence_name']
+    if not sequence_name:
+        sequence_name = fasta_description
+        if not sequence_name:
+            sequence_name = dbkey
+    return sequence_id, sequence_name
+
+def build_bwa_index( data_manager_dict, fasta_filename, params, target_directory, dbkey, sequence_id, sequence_name, data_table_name=DEFAULT_DATA_TABLE_NAME ):
+    #TODO: allow multiple FASTA input files
+    #tmp_dir = tempfile.mkdtemp( prefix='tmp-data-manager-bwa-index-builder-' )
+    fasta_base_name = os.path.split( fasta_filename )[-1]
+    sym_linked_fasta_filename = os.path.join( target_directory, fasta_base_name )
+    os.symlink( fasta_filename, sym_linked_fasta_filename )
+    if params['param_dict']['index_algorithm'] == 'automatic':
+        if os.stat( fasta_filename ).st_size < TWO_GB: #use 2 GB as cut off for memory vs. max of 2gb database size; this is somewhat arbitrary
+            index_algorithm = 'is'
+        else:
+            index_algorithm = 'bwtsw'
+    else:
+        index_algorithm = params['param_dict']['index_algorithm']
+
+    args = [ 'bwa', 'index', '-a', index_algorithm ]
+    args.append( sym_linked_fasta_filename )
+    proc = subprocess.Popen( args=args, shell=False, cwd=target_directory )
+    return_code = proc.wait()
+    if return_code:
+        print >> sys.stderr, "Error building index."
+        sys.exit( return_code )
+    data_table_entry = dict( value=sequence_id, dbkey=dbkey, name=sequence_name, path=fasta_base_name )
+    _add_data_table_entry( data_manager_dict, data_table_name, data_table_entry )
+
+def _add_data_table_entry( data_manager_dict, data_table_name, data_table_entry ):
+    data_manager_dict['data_tables'] = data_manager_dict.get( 'data_tables', {} )
+    data_manager_dict['data_tables'][ data_table_name ] = data_manager_dict['data_tables'].get( data_table_name, [] )
+    data_manager_dict['data_tables'][ data_table_name ].append( data_table_entry )
+    return data_manager_dict
+
+def main():
+    #Parse Command Line
+    parser = optparse.OptionParser()
+    parser.add_option( '-f', '--fasta_filename', dest='fasta_filename', action='store', type="string", default=None, help='fasta_filename' )
+    parser.add_option( '-d', '--fasta_dbkey', dest='fasta_dbkey', action='store', type="string", default=None, help='fasta_dbkey' )
+    parser.add_option( '-t', '--fasta_description', dest='fasta_description', action='store', type="string", default=None, help='fasta_description' )
+    parser.add_option( '-n', '--data_table_name', dest='data_table_name', action='store', type="string", default=None, help='data_table_name' )
+    (options, args) = parser.parse_args()
+
+    filename = args[0]
+
+    params = loads( open( filename ).read() )
+    target_directory = params[ 'output_data' ][0]['extra_files_path']
+    os.mkdir( target_directory )
+    data_manager_dict = {}
+
+    dbkey = options.fasta_dbkey
+
+    if dbkey in [ None, '', '?' ]:
+        raise Exception( '"%s" is not a valid dbkey. You must specify a valid dbkey.' % ( dbkey ) )
+
+    sequence_id, sequence_name = get_id_name( params, dbkey=dbkey, fasta_description=options.fasta_description )
+
+    #build the index
+    build_bwa_index( data_manager_dict, options.fasta_filename, params, target_directory, dbkey, sequence_id, sequence_name, data_table_name=options.data_table_name or DEFAULT_DATA_TABLE_NAME )
+
+    #save info to json file
+    open( filename, 'wb' ).write( dumps( data_manager_dict ) )
+
+if __name__ == "__main__": main()
--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/data_manager/bwa_mem_index_builder.xml	Wed Mar 18 15:18:49 2015 -0400
@@ -0,0 +1,37 @@
+<tool id="bwa_mem_index_builder_data_manager" name="BWA-MEM index" tool_type="manage_data" version="0.0.1">
+    <description>builder</description>
+    <requirements>
+        <requirement type="package" version="0.7.10.039ea20639">bwa</requirement>
+    </requirements>
+    <command interpreter="python">bwa_mem_index_builder.py "${out_file}" --fasta_filename "${all_fasta_source.fields.path}" --fasta_dbkey "${all_fasta_source.fields.dbkey}" --fasta_description "${all_fasta_source.fields.name}" --data_table_name "bwa_mem_indexes"</command>
+    <stdio>
+        <exit_code range=":-1" />
+        <exit_code range="1:" />
+    </stdio>
+    <inputs>
+        <param name="all_fasta_source" type="select" label="Source FASTA Sequence">
+            <options from_data_table="all_fasta"/>
+        </param>
+        <param type="text" name="sequence_name" value="" label="Name of sequence" />
+        <param type="text" name="sequence_id" value="" label="ID for sequence" />
+
+        <param name="index_algorithm" type="select" label="Algorithm for constructing BWT index">
+            <option value="automatic" selected="True" help="2GB cut-off">Guess automatically</option>
+            <option value="is" hel="Small genomes">IS linear-time algorithm</option>
+            <!-- <option value="div">div</option> -->
+            <option value="bwtsw" help="Large genomes">BWT-SW</option>
+        </param>
+
+    </inputs>
+    <outputs>
+        <data name="out_file" format="data_manager_json"/>
+    </outputs>
+
+    <help>
+
+.. class:: infomark
+
+**Notice:** If you leave name, description, or id blank, it will be generated automatically.
+
+    </help>
+</tool>
--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/data_manager_conf.xml	Wed Mar 18 15:18:49 2015 -0400
@@ -0,0 +1,22 @@
+<?xml version="1.0"?>
+<data_managers>
+
+    <data_manager tool_file="data_manager/bwa_mem_index_builder.xml" id="bwa_mem_index_builder" version="0.0.1">
+        <data_table name="bwa_mem_indexes">
+            <output>
+                <column name="value" />
+                <column name="dbkey" />
+                <column name="name" />
+                <column name="path" output_ref="out_file" >
+                    <move type="directory" relativize_symlinks="True">
+                        <!-- <source>${path}</source>--> <!-- out_file.extra_files_path is used as base by default --> <!-- if no source, eg for type=directory, then refers to base -->
+                        <target base="${GALAXY_DATA_MANAGER_DATA_PATH}">${dbkey}/bwa_mem_index/${value}</target>
+                    </move>
+                    <value_translation>${GALAXY_DATA_MANAGER_DATA_PATH}/${dbkey}/bwa_mem_index/${value}/${path}</value_translation>
+                    <value_translation type="function">abspath</value_translation>
+                </column>
+            </output>
+        </data_table>
+    </data_manager>
+
+</data_managers>
--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/tool-data/bwa_mem_index.loc.sample	Wed Mar 18 15:18:49 2015 -0400
@@ -0,0 +1,38 @@
+#This is a sample file distributed with Galaxy that enables tools
+#to use a directory of BWA indexed sequences data files. You will need
+#to create these data files and then create a bwa_index.loc file
+#similar to this one (store it in this directory) that points to
+#the directories in which those files are stored. The bwa_index.loc
+#file has this format (longer white space characters are TAB characters):
+#
+#<unique_build_id>   <dbkey>   <display_name>   <file_path>
+#
+#So, for example, if you had phiX indexed stored in
+#/depot/data2/galaxy/phiX/base/,
+#then the bwa_index.loc entry would look like this:
+#
+#phiX174   phiX   phiX Pretty   /depot/data2/galaxy/phiX/base/phiX.fa
+#
+#and your /depot/data2/galaxy/phiX/base/ directory
+#would contain phiX.fa.* files:
+#
+#-rw-r--r--  1 james    universe 830134 2005-09-13 10:12 phiX.fa.amb
+#-rw-r--r--  1 james    universe 527388 2005-09-13 10:12 phiX.fa.ann
+#-rw-r--r--  1 james    universe 269808 2005-09-13 10:12 phiX.fa.bwt
+#...etc...
+#
+#Your bwa_index.loc file should include an entry per line for each
+#index set you have stored. The "file" in the path does not actually
+#exist, but it is the prefix for the actual index files.  For example:
+#
+#phiX174				phiX	phiX174			/depot/data2/galaxy/phiX/base/phiX.fa
+#hg18canon				hg18	hg18 Canonical	/depot/data2/galaxy/hg18/base/hg18canon.fa
+#hg18full				hg18	hg18 Full		/depot/data2/galaxy/hg18/base/hg18full.fa
+#/orig/path/hg19.fa		hg19	hg19			/depot/data2/galaxy/hg19/base/hg19.fa
+#...etc...
+#
+#Note that for backwards compatibility with workflows, the unique ID of
+#an entry must be the path that was in the original loc file, because that
+#is the value stored in the workflow for that parameter. That is why the
+#hg19 entry above looks odd. New genomes can be better-looking.
+#
--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/tool_data_table_conf.xml.sample	Wed Mar 18 15:18:49 2015 -0400
@@ -0,0 +1,7 @@
+<tables>
+    <!-- Locations of indexes in the BWA mapper format for BWA versions 0.6 and higher including BWA MEM and ALN-->
+    <table name="bwa_mem_indexes" comment_char="#">
+        <columns>value, dbkey, name, path</columns>
+        <file path="tool-data/bwa_mem_index.loc" />
+    </table>
+</tables>
--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/tool_dependencies.xml	Wed Mar 18 15:18:49 2015 -0400
@@ -0,0 +1,6 @@
+<?xml version="1.0"?>
+<tool_dependency>
+    <package name="bwa" version="0.7.10.039ea20639">
+        <repository changeset_revision="5b9aca1e1c07" name="package_bwa_0_7_10_039ea20639" owner="devteam" toolshed="https://toolshed.g2.bx.psu.edu" />
+    </package>
+</tool_dependency>