# HG changeset patch
# User jjohnson
# Date 1406033573 14400
# Node ID 4c7db9cbbbf7ddd9eeb6b17b8f517feed14a169d
Uploaded
diff -r 000000000000 -r 4c7db9cbbbf7 README
--- /dev/null Thu Jan 01 00:00:00 1970 +0000
+++ b/README Tue Jul 22 08:52:53 2014 -0400
@@ -0,0 +1,2 @@
+Builds a hisat compatible index from a fasta reference from the tool_data_table_conf all_fasta reference.
+It adds an entry to the tool_data_table_conf hisat_indexes reference.
diff -r 000000000000 -r 4c7db9cbbbf7 data_manager/hisat_index_builder.py
--- /dev/null Thu Jan 01 00:00:00 1970 +0000
+++ b/data_manager/hisat_index_builder.py Tue Jul 22 08:52:53 2014 -0400
@@ -0,0 +1,88 @@
+#!/usr/bin/env python
+
+import sys
+import os
+import tempfile
+import optparse
+import subprocess
+
+from galaxy.util.json import from_json_string, to_json_string
+
+
+CHUNK_SIZE = 2**20
+
+DEFAULT_DATA_TABLE_NAME = "hisat_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_hisat_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-hisat-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 )
+ args = [ 'hisat-build',sym_linked_fasta_filename,fasta_base_name ]
+ tmp_stderr = tempfile.NamedTemporaryFile( prefix = "tmp-data-manager-hisat-index-builder-stderr" )
+ proc = subprocess.Popen( args=args, shell=False, cwd=target_directory, stderr=tmp_stderr.fileno() )
+ return_code = proc.wait()
+ if return_code:
+ tmp_stderr.flush()
+ tmp_stderr.seek(0)
+ print >> sys.stderr, "Error building index:"
+ while True:
+ chunk = tmp_stderr.read( CHUNK_SIZE )
+ if not chunk:
+ break
+ sys.stderr.write( chunk )
+ sys.exit( return_code )
+ tmp_stderr.close()
+ 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 = from_json_string( 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_hisat_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( to_json_string( data_manager_dict ) )
+
+if __name__ == "__main__": main()
diff -r 000000000000 -r 4c7db9cbbbf7 data_manager/hisat_index_builder.xml
--- /dev/null Thu Jan 01 00:00:00 1970 +0000
+++ b/data_manager/hisat_index_builder.xml Tue Jul 22 08:52:53 2014 -0400
@@ -0,0 +1,25 @@
+
+ hisat index builder
+
+ hisat
+
+ hisat_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 "hisat_indexes"
+
+
+
+
+
+
+
+
+
+
+
+
+
+.. class:: infomark
+
+**Notice:** If you leave name, description, or id blank, it will be generated automatically.
+
+
+
diff -r 000000000000 -r 4c7db9cbbbf7 data_manager_conf.xml
--- /dev/null Thu Jan 01 00:00:00 1970 +0000
+++ b/data_manager_conf.xml Tue Jul 22 08:52:53 2014 -0400
@@ -0,0 +1,22 @@
+
+
+
+
+
+
+
+
+
+
diff -r 000000000000 -r 4c7db9cbbbf7 tool-data/all_fasta.loc.sample
--- /dev/null Thu Jan 01 00:00:00 1970 +0000
+++ b/tool-data/all_fasta.loc.sample Tue Jul 22 08:52:53 2014 -0400
@@ -0,0 +1,18 @@
+#This file lists the locations and dbkeys of all the fasta files
+#under the "genome" directory (a directory that contains a directory
+#for each build). The script extract_fasta.py will generate the file
+#all_fasta.loc. This file has the format (white space characters are
+#TAB characters):
+#
+#
+#
+#So, all_fasta.loc could look something like this:
+#
+#apiMel3 apiMel3 Honeybee (Apis mellifera): apiMel3 /path/to/genome/apiMel3/apiMel3.fa
+#hg19canon hg19 Human (Homo sapiens): hg19 Canonical /path/to/genome/hg19/hg19canon.fa
+#hg19full hg19 Human (Homo sapiens): hg19 Full /path/to/genome/hg19/hg19full.fa
+#
+#Your all_fasta.loc file should contain an entry for each individual
+#fasta file. So there will be multiple fasta files for each build,
+#such as with hg19 above.
+#
diff -r 000000000000 -r 4c7db9cbbbf7 tool-data/hisat_indices.loc.sample
--- /dev/null Thu Jan 01 00:00:00 1970 +0000
+++ b/tool-data/hisat_indices.loc.sample Tue Jul 22 08:52:53 2014 -0400
@@ -0,0 +1,41 @@
+# hisat_indices.loc.sample
+# This is a *.loc.sample file distributed with Galaxy that enables tools
+# to use a directory of indexed data files. This one is for Bowtie2 and Tophat2.
+# See the wiki: http://wiki.galaxyproject.org/Admin/NGS%20Local%20Setup
+# First create these data files and save them in your own data directory structure.
+# Then, create a hisat_indices.loc file to use those indexes with tools.
+# Copy this file, save it with the same name (minus the .sample),
+# follow the format examples, and store the result in this directory.
+# The file should include an one line entry for each index set.
+# The path points to the "basename" for the set, not a specific file.
+# It has four text columns seperated by TABS.
+#
+#
+#
+# So, for example, if you had hg18 indexes stored in:
+#
+# /depot/data2/galaxy/hg19/hisat/
+#
+# containing hg19 genome and hg19.*.bt2 files, such as:
+# -rw-rw-r--. 1 galaxy galaxy 914M Jul 18 09:17 hg19canon.1.bt2
+# -rw-rw-r--. 1 galaxy galaxy 683M Jul 18 09:17 hg19canon.2.bt2
+# -rw-rw-r--. 1 galaxy galaxy 3.3K Jul 18 08:22 hg19canon.3.bt2
+# -rw-rw-r--. 1 galaxy galaxy 683M Jul 18 08:22 hg19canon.4.bt2
+# -rw-rw-r--. 1 galaxy galaxy 1.2G Jul 18 09:23 hg19canon.5.bt2
+# -rw-rw-r--. 1 galaxy galaxy 694M Jul 18 09:23 hg19canon.6.bt2
+# -rw-rw-r--. 2 galaxy galaxy 3.0G Nov 15 2011 hg19canon.fa
+# -rw-rw-r--. 1 galaxy galaxy 914M Jul 18 10:13 hg19canon.rev.1.bt2
+# -rw-rw-r--. 1 galaxy galaxy 683M Jul 18 10:13 hg19canon.rev.2.bt2
+# -rw-rw-r--. 1 galaxy galaxy 1.2G Jul 18 10:20 hg19canon.rev.5.bt2
+# -rw-rw-r--. 1 galaxy galaxy 694M Jul 18 10:20 hg19canon.rev.6.bt2
+#
+# then the hisat_indices.loc entry could look like this:
+#
+#hg19 hg19 Human (hg19) /depot/data2/galaxy/hg19/hisat/hg19canon
+#
+#More examples:
+#
+#mm10 mm10 Mouse (mm10) /depot/data2/galaxy/mm10/hisat/mm10
+#dm3 dm3 D. melanogaster (dm3) /depot/data2/galaxy/mm10/hisat/dm3
+#
+#
diff -r 000000000000 -r 4c7db9cbbbf7 tool_data_table_conf.xml.sample
--- /dev/null Thu Jan 01 00:00:00 1970 +0000
+++ b/tool_data_table_conf.xml.sample Tue Jul 22 08:52:53 2014 -0400
@@ -0,0 +1,12 @@
+
+
+
+ value, dbkey, name, path
+
+
+
+
+ value, dbkey, name, path
+
+
+
diff -r 000000000000 -r 4c7db9cbbbf7 tool_dependencies.xml
--- /dev/null Thu Jan 01 00:00:00 1970 +0000
+++ b/tool_dependencies.xml Tue Jul 22 08:52:53 2014 -0400
@@ -0,0 +1,6 @@
+
+
+
+
+
+