# HG changeset patch # User devteam # Date 1446837444 18000 # Node ID 8082f04de7ae719b5e483ecd349b1e07a935d6be planemo upload for repository https://github.com/galaxyproject/tools-devteam/tree/master/data_managers/data_manager_hisat_index_builder commit 86cf90107482cab1cb47fc0d42d6705f8077daa7 diff -r 000000000000 -r 8082f04de7ae data_manager/hisat_index_builder.py --- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/data_manager/hisat_index_builder.py Fri Nov 06 14:17:24 2015 -0500 @@ -0,0 +1,76 @@ +#!/usr/bin/env python +# Based heavily on the Bowtie 2 data manager wrapper script by Dan Blankenberg + +import sys +import os +import optparse +import subprocess + +from json import loads, dumps + + +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 + 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, sequence_id ] + 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=sequence_id ) + _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_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( dumps( data_manager_dict ) ) + +if __name__ == "__main__": main() diff -r 000000000000 -r 8082f04de7ae data_manager/hisat_index_builder.xml --- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/data_manager/hisat_index_builder.xml Fri Nov 06 14:17:24 2015 -0500 @@ -0,0 +1,67 @@ + + 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" + + + + + + + + + + + +`__ is a fast and sensitive +spliced alignment program. As part of HISAT, we have developed a new +indexing scheme based on the Burrows-Wheeler transform +(`BWT `__) and +the `FM index `__, called +hierarchical indexing, that employs two types of indexes: (1) one global +FM index representing the whole genome, and (2) many separate local FM +indexes for small regions collectively covering the genome. Our +hierarchical index for the human genome (about 3 billion bp) includes +~48,000 local FM indexes, each representing a genomic region of +~64,000bp. As the basis for non-gapped alignment, the FM index is +extremely fast with a low memory footprint, as demonstrated by +`Bowtie `__. In addition, HISAT provides +several alignment strategies specifically designed for mapping different +types of RNA-seq reads. All these together, HISAT enables extremely fast +and sensitive alignment of reads, in particular those spanning two exons +or more. As a result, HISAT is much faster >50 times than +`TopHat2 `__ with better alignment +quality. Although it uses a large number of indexes, the memory +requirement of HISAT is still modest, approximately 4.3 GB for human. +HISAT uses the `Bowtie2 `__ +implementation to handle most of the operations on the FM index. In +addition to spliced alignment, HISAT handles reads involving indels and +supports a paired-end alignment mode. Multiple processors can be used +simultaneously to achieve greater alignment speed. HISAT outputs +alignments in `SAM `__ format, +enabling interoperation with a large number of other tools (e.g. +`SAMtools `__, +`GATK `__) +that use SAM. HISAT is distributed under the `GPLv3 +license `__, and it runs on +the command line under Linux, Mac OS X and Windows. +]]> + + + 10.1038/nmeth.3317 + + diff -r 000000000000 -r 8082f04de7ae data_manager_conf.xml --- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/data_manager_conf.xml Fri Nov 06 14:17:24 2015 -0500 @@ -0,0 +1,20 @@ + + + + + + + + + + + + ${dbkey}/hisat_index/${value} + + ${GALAXY_DATA_MANAGER_DATA_PATH}/${dbkey}/hisat_index/${value}/${path} + abspath + + + + + \ No newline at end of file diff -r 000000000000 -r 8082f04de7ae tool-data/all_fasta.loc.sample --- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/tool-data/all_fasta.loc.sample Fri Nov 06 14:17:24 2015 -0500 @@ -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 8082f04de7ae tool-data/hisat_indexes.loc.sample --- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/tool-data/hisat_indexes.loc.sample Fri Nov 06 14:17:24 2015 -0500 @@ -0,0 +1,37 @@ +# hisat_indexes.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 HISAT. +# 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_indexes.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 james james 914M Feb 10 18:56 hg19canon.fa +# -rw-rw-r-- 1 james james 914M Feb 10 18:56 hg19canon.1.bt2 +# -rw-rw-r-- 1 james james 683M Feb 10 18:56 hg19canon.2.bt2 +# -rw-rw-r-- 1 james james 3.3K Feb 10 16:54 hg19canon.3.bt2 +# -rw-rw-r-- 1 james james 683M Feb 10 16:54 hg19canon.4.bt2 +# -rw-rw-r-- 1 james james 914M Feb 10 20:45 hg19canon.rev.1.bt2 +# -rw-rw-r-- 1 james james 683M Feb 10 20:45 hg19canon.rev.2.bt2 +# +# then the hisat_indexes.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 8082f04de7ae tool_data_table_conf.xml.sample --- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/tool_data_table_conf.xml.sample Fri Nov 06 14:17:24 2015 -0500 @@ -0,0 +1,13 @@ + + + + + value, dbkey, name, path + +
+ + + value, dbkey, name, path + +
+ diff -r 000000000000 -r 8082f04de7ae tool_dependencies.xml --- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/tool_dependencies.xml Fri Nov 06 14:17:24 2015 -0500 @@ -0,0 +1,6 @@ + + + + + +