# HG changeset patch # User jjohnson # Date 1377011522 14400 # Node ID ce8e6a5b8830a08458e0e492ed82ffa761fe3caf Uploaded diff -r 000000000000 -r ce8e6a5b8830 README --- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/README Tue Aug 20 11:12:02 2013 -0400 @@ -0,0 +1,2 @@ +Uses Picard CreateSequenceDictionary to create a sequence dictionary from a fasta file listed in the all_fasta.loc file. +The location of the resulting sequence dictionary is recorded in the picard_index.loc file. diff -r 000000000000 -r ce8e6a5b8830 data_manager/picard_index_builder.py --- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/data_manager/picard_index_builder.py Tue Aug 20 11:12:02 2013 -0400 @@ -0,0 +1,91 @@ +#!/usr/bin/env python +#Jim Johnson + +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 = "picard_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_picard_index( jar_path, 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-picard-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 ) + basename,ext = os.path.splitext(fasta_base_name) + ref_dict = "%s.dict" % basename + args = [ 'java','-Xmx4G','-jar', jar_path, "R=%s" % sym_linked_fasta_filename, "O=%s" % ref_dict ] + tmp_stderr = tempfile.NamedTemporaryFile( prefix = "tmp-data-manager-picard-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' ) + parser.add_option( '-j', '--jar_path', dest='jar_path', action='store', type="string", default=None, help='path to CreateSequenceDictionary.jar' ) + (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_picard_index( options.jar_path, 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 ce8e6a5b8830 data_manager/picard_index_builder.xml --- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/data_manager/picard_index_builder.xml Tue Aug 20 11:12:02 2013 -0400 @@ -0,0 +1,25 @@ + + builder + + picard + + picard_index_builder.py "${out_file}" --jar_path "\$PICARD_JAR_PATH/CreateSequenceDictionary.jar" --fasta_filename "${all_fasta_source.fields.path}" --fasta_dbkey "${all_fasta_source.fields.dbkey}" --fasta_description "${all_fasta_source.fields.name}" --data_table_name "picard_indexes" + + + + + + + + + + + + + +.. class:: infomark + +**Notice:** If you leave name, description, or id blank, it will be generated automatically. + + + diff -r 000000000000 -r ce8e6a5b8830 data_manager_conf.xml --- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/data_manager_conf.xml Tue Aug 20 11:12:02 2013 -0400 @@ -0,0 +1,22 @@ + + + + + + + + + + + + + ${dbkey}/seq + + ${GALAXY_DATA_MANAGER_DATA_PATH}/${dbkey}/seq/${path} + abspath + + + + + + diff -r 000000000000 -r ce8e6a5b8830 tool-data/all_fasta.loc.sample --- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/tool-data/all_fasta.loc.sample Tue Aug 20 11:12:02 2013 -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 ce8e6a5b8830 tool-data/picard_index.loc.sample --- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/tool-data/picard_index.loc.sample Tue Aug 20 11:12:02 2013 -0400 @@ -0,0 +1,26 @@ +#This is a sample file distributed with Galaxy that enables tools +#to use a directory of Picard dict and associated files. You will need +#to create these data files and then create a picard_index.loc file +#similar to this one (store it in this directory) that points to +#the directories in which those files are stored. The picard_index.loc +#file has this format (longer white space is the TAB character): +# +# +# +#So, for example, if you had hg18 indexed and stored in +#/depot/data2/galaxy/srma/hg18/, +#then the srma_index.loc entry would look like this: +# +#hg18 hg18 hg18 Pretty /depot/data2/galaxy/picard/hg18/hg18.fa +# +#and your /depot/data2/galaxy/srma/hg18/ directory +#would contain the following three files: +#hg18.fa +#hg18.dict +#hg18.fa.fai +# +#The dictionary file for each reference (ex. hg18.dict) must be +#created via Picard (http://picard.sourceforge.net). Note that +#the dict file does not have the .fa extension although the +#path list in the loc file does include it. +# diff -r 000000000000 -r ce8e6a5b8830 tool_data_table_conf.xml.sample --- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/tool_data_table_conf.xml.sample Tue Aug 20 11:12:02 2013 -0400 @@ -0,0 +1,12 @@ + + + + value, dbkey, name, path + +
+ + + value, dbkey, name, path + +
+ diff -r 000000000000 -r ce8e6a5b8830 tool_dependencies.xml --- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/tool_dependencies.xml Tue Aug 20 11:12:02 2013 -0400 @@ -0,0 +1,6 @@ + + + + + +