Mercurial > repos > devteam > data_manager_twobit_builder
changeset 0:74b09c8e5f6e draft
planemo upload for repository https://github.com/galaxyproject/tools-devteam/tree/master/data_managers/data_manager_twobit_builder commit 130cb0c08ad3c5b858ba46b1024dcdccc3cb68c6-dirty
| author | devteam |
|---|---|
| date | Thu, 11 Jun 2015 16:14:27 -0400 |
| parents | |
| children | df883cc67fbd |
| files | README data_manager/twobit_builder.py data_manager/twobit_builder.xml data_manager_conf.xml tool-data/alignseq.loc.sample tool-data/all_fasta.loc.sample tool-data/lastz_seqs.loc.sample tool-data/twobit.loc.sample tool_data_table_conf.xml.sample tool_dependencies.xml |
| diffstat | 10 files changed, 326 insertions(+), 0 deletions(-) [+] |
line wrap: on
line diff
--- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/README Thu Jun 11 16:14:27 2015 -0400 @@ -0,0 +1,1 @@ +TODO
--- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/data_manager/twobit_builder.py Thu Jun 11 16:14:27 2015 -0400 @@ -0,0 +1,92 @@ +#!/usr/bin/env python +#Dan Blankenberg + +import sys, os, tempfile, optparse, uuid, subprocess + +from json import loads, dumps + + +CHUNK_SIZE = 2**20 #1mb + +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 #uuid.uuid4() generate and use an uuid + + 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_twobit( data_manager_dict, fasta_filename, params, target_directory, dbkey, sequence_id, sequence_name ): + twobit_base_name = "%s.2bit" % ( sequence_id ) + twobit_filename = os.path.join( target_directory, twobit_base_name ) + + args = [ 'faToTwoBit', fasta_filename, twobit_filename ] + tmp_stderr = tempfile.NamedTemporaryFile( prefix = "tmp-data-manager-twobit-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() + #lastz_seqs + data_table_entry = dict( value=sequence_id, name=sequence_name, path=twobit_base_name ) + + _add_data_table_entry( data_manager_dict, "lastz_seqs", data_table_entry ) + #twobit.loc + data_table_entry = dict( value=sequence_id, path=twobit_base_name ) + + _add_data_table_entry( data_manager_dict, "twobit", data_table_entry ) + #alignseq + data_table_entry = dict( type="seq", value=sequence_id, path=twobit_base_name ) + + _add_data_table_entry( data_manager_dict, "alignseq_seq", 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' ) + (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_twobit( data_manager_dict, options.fasta_filename, params, target_directory, dbkey, sequence_id, sequence_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/twobit_builder.xml Thu Jun 11 16:14:27 2015 -0400 @@ -0,0 +1,35 @@ +<tool id="twobit_builder_data_manager" name="TwoBit" tool_type="manage_data" version="0.0.1"> + <requirements> + <requirement type="package" version="312">ucsc_tools</requirement> + </requirements> + <description>builder</description> + <command interpreter="python">twobit_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}"</command> + <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" /> + + </inputs> + <outputs> + <data name="out_file" format="data_manager_json"/> + </outputs> + + <tests> + <test> + <param name="all_fasta_source" value="sacCer2"/> + <param name="sequence_name" value=""/> + <output name="sequence_id" file="data_manager_two_bit_out_1.dat"/> + </test> + </tests> + + <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 Thu Jun 11 16:14:27 2015 -0400 @@ -0,0 +1,40 @@ +<?xml version="1.0"?> +<data_managers> + + <data_manager tool_file="data_manager/twobit_builder.xml" id="twobit_builder" version="0.0.1"> + <data_table name="lastz_seqs"> + <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}">${value}/seq/${path}</target> + </move> + <value_translation>${GALAXY_DATA_MANAGER_DATA_PATH}/${value}/seq/${path}</value_translation> + </column> + </output> + </data_table> + + <data_table name="twobit"> + <output> + <column name="value" /> + <column name="path" output_ref="out_file" ><!-- move happens above --> + <value_translation>${GALAXY_DATA_MANAGER_DATA_PATH}/${value}/seq/${path}</value_translation> + </column> + </output> + </data_table> + + <data_table name="alignseq_seq"> + <output> + <column name="type" /><!-- always seq --> + <column name="value" /><!-- also dbkey --> + <column name="path" output_ref="out_file" ><!-- move happens above --> + <value_translation>${GALAXY_DATA_MANAGER_DATA_PATH}/${value}/seq/${path}</value_translation> + </column> + </output> + </data_table> + + </data_manager> + +</data_managers>
--- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/tool-data/alignseq.loc.sample Thu Jun 11 16:14:27 2015 -0400 @@ -0,0 +1,57 @@ +#This is a sample file distributed with Galaxy that enables tools +#to use alignment data stored as axt files (lines starting with "align") +#or nib files (lines starting with "seq"). You will need to index +#them and then create an alignseq.loc file similar to this one (store +#it in this directory) that points to the directories in which those +#alignments are stored. The "align" data referred to by the alignseq.loc +#file has this format (white space characters are TAB characters): +# +#align <build1> <build2> <dir> +# +#So, for example, if you had hg18/bosTau2 alignment files stored in +#/depot/data2/galaxy/hg18/align/bosTau2, then the alignseq.loc entry +#would look like this: +# +#align hg18 bosTau2 /depot/data2/galaxy/hg18/align/bosTau2 +# +#and your /depot/data2/galaxy/hg18/align/bosTau2 directory would +#contain all of your alignment files (e.g.): +# +#-rw-rw-r-- 1 nate galaxy 151842783 2006-01-08 01:00 chr10.axt +#-rw-rw-r-- 1 nate galaxy 79575 2006-01-08 01:00 chr10_random.axt +#-rw-rw-r-- 1 nate galaxy 155015634 2006-01-08 01:01 chr11.axt +#...etc... +# +#Your alignseq.loc file should include an entry per line for each alignment +#file you have stored. For example: +# +#align anoGam1 dm1 /depot/data2/galaxy/anoGam1/align/dm1 +#align anoGam1 dm2 /depot/data2/galaxy/anoGam1/align/dm2 +#align canFam1 hg17 /depot/data2/galaxy/canFam1/align/hg17 +#...etc... +# +#The "seq" data referred to by the alignseq.loc file has this +#format (white space characters are TAB characters): +# +#seq <build1> <dir> +# +#So, for example, if you had anoGam1 sequence files stored in +#/depot/data2/galaxy/anoGam1/seq, then the alignseq.loc entry +#would look like this: +# +#seq anoGam1 /depot/data2/galaxy/anoGam1/seq +#and your seq anoGam1 /depot/data2/galaxy/anoGam1/seq directory would +#contain all of your sequence files (e.g.): +# +#-rw-rw-r-- 1 nate galaxy 24397551 2006-06-26 12:51 chr2L.nib +#-rw-rw-r-- 1 nate galaxy 31362964 2006-06-26 12:51 chr2R.nib +#-rw-rw-r-- 1 nate galaxy 20642013 2006-06-26 12:51 chr3L.nib +#-rw-rw-r-- 1 nate galaxy 26636071 2006-06-26 12:51 chr3R.nib +# +#Your alignseq.loc file should include an entry per line for each sequence +#file you have stored. For example: +# +#seq anoGam1 /depot/data2/galaxy/anoGam1/seq +#seq bosTau2 /depot/data2/galaxy/bosTau2/seq +#seq bosTau3 /depot/data2/galaxy/bosTau3/seq +#...etc...
--- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/tool-data/all_fasta.loc.sample Thu Jun 11 16:14:27 2015 -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): +# +#<unique_build_id> <dbkey> <display_name> <file_path> +# +#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. +#
--- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/tool-data/lastz_seqs.loc.sample Thu Jun 11 16:14:27 2015 -0400 @@ -0,0 +1,30 @@ +#This is a sample file distributed with Galaxy that enables tools +#to use a directory of 2bit genome files for use with Lastz. You will +#need to supply these files and then create a lastz_seqs.loc file +#similar to this one (store it in this directory) that points to +#the directories in which those files are stored. The lastz_seqs.loc +#file has this format (white space characters are TAB characters): +# +#<unique_build_id> <display_name> <file_path> +# +#So, for example, if your lastz_seqs.loc began like this: +# +#hg18 Human (Homo sapiens): hg18 /depot/data2/galaxy/twobit/hg18.2bit +#hg19 Human (Homo sapiens): hg19 /depot/data2/galaxy/twobit/hg19.2bit +#mm9 Mouse (Mus musculus): mm9 /depot/data2/galaxy/twobit/mm9.2bit +# +#then your /depot/data2/galaxy/twobit/ directory +#would need to contain the following 2bit files: +# +#-rw-r--r-- 1 james universe 830134 2005-09-13 10:12 hg18.2bit +#-rw-r--r-- 1 james universe 527388 2005-09-13 10:12 hg19.2bit +#-rw-r--r-- 1 james universe 269808 2005-09-13 10:12 mm9.2bit +# +#Your lastz_seqs.loc file should include an entry per line for +#each file you have stored that you want to be available. Note that +#your files should all have the extension '2bit'. +# +#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. +#
--- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/tool-data/twobit.loc.sample Thu Jun 11 16:14:27 2015 -0400 @@ -0,0 +1,26 @@ +#This is a sample file distributed with Galaxy that is used by some +#tools. The twobit.loc file has this format (white space characters +#are TAB characters): +# +#<Build> <FullPathToFile> +# +#So, for example, if you had droPer1 twobit files stored in +#/depot/data2/galaxy/droPer1/, then the twobit.loc entry +#would look like this: +# +#droPer1 /depot/data2/galaxy/droPer1/droPer1.2bit +# +#and your /depot/data2/galaxy/droPer1/ directory would +#contain all of your twobit files (e.g.): +# +#-rw-rw-r-- 1 nate galaxy 48972650 2007-05-04 11:27 droPer1.2bit +#...etc... +# +#Your twobit.loc file should include an entry per line for each twobit +#file you have stored. For example: +# +#droPer1 /depot/data2/galaxy/droPer1/droPer1.2bit +#apiMel2 /depot/data2/galaxy/apiMel2/apiMel2.2bit +#droAna1 /depot/data2/galaxy/droAna1/droAna1.2bit +#droAna2 /depot/data2/galaxy/droAna2/droAna2.2bit +#...etc...
--- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/tool_data_table_conf.xml.sample Thu Jun 11 16:14:27 2015 -0400 @@ -0,0 +1,21 @@ +<!-- 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 2bit sequence files for use in Lastz --> + <table name="lastz_seqs" comment_char="#"> + <columns>value, name, path</columns> + <file path="tool-data/lastz_seqs.loc" /> + </table> + <table name="twobit" comment_char="#"> + <columns>value, path</columns> + <file path="tool-data/twobit.loc" /> + </table> + <table name="alignseq_seq" comment_char="#"> + <columns>type, value, path</columns> + <file path="tool-data/alignseq.loc" /> + </table> +</tables>
--- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/tool_dependencies.xml Thu Jun 11 16:14:27 2015 -0400 @@ -0,0 +1,6 @@ +<?xml version="1.0"?> +<tool_dependency> + <package name="ucsc_tools" version="312"> + <repository changeset_revision="2d6bafd63401" name="package_ucsc_tools_312" owner="iuc" toolshed="https://toolshed.g2.bx.psu.edu" /> + </package> +</tool_dependency>