| Next changeset 1:955a8d483fa3 (2018-07-10) |
|
Commit message:
Uploaded |
|
added:
README.md data_manager/data_manager_fetch_gff.py data_manager/data_manager_fetch_gff.xml data_manager_conf.xml tool-data/all_gff.loc.sample tool_data_table_conf.xml.sample |
| b |
| diff -r 000000000000 -r ac4fde07eaed README.md --- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/README.md Mon Jul 09 11:58:50 2018 -0400 |
| b |
| @@ -0,0 +1,2 @@ +# data_manager_fetch_gff +Galaxy Data Manager to fetch gene annotation files |
| b |
| diff -r 000000000000 -r ac4fde07eaed data_manager/data_manager_fetch_gff.py --- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/data_manager/data_manager_fetch_gff.py Mon Jul 09 11:58:50 2018 -0400 |
| [ |
| b'@@ -0,0 +1,458 @@\n+#!/usr/bin/env python\n+#Dan Blankenberg\n+\n+import sys\n+import os\n+import tempfile\n+import shutil\n+import optparse\n+from ftplib import FTP\n+import tarfile\n+import zipfile\n+import gzip\n+import bz2\n+try:\n+ # For Python 3.0 and later\n+ from urllib.request import urlopen\n+ from io import BytesIO as StringIO\n+ from io import UnsupportedOperation\n+except ImportError:\n+ # Fall back to Python 2\'s urllib2\n+ from urllib2 import urlopen\n+ from StringIO import StringIO\n+ UnsupportedOperation = AttributeError\n+from json import loads, dumps\n+\n+\n+CHUNK_SIZE = 2**20 # 1mb\n+\n+DATA_TABLE_NAME = \'all_gff\'\n+\n+def cleanup_before_exit( tmp_dir ):\n+ if tmp_dir and os.path.exists( tmp_dir ):\n+ shutil.rmtree( tmp_dir )\n+\n+\n+def stop_err(msg):\n+ sys.stderr.write(msg)\n+ sys.exit(1)\n+\n+\n+def get_dbkey_dbname_id_name( params, dbkey_description=None ):\n+ dbkey = params[\'param_dict\'][\'dbkey_source\'][\'dbkey\']\n+ #TODO: ensure sequence_id is unique and does not already appear in location file\n+ sequence_id = params[\'param_dict\'][\'sequence_id\']\n+ if not sequence_id:\n+ sequence_id = dbkey #uuid.uuid4() generate and use an uuid instead?\n+ \n+ if params[\'param_dict\'][\'dbkey_source\'][\'dbkey_source_selector\'] == \'new\':\n+ dbkey_name = params[\'param_dict\'][\'dbkey_source\'][\'dbkey_name\']\n+ if not dbkey_name:\n+ dbkey_name = dbkey\n+ else:\n+ dbkey_name = None\n+ \n+ sequence_name = params[\'param_dict\'][\'sequence_name\']\n+ if not sequence_name:\n+ sequence_name = dbkey_description\n+ if not sequence_name:\n+ sequence_name = dbkey\n+ return dbkey, dbkey_name, sequence_id, sequence_name\n+\n+\n+def _get_files_in_ftp_path( ftp, path ):\n+ path_contents = []\n+ ftp.retrlines( \'MLSD %s\' % ( path ), path_contents.append )\n+ return [ line.split( \';\' )[ -1 ].lstrip() for line in path_contents ]\n+\n+\n+def _get_stream_readers_for_tar( fh, tmp_dir ):\n+ fasta_tar = tarfile.open( fileobj=fh, mode=\'r:*\' )\n+ return [x for x in [fasta_tar.extractfile(member) for member in fasta_tar.getmembers()] if x]\n+\n+\n+def _get_stream_readers_for_zip( fh, tmp_dir ):\n+ """\n+ Unpacks all archived files in a zip file.\n+ Individual files will be concatenated (in _stream_fasta_to_file)\n+ """\n+ fasta_zip = zipfile.ZipFile( fh, \'r\' )\n+ rval = []\n+ for member in fasta_zip.namelist():\n+ fasta_zip.extract( member, tmp_dir )\n+ rval.append( open( os.path.join( tmp_dir, member ), \'rb\' ) )\n+ return rval\n+\n+\n+def _get_stream_readers_for_gzip( fh, tmp_dir ):\n+ return [ gzip.GzipFile( fileobj=fh, mode=\'rb\') ]\n+\n+\n+def _get_stream_readers_for_bz2( fh, tmp_dir ):\n+ return [ bz2.BZ2File( fh.name, \'rb\') ]\n+\n+\n+def sort_fasta( fasta_filename, sort_method, params ):\n+ if sort_method is None:\n+ return\n+ assert sort_method in SORTING_METHODS, ValueError( "%s is not a valid sorting option." % sort_method )\n+ return SORTING_METHODS[ sort_method ]( fasta_filename, params )\n+\n+\n+def _move_and_index_fasta_for_sorting( fasta_filename ):\n+ unsorted_filename = tempfile.NamedTemporaryFile().name\n+ shutil.move( fasta_filename, unsorted_filename )\n+ fasta_offsets = {}\n+ unsorted_fh = open( unsorted_filename )\n+ while True:\n+ offset = unsorted_fh.tell()\n+ line = unsorted_fh.readline()\n+ if not line:\n+ break\n+ if line.startswith( ">" ):\n+ line = line.split( None, 1 )[0][1:]\n+ fasta_offsets[ line ] = offset\n+ unsorted_fh.close()\n+ current_order = map( lambda x: x[1], sorted( map( lambda x: ( x[1], x[0] ), fasta_offsets.items() ) ) )\n+ return ( unsorted_filename, fasta_offsets, current_order )\n+\n+\n+def _write_sorted_fasta( sorted_names, fasta_offsets, sorted_fasta_filename, unsorted_fasta_filename ):\n+ unsorted_fh = open( unsorted_fasta_filename )\n+ sorted_fh = open( sorted_fasta_filename, \'wb+\' )\n+ \n+ for name in sorted_names:\n+ '..b'y_name:\n+ #do len calc here\n+ #len_base_name = "%s.len" % ( dbkey )\n+ #compute_fasta_length( fasta_filename, os.path.join( target_directory, len_base_name ), keep_first_word=True )\n+ dbkey_dict = dict( value=dbkey, name=dbkey_name, len_path=\'\' )\n+ \n+ return [ ( \'__dbkeys__\', dbkey_dict ), ( DATA_TABLE_NAME, dict( value=sequence_id, dbkey=dbkey, name=sequence_name, path=fasta_base_filename ) ) ]\n+\n+\n+def compute_fasta_length( fasta_file, out_file, keep_first_word=False ):\n+\n+ infile = fasta_file\n+ out = open( out_file, \'w\')\n+\n+ fasta_title = \'\'\n+ seq_len = 0\n+\n+ first_entry = True\n+\n+ for line in open( infile ):\n+ line = line.strip()\n+ if not line or line.startswith( \'#\' ):\n+ continue\n+ if line[0] == \'>\':\n+ if first_entry == False:\n+ if keep_first_word:\n+ fasta_title = fasta_title.split()[0]\n+ out.write( "%s\\t%d\\n" % ( fasta_title[ 1: ], seq_len ) )\n+ else:\n+ first_entry = False\n+ fasta_title = line\n+ seq_len = 0\n+ else:\n+ seq_len += len(line)\n+\n+ # last fasta-entry\n+ if keep_first_word:\n+ fasta_title = fasta_title.split()[0]\n+ out.write( "%s\\t%d\\n" % ( fasta_title[ 1: ], seq_len ) )\n+ out.close()\n+\n+\n+def _create_symlink( input_filename, target_directory, dbkey, dbkey_name, sequence_id, sequence_name ):\n+ fasta_base_filename = "%s.fa" % sequence_id\n+ fasta_filename = os.path.join( target_directory, fasta_base_filename )\n+ os.symlink( input_filename, fasta_filename )\n+ \n+ dbkey_dict = None\n+ if dbkey_name:\n+ #do len calc here\n+ len_base_name = "%s.len" % ( dbkey )\n+ compute_fasta_length( fasta_filename, os.path.join( target_directory, len_base_name ), keep_first_word=True )\n+ dbkey_dict = dict( value=dbkey, name=dbkey_name, len_path=len_base_name )\n+ \n+ return [ ( \'__dbkeys__\', dbkey_dict ), ( DATA_TABLE_NAME, dict( value=sequence_id, dbkey=dbkey, name=sequence_name, path=fasta_base_filename ) ) ]\n+\n+\n+REFERENCE_SOURCE_TO_DOWNLOAD = dict( ucsc=download_from_ucsc, ncbi=download_from_ncbi, url=download_from_url, history=download_from_history, directory=copy_from_directory )\n+\n+SORTING_METHODS = dict( as_is=_sort_fasta_as_is, lexicographical=_sort_fasta_lexicographical, gatk=_sort_fasta_gatk, custom=_sort_fasta_custom )\n+\n+\n+def main():\n+ #Parse Command Line\n+ parser = optparse.OptionParser()\n+ parser.add_option( \'-d\', \'--dbkey_description\', dest=\'dbkey_description\', action=\'store\', type="string", default=None, help=\'dbkey_description\' )\n+ parser.add_option( \'-t\', \'--type\', dest=\'file_type\', action=\'store\', type=\'string\', default=None, help=\'file_type\')\n+ (options, args) = parser.parse_args()\n+ \n+ filename = args[0]\n+ global DATA_TABLE_NAME\n+ if options.file_type == \'representative\':\n+ DATA_TABLE_NAME= \'representative_gff\'\n+ params = loads( open( filename ).read() )\n+ target_directory = params[ \'output_data\' ][0][\'extra_files_path\']\n+ os.mkdir( target_directory )\n+ data_manager_dict = {}\n+ \n+ dbkey, dbkey_name, sequence_id, sequence_name = get_dbkey_dbname_id_name( params, dbkey_description=options.dbkey_description ) \n+ \n+ if dbkey in [ None, \'\', \'?\' ]:\n+ raise Exception( \'"%s" is not a valid dbkey. You must specify a valid dbkey.\' % ( dbkey ) )\n+\n+ # Create a tmp_dir, in case a zip file needs to be uncompressed\n+ tmp_dir = tempfile.mkdtemp()\n+ #Fetch the FASTA\n+ try:\n+ REFERENCE_SOURCE_TO_DOWNLOAD[ params[\'param_dict\'][\'reference_source\'][\'reference_source_selector\'] ]( data_manager_dict, params, target_directory, dbkey, dbkey_name, sequence_id, sequence_name, tmp_dir )\n+ finally:\n+ cleanup_before_exit(tmp_dir)\n+ #save info to json file\n+ open( filename, \'wb\' ).write( dumps( data_manager_dict ).encode() )\n+ \n+if __name__ == "__main__":\n+ main()\n' |
| b |
| diff -r 000000000000 -r ac4fde07eaed data_manager/data_manager_fetch_gff.xml --- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/data_manager/data_manager_fetch_gff.xml Mon Jul 09 11:58:50 2018 -0400 |
| [ |
| @@ -0,0 +1,82 @@ +<tool id="data_manager_fetch_gff" name="Create entries in gff data table" version="0.0.1" tool_type="manage_data"> + <description>fetching</description> + <command><![CDATA[ + python "$__tool_directory__"/data_manager_fetch_gff.py "${out_file}" + --type $file_type + #if str( $dbkey_source.dbkey_source_selector ) == 'existing': + --dbkey_description ${ dbkey_source.dbkey.get_display_text() } + #else + --dbkey_description "${ dbkey_source.dbkey_name or $dbkey_source.dbkey }" + #end if + + ]]></command> + <inputs> + <param name="file_type" type="select" label="GFF file with only one representative transcript per gene (for htseq-count use) or full features file"> + <option value="representative">Representative GFF</option> + <option value="full">GFF with complete features</option> + </param> + + <conditional name="dbkey_source"> + <param name="dbkey_source_selector" type="select" label="Use existing dbkey or create a new one."> + <option value="existing" selected="True">Existing</option> + <option value="new">New</option> + </param> + <when value="existing"> + <param name="dbkey" type="genomebuild" label="DBKEY to assign to data" /> + </when> + <when value="new"> + <param type="text" name="dbkey" value="" label="dbkey" optional="False" /> + <param type="text" name="dbkey_name" value="" label="Display name for dbkey" /> + </when> + </conditional> + <param type="text" name="sequence_name" value="" label="Name of sequence" /> + <param type="text" name="sequence_id" value="" label="ID for sequence" /> + <conditional name="reference_source"> + <param name="reference_source_selector" type="select" label="Choose the source for the reference genome"> + <option value="url">URL</option> + <option value="history">History</option> + <option value="directory">Directory on Server</option> + </param> + <when value="url"> + <param type="text" area="True" name="user_url" value="http://" label="URLs" optional="False" /> + </when> + <when value="history"> + <param name="input_fasta" type="data" format="fasta" label="FASTA File" multiple="False" optional="False" /> + </when> + <when value="directory"> + <param type="text" name="fasta_filename" value="" label="Full path to FASTA File on disk" optional="False" /> + <param type="boolean" name="create_symlink" truevalue="create_symlink" falsevalue="copy_file" label="Create symlink to original data instead of copying" checked="False" /> + </when> + </conditional> + </inputs> + <outputs> + <data name="out_file" format="data_manager_json"/> + </outputs> + <tests> + <!-- TODO: need some way to test that new entry was added to data table --> + <test> + <param name="dbkey" value="anoGam1"/> + <param name="sequence_name" value=""/> + <param name="sequence_desc" value=""/> + <param name="sequence_id" value=""/> + <param name="reference_source_selector" value="history"/> + <param name="input_fasta" value="phiX174.fasta"/> + <param name="sort_selector" value="as_is"/> + <output name="out_file" file="phiX174.data_manager_json"/> + </test> + </tests> + <help> +**What it does** + +Fetches a gff file from various sources (URL, Galaxy History, or a server directory) and populates the "all_gff" data table. + +------ + + + +.. class:: infomark + +**Notice:** If you leave name, description, or id blank, it will be generated automatically. + + </help> +</tool> |
| b |
| diff -r 000000000000 -r ac4fde07eaed data_manager_conf.xml --- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/data_manager_conf.xml Mon Jul 09 11:58:50 2018 -0400 |
| b |
| @@ -0,0 +1,47 @@ +<data_manager tool_file="data_manager/data_manager_fetch_gff.xml" id="data_manager_fetch_gff"> + <data_table name="all_gff"> + <output> + <column name="value" /> + <column name="dbkey" /> + <column name="name" /> + <column name="path" output_ref="out_file"> + <move type="file"> + <source>${path}</source> + <target base="${GALAXY_DATA_MANAGER_DATA_PATH}">${dbkey}/gff/${path}</target> + </move> + <value_translation>${GALAXY_DATA_MANAGER_DATA_PATH}/${dbkey}/gff/${path}</value_translation> + <value_translation type="function">abspath</value_translation> + </column> + </output> + </data_table> + <data_table name="representative_gff"> + <output> + <column name="value" /> + <column name="dbkey" /> + <column name="name" /> + <column name="path" output_ref="out_file"> + <move type="file"> + <source>${path}</source> + <target base="${GALAXY_DATA_MANAGER_DATA_PATH}">${dbkey}/representative_gff/${path}</target> + </move> + <value_translation>${GALAXY_DATA_MANAGER_DATA_PATH}/${dbkey}/representative_gff/${path}</value_translation> + <value_translation type="function">abspath</value_translation> + </column> + </output> + </data_table> + + <data_table name="__dbkeys__"> + <output> + <column name="value" /> + <column name="name" /> + <column name="len_path" output_ref="out_file"> + <move type="file"> + <source>${len_path}</source> + <target base="${GALAXY_DATA_MANAGER_DATA_PATH}">${value}/len/${len_path}</target> + </move> + <value_translation>${GALAXY_DATA_MANAGER_DATA_PATH}/${value}/len/${len_path}</value_translation> + <value_translation type="function">abspath</value_translation> + </column> + </output> + </data_table> + </data_manager> |
| b |
| diff -r 000000000000 -r ac4fde07eaed tool-data/all_gff.loc.sample --- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/tool-data/all_gff.loc.sample Mon Jul 09 11:58:50 2018 -0400 |
| b |
| @@ -0,0 +1,3 @@ +#The all_gff.loc file has this format: +# +#<id> <dbkey> <name> <path_to_gff_file> |
| b |
| diff -r 000000000000 -r ac4fde07eaed tool_data_table_conf.xml.sample --- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/tool_data_table_conf.xml.sample Mon Jul 09 11:58:50 2018 -0400 |
| b |
| @@ -0,0 +1,5 @@ +<?xml version="1.0"?> +<tables> + <table name="all_gff" comment_char="#"> <columns>value, dbkey, name, path</columns> <file path="tool-data/all_gff.loc" /> </table> + <table name="representative_gff" comment_char="#"> <columns>value, dbkey, name, path</columns> <file path="tool-data/representative_gff.loc" /> </table> +</tables> |