# HG changeset patch # User jeremyjliu # Date 1421022112 18000 # Node ID ba049ce6569314a20f5105c689879e6d8c2c520e Initial upload diff -r 000000000000 -r ba049ce65693 data_manager/data_manager_fetch_motifs.py --- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/data_manager/data_manager_fetch_motifs.py Sun Jan 11 19:21:52 2015 -0500 @@ -0,0 +1,73 @@ +#!/usr/bin/env python +#Dan Blankenberg + +import sys +import os +import tempfile +import shutil +import optparse +import urllib2 +#import uuid +from ftplib import FTP +import tarfile +import zipfile +import gzip +import bz2 + +from galaxy.util.json import from_json_string, to_json_string + +CHUNK_SIZE = 2**20 #1mb + +def download_motif_databases( data_manager_dict, params, target_directory, motif_db ): + TEST_DOWNLOAD_URL = 'http://gehlenborg.com/wp-content/uploads/motif/pouya_test_motifs.bed.bgz' + #TO DO: Add tbi file + + url = TEST_DOWNLOAD_URL + fasta_reader = urllib2.urlopen( url ) + + data_table_entry = _stream_fasta_to_file( fasta_reader, target_directory, params ) + _add_data_table_entry( data_manager_dict, data_table_entry ) + +def _add_data_table_entry( data_manager_dict, data_table_entry ): + data_manager_dict['data_tables'] = data_manager_dict.get( 'data_tables', {} ) + data_manager_dict['data_tables']['all_fasta'] = data_manager_dict['data_tables'].get( 'all_fasta', [] ) + data_manager_dict['data_tables']['all_fasta'].append( data_table_entry ) + return data_manager_dict + +def _stream_fasta_to_file( fasta_stream, target_directory, params, close_stream=True ): + fasta_base_filename = "pouya_test_motifs.bed.bgz" + fasta_filename = os.path.join( target_directory, fasta_base_filename ) + fasta_writer = open( fasta_filename, 'wb+' ) + + while True: + buffer = fasta_stream.read(CHUNK_SIZE) + if not buffer: + break + + fasta_writer.write(buffer) + + fasta_stream.close() + fasta_writer.close() + + return dict( value="test", name="Test Pouya Subset (hg19)", path=fasta_base_filename ) + +def main(): + #Parse Command Line + parser = optparse.OptionParser() + parser.add_option( '-m', '--motif_db', dest='motif_db', action='store', type="string", default=None, help='motif_db' ) + (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 = {} + + #Fetch the Motif Database + download_motif_databases( data_manager_dict, params, target_directory, motif_db ) + + #save info to json file + open( filename, 'wb' ).write( to_json_string( data_manager_dict ) ) + +if __name__ == "__main__": main() diff -r 000000000000 -r ba049ce65693 data_manager/data_manager_fetch_motifs.xml --- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/data_manager/data_manager_fetch_motifs.xml Sun Jan 11 19:21:52 2015 -0500 @@ -0,0 +1,22 @@ + + fetching + data_manager_fetch_motifs.py "${out_file}" --motif_db ${motif_db_selector} + + + + + + + + + + + + + **What it does** + + Fetches a reference genome from various sources (UCSC, NCBI, URL, Galaxy History, or a server directory) and populates the "all_fasta" data table. + + **Notice:** If you leave name, description, or id blank, it will be generated automatically. + + diff -r 000000000000 -r ba049ce65693 data_manager/test.py --- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/data_manager/test.py Sun Jan 11 19:21:52 2015 -0500 @@ -0,0 +1,13 @@ +#!/usr/bin/env python +import optparse + +def main(): + #Parse Command Line + parser = optparse.OptionParser() + parser.add_option( '-d', '--dbkey_description', dest='dbkey_description', action='store', type="string", default=None, help='dbkey_description' ) + (options, args) = parser.parse_args() + + filename = args[0] + print(args) + +main() \ No newline at end of file diff -r 000000000000 -r ba049ce65693 data_manager_conf.xml --- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/data_manager_conf.xml Sun Jan 11 19:21:52 2015 -0500 @@ -0,0 +1,21 @@ + + + + + + + + + + + ${path} + motifs/${path} + + ${GALAXY_DATA_MANAGER_DATA_PATH}/motifs/${path} + abspath + + + + + + diff -r 000000000000 -r ba049ce65693 tool-data/all_fasta.loc.sample --- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/tool-data/all_fasta.loc.sample Sun Jan 11 19:21:52 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 ba049ce65693 tool_data_table_conf.xml.sample --- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/tool_data_table_conf.xml.sample Sun Jan 11 19:21:52 2015 -0500 @@ -0,0 +1,7 @@ + + + + value, name, path + +
+