changeset 0:5a613b179173 draft

Uploaded

--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/.shed.yml	Sat Feb 07 22:08:14 2015 -0500
@@ -0,0 +1,2 @@
+owner: bgruening
+name: data_manager_diamond_database_builder

--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/README	Sat Feb 07 22:08:14 2015 -0500
@@ -0,0 +1,2 @@
+Diamond database builder
+========================

--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/data_manager/data_manager_diamond_database_builder.py	Sat Feb 07 22:08:14 2015 -0500
@@ -0,0 +1,231 @@
+#!/usr/bin/env python
+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 cleanup_before_exit( tmp_dir ):
+    if tmp_dir and os.path.exists( tmp_dir ):
+        shutil.rmtree( tmp_dir )
+
+
+def stop_err(msg):
+    sys.stderr.write(msg)
+    sys.exit(1)
+
+
+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 _get_files_in_ftp_path( ftp, path ):
+    path_contents = []
+    ftp.retrlines( 'MLSD %s' % ( path ), path_contents.append )
+    return [ line.split( ';' )[ -1 ].lstrip() for line in path_contents ]
+
+
+def _get_stream_readers_for_tar( file_obj, tmp_dir ):
+    fasta_tar = tarfile.open( fileobj=file_obj, mode='r:*' )
+    return [ fasta_tar.extractfile( member ) for member in fasta_tar.getmembers() ]
+
+
+def _get_stream_readers_for_zip( file_obj, tmp_dir ):
+    fasta_zip = zipfile.ZipFile( file_obj, 'r' )
+    rval = []
+    for member in fasta_zip.namelist():
+        fasta_zip.extract( member, tmp_dir )
+        rval.append( open( os.path.join( tmp_dir, member ), 'rb' ) )
+    return rval
+
+
+def _get_stream_readers_for_gzip( file_obj, tmp_dir ):
+    return [ gzip.GzipFile( fileobj=file_obj, mode='rb' ) ]
+
+
+def _get_stream_readers_for_bz2( file_obj, tmp_dir ):
+    return [ bz2.BZ2File( file_obj.name, 'rb' ) ]
+
+
+def download_from_ncbi( data_manager_dict, params, target_directory, sequence_id, sequence_name ):
+    NCBI_FTP_SERVER = 'ftp.ncbi.nlm.nih.gov'
+    NCBI_DOWNLOAD_PATH = '/blast/db/FASTA/'
+    COMPRESSED_EXTENSIONS = [ ( '.tar.gz', _get_stream_readers_for_tar ), ( '.tar.bz2', _get_stream_readers_for_tar ), ( '.zip', _get_stream_readers_for_zip ), ( '.fa.gz', _get_stream_readers_for_gzip ), ( '.fa.bz2', _get_stream_readers_for_bz2 ) ]
+
+    ucsc_dbkey = params['param_dict']['reference_source']['requested_dbkey'] or dbkey
+    ftp = FTP( UCSC_FTP_SERVER )
+    ftp.login()
+
+    path_contents = _get_files_in_ftp_path( ftp, UCSC_DOWNLOAD_PATH )
+
+    ucsc_file_name = None
+    get_stream_reader = None
+    ext = None
+    for ext, get_stream_reader in COMPRESSED_EXTENSIONS:
+        if "%s%s" % ( sequence_name, ext ) in path_contents:
+            ucsc_file_name = "%s%s%s" % ( UCSC_DOWNLOAD_PATH, sequence_name, ext )
+            break
+
+    if not ucsc_file_name:
+        raise Exception( 'Unable to determine filename for UCSC Genome for %s: %s' % ( ucsc_dbkey, path_contents ) )
+
+    tmp_dir = tempfile.mkdtemp( prefix='tmp-data-manager-ucsc-' )
+    ucsc_fasta_filename = os.path.join( tmp_dir, "%s%s" % ( sequence_name, ext ) )
+    
+    fasta_base_filename = "%s.fa" % sequence_id
+    fasta_filename = os.path.join( target_directory, fasta_base_filename )
+    fasta_writer = open( fasta_filename, 'wb+' )
+    
+    tmp_extract_dir = os.path.join ( tmp_dir, 'extracted_fasta' )
+    os.mkdir( tmp_extract_dir )
+    
+    tmp_fasta = open( ucsc_fasta_filename, 'wb+' )
+    
+    ftp.retrbinary( 'RETR %s' % ucsc_file_name, tmp_fasta.write )
+    
+    tmp_fasta.flush()
+    tmp_fasta.seek( 0 )
+    
+    fasta_readers = get_stream_reader( tmp_fasta, tmp_extract_dir )
+    
+    data_table_entry = _stream_fasta_to_file( fasta_readers, target_directory, sequence_id, sequence_name, params )
+    _add_data_table_entry( data_manager_dict, data_table_entry )
+    
+    for fasta_reader in fasta_readers:
+        fasta_reader.close()
+    tmp_fasta.close()
+    cleanup_before_exit( tmp_dir )
+
+
+def download_from_url( data_manager_dict, params, target_directory, sequence_id, sequence_name ):
+    #TODO: we should automatically do decompression here
+    urls = filter( bool, map( lambda x: x.strip(), params['param_dict']['reference_source']['user_url'].split( '\n' ) ) )
+    fasta_reader = [ urllib2.urlopen( url ) for url in urls ]
+    
+    data_table_entry = _stream_fasta_to_file( fasta_reader, target_directory, sequence_id, sequence_name, params )
+    _add_data_table_entry( data_manager_dict, data_table_entry )
+
+
+def download_from_history( data_manager_dict, params, target_directory, sequence_id, sequence_name ):
+    #TODO: allow multiple FASTA input files
+    input_filename = params['param_dict']['reference_source']['input_fasta']
+    if isinstance( input_filename, list ):
+        fasta_reader = [ open( filename, 'rb' ) for filename in input_filename ]
+    else:
+        fasta_reader = open( input_filename )
+    
+    data_table_entry = _stream_fasta_to_file( fasta_reader, target_directory, sequence_id, sequence_name, params )
+    _add_data_table_entry( data_manager_dict, data_table_entry )
+
+
+def copy_from_directory( data_manager_dict, params, target_directory, sequence_id, sequence_name ):
+    input_filename = params['param_dict']['reference_source']['fasta_filename']
+    create_symlink = params['param_dict']['reference_source']['create_symlink'] == 'create_symlink'
+    if create_symlink:
+        data_table_entry = _create_symlink( input_filename, target_directory, sequence_id, sequence_name )
+    else:
+        if isinstance( input_filename, list ):
+            fasta_reader = [ open( filename, 'rb' ) for filename in input_filename ]
+        else:
+            fasta_reader = open( input_filename )    
+        data_table_entry = _stream_fasta_to_file( fasta_reader, target_directory, sequence_id, sequence_name, 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, sequence_id, sequence_name, params, close_stream=True ):
+    fasta_base_filename = "%s.fa" % sequence_id
+    fasta_filename = os.path.join( target_directory, fasta_base_filename )
+    fasta_writer = open( fasta_filename, 'wb+' )
+
+    if isinstance( fasta_stream, list ) and len( fasta_stream ) == 1:
+        fasta_stream = fasta_stream[0]
+
+    if isinstance( fasta_stream, list ):
+        last_char = None
+        for fh in fasta_stream:
+            if last_char not in [ None, '\n', '\r' ]:
+                fasta_writer.write( '\n' )
+            while True:
+                data = fh.read( CHUNK_SIZE )
+                if data:
+                    fasta_writer.write( data )
+                    last_char = data[-1]
+                else:
+                    break
+            if close_stream:
+                fh.close()
+    else:
+        while True:
+            data = fasta_stream.read( CHUNK_SIZE )
+            if data:
+                fasta_writer.write( data )
+            else:
+                break
+        if close_stream:
+            fasta_stream.close()
+    
+    fasta_writer.close()
+    
+    return dict( value=sequence_id, name=sequence_name, path=fasta_base_filename )
+
+
+def _create_symlink( input_filename, target_directory, sequence_id, sequence_name ):
+    fasta_base_filename = "%s.fa" % sequence_id
+    fasta_filename = os.path.join( target_directory, fasta_base_filename )
+    os.symlink( input_filename, fasta_filename )
+    return dict( value=sequence_id, name=sequence_name, path=fasta_base_filename )
+
+
+REFERENCE_SOURCE_TO_DOWNLOAD = dict( ncbi=download_from_ncbi, url=download_from_url, history=download_from_history, directory=copy_from_directory )
+
+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]
+    
+    params = from_json_string( open( filename ).read() )
+    target_directory = params[ 'output_data' ][0]['extra_files_path']
+    os.mkdir( target_directory )
+    data_manager_dict = {}
+
+    sequence_id, sequence_name = get_id_name( params, fasta_description=options.fasta_description )
+
+    #Fetch the FASTA
+    REFERENCE_SOURCE_TO_DOWNLOAD[ params['param_dict']['reference_source']['reference_source_selector'] ]( data_manager_dict, params, target_directory, sequence_id, sequence_name )
+    
+    #save info to json file
+    open( filename, 'wb' ).write( to_json_string( data_manager_dict ) )
+
+if __name__ == "__main__":
+    main()

--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/data_manager/data_manager_diamond_database_builder.xml	Sat Feb 07 22:08:14 2015 -0500
@@ -0,0 +1,44 @@
+<tool id="diamond_database_builder" name="Diamond Database" tool_type="manage_data" version="0.0.1">
+    <description>builder</description>
+    <requirements>
+        <requirement type="package" version="0.6.13">diamond</requirement>
+    </requirements>
+    <command interpreter="python">data_manager_sam_fasta_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 "fasta_indexes"</command>
+    <inputs>
+        <param type="text" name="database" value="" label="Name of database" help="e.g. nr"/>
+        <param type="text" name="database_desc" value="" label="Description of database" />
+        <param type="text" name="database_id" value="" label="Database ID" />
+        <conditional name="reference_source">
+          <param name="reference_source_selector" type="select" label="Choose the source for the reference genome">
+            <option value="ncbi">NCBI</option>
+            <option value="url">URL</option>
+            <option value="history">History</option>
+            <option value="directory">Directory on Server</option>
+          </param>
+          <when value="ncbi">
+            <param type="text" name="requested_identifier" value="" label="NCBI identifier" help="e.g. nr" optional="False" />
+          </when>
+          <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 orignal data instead of copying" checked="False" />
+          </when>
+        </conditional>
+    </inputs>
+    <outputs>
+        <data name="out_file" format="data_manager_json"/>
+    </outputs>
+    <help>
+
+.. class:: infomark
+
+NCBI databases can be downded from ftp://ftp.ncbi.nlm.nih.gov/blast/db/FASTA/
+For example the NR database can be downloaded from ftp://ftp.ncbi.nlm.nih.gov/blast/db/FASTA/nr.gz
+
+    </help>
+</tool>

--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/data_manager_conf.xml	Sat Feb 07 22:08:14 2015 -0500
@@ -0,0 +1,19 @@
+<?xml version="1.0"?>
+<data_managers>
+    <data_manager tool_file="data_manager/data_manager_diamond_database_builder.xml" id="diamond_database_builder" version="0.0.1">
+        <data_table name="diamond_database">
+            <output>
+                <column name="value" />
+                <column name="name" />
+                <column name="db_path" output_ref="out_file" >
+                    <move type="directory" relativize_symlinks="True">
+                        <!-- <source>${path}</source>--> <!-- out_file.extra_files_path is used as base by default --> <!-- if no source, eg for type=directory, then refers to base -->
+                        <target base="${GALAXY_DATA_MANAGER_DATA_PATH}">diamond_database/${value}</target>
+                    </move>
+                    <value_translation>${GALAXY_DATA_MANAGER_DATA_PATH}/diamond_database/${value}/${path}</value_translation>
+                    <value_translation type="function">abspath</value_translation>
+                </column>
+            </output>
+        </data_table>
+    </data_manager>
+</data_managers>

--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/tool-data/diamond_database.loc.sample	Sat Feb 07 22:08:14 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):
+#
+#<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_table_conf.xml.sample	Sat Feb 07 22:08:14 2015 -0500
@@ -0,0 +1,7 @@
+<tables>
+    <!-- Locations of all fasta files required to build Diamond databases -->
+    <table name="diamond_database" comment_char="#">
+        <columns>value, name, db_path</columns>
+        <file path="tool-data/diamond_database.loc" />
+    </table>
+</tables>

--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/tool_dependencies.xml	Sat Feb 07 22:08:14 2015 -0500
@@ -0,0 +1,6 @@
+<?xml version="1.0"?>
+<tool_dependency>
+    <package name="diamond" version="0.6.13">
+        <repository changeset_revision="25ea67a866ca" name="package_diamond_0_6_13" owner="iuc" toolshed="https://testtoolshed.g2.bx.psu.edu" />
+    </package>
+</tool_dependency>