Mercurial > repos > fubar > data_manager_rnasta

--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/README	Mon Sep 29 20:25:10 2014 -0400
@@ -0,0 +1,1 @@
+TODO
\ No newline at end of file
--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/data_manager/rnastar_index_builder.py	Mon Sep 29 20:25:10 2014 -0400
@@ -0,0 +1,111 @@
+#!/usr/bin/env python
+#Dan Blankenberg
+# adapted from Dan's BWA one for rna star
+# ross lazarus sept 2014
+#
+import sys
+import os
+import tempfile
+import optparse
+import subprocess
+
+from galaxy.util.json import from_json_string, to_json_string
+
+DEFAULT_DATA_TABLE_NAME = "rnastar_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_rnastar_index( data_manager_dict, fasta_filename, target_directory, dbkey, sequence_id, sequence_name, data_table_name,
+    sjdbOverhang,sjdbGTFfile, sjdbFileChrStartEnd,sjdbGTFtagExonParentTranscript,sjdbGTFfeatureExon,sjdbGTFchrPrefix,n_threads):
+    #TODO: allow multiple FASTA input files
+    #tmp_dir = tempfile.mkdtemp( prefix='tmp-data-manager-bwa-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 )
+    pdict={'target_directory':target_directory,'n_threads':n_threads, 'sjdbFileChrStartEnd':sjdbFileChrStartEnd,
+           'sjdbGTFtagExonParentTranscript':sjdbGTFtagExonParentTranscript, 'sjdbGTFfeatureExon':sjdbGTFfeatureExon,
+           'sjdbGTFchrPrefix':sjdbGTFchrPrefix,'sjdbOverhang':sjdbOverhang, 'sjdbGTFfile':sjdbGTFfile,
+           'sym_linked_fasta_filename':sym_linked_fasta_filename}
+
+    cl = 'STAR --runMode genomeGenerate --genomeFastaFiles %(sym_linked_fasta_filename)s --genomeDir %(target_directory)s --runThreadN %(n_threads)s' % pdict
+    if sjdbGTFfile:
+         cl += '''--sjdbGTFchrPrefix %(sjdbGTFchrPrefix)s --sjdbGTFfeatureExon %(sjdbGTFfeatureExon)s --sjdbOverhang %(sjdbOverhang)s
+   --sjdbGTFfile %(sjdbGTFfile)s --sjdbGTFtagExonParentTranscript %(sjdbGTFtagExonParentTranscript)s''' %  pdict
+    elif sjdbFileChrStartEnd:
+        cl += '--sjdbFileChrStartEnd %(sjdbFileChrStartEnd)s --sjdbOverhang %(sjdbOverhangs)s'
+    tmp_stderr = tempfile.NamedTemporaryFile( prefix = "tmp-data-manager-rnastar-index-builder-stderr" )
+    args = cl.split(' ')
+    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: retcode=",retcode
+        while True:
+            chunk = tmp_stderr.read( CHUNK_SIZE )
+            if not chunk:
+                break
+            sys.stderr.write( chunk )
+    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( '--out_file', default=None)
+    parser.add_option( '--out_index_path', default=None)
+    parser.add_option( '--sjdbGTFfile', type="string", default=None )
+    parser.add_option( '--sjdbGTFchrPrefix', type="string", default=None )
+    parser.add_option( '--sjdbGTFfeatureExon', type="string", default=None )
+    parser.add_option( '--sjdbGTFtagExonParentTranscript', type="string", default=None )
+    parser.add_option( '--sjdbFileChrStartEnd', type="string", default=None )
+    parser.add_option( '--sjdbOverhang', type="int", default=100 )
+    parser.add_option( '--runThreadN', type="int", default=4 )
+    (options, args) = parser.parse_args()
+
+    filename = options.out_file
+    params = from_json_string( open( filename ).read() )
+    target_directory = options.out_index_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_rnastar_index( data_manager_dict, options.fasta_filename, target_directory, dbkey, sequence_id, sequence_name, data_table_name=options.data_table_name,
+      sjdbOverhang=options.sjdbOverhang,sjdbGTFfile=options.sjdbGTFfile,
+      sjdbFileChrStartEnd=options.sjdbFileChrStartEnd,sjdbGTFtagExonParentTranscript=options.sjdbGTFtagExonParentTranscript,
+      sjdbGTFfeatureExon=options.sjdbGTFfeatureExon,sjdbGTFchrPrefix=options.sjdbGTFchrPrefix,
+      n_threads=options.runThreadN )
+
+    #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/rnastar_index_builder.xml	Mon Sep 29 20:25:10 2014 -0400
@@ -0,0 +1,126 @@
+<tool id="rnastar_index_builder_data_manager" name="rnastar index" tool_type="manage_data" version="0.0.1">
+    <description>builder</description>
+    <requirements>
+        <requirement type="package" version="2.4.0d">rnastar</requirement>
+    </requirements>
+    <command interpreter="python">
+rnastar_index_builder.py --out_file "${out_file}" --fasta_filename "${all_fasta_source.fields.path}"
+--fasta_dbkey "${all_fasta_source.fields.dbkey}" --fasta_description "${all_fasta_source.fields.name}"
+--data_table_name "rnastar_indexes" --out_index_path "$out_file.extra_files_path" --runThreadN 1
+#if $genemodel.modelformat=="gff3":
+ --sjdbOverhang "${genemodel.sjdbOverhang}"
+ --sjdbGTFfile "${genemodel.sjdbGTFfile}"
+ --sjdbGTFtagExonParentTranscript "${genemodel.sjdbGTFtagExonParentTranscript}"
+ --sjdbGTFfeatureExon "${genemodel.sjdbGTFfeatureExon}"
+#end if
+#if $genemodel.modelformat=="bed":
+ --sjdbFileChrStartEnd "${genemodel.sjdbFileChrStartEnd}"
+ --sjdbOverhang "${genemodel.sjdbOverhang}"
+#end if
+#if $genemodel.modelformat=="None":
+ --sjdbOverhang 0
+#end if
+</command>
+    <stdio>
+        <regex match=".*" source="both" level="warning" description="stdout/err chatter:"/>
+    </stdio>
+
+    <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="Informative name for sequence index" />
+        <param type="text" name="sequence_id" value="" label="ID for sequence index" />
+
+
+        <conditional name="genemodel">
+            <param name="modelformat" type="select"
+               label="Choose the format of gene model data from your history - bed or gff3"
+               help="This will be the source of splice junction indexing if required">
+              <option value="gff3"  selected="true">gff3,gtf</option>
+              <option value="bed">BED - tabular chr,start,end,strand</option>
+              <option value="None" >None - no splice junction index</option>
+             </param>
+             <when value="gff3">
+                <param type="data" format="gff3,gff" name="sjdbGTFfile" value="" label="Gene model - must be gff3 or compatible and must match the input genome"
+                   help="Required if you want to index splice junctions during index generation." />
+
+                <param type="text" name="sjdbGTFchrPrefix" value="chr" label="String prefix for GTF chromosomes"
+                    help='GTF prefix for chromosome names (e.g. "chr" to use ENSMEBL annotations with UCSC geneomes)' >
+                    <sanitizer invalid_char="">
+                        <valid initial="string.printable"/>
+                     </sanitizer>
+                </param>
+                <param type="text" name="sjdbGTFfeatureExon" value="exon_id" label="GTF feature to use as exon marker"
+                   help="GTF feature type in GTF file to be used as exons for building transcripts - use what's in your GTF">
+                    <sanitizer invalid_char="">
+                        <valid initial="string.printable"/>
+                     </sanitizer>
+                </param>
+
+                <param type="text" name="sjdbGTFtagExonParentTranscript" value="transcript_id" label="GTF feature to define for each exon's parents"
+                   help="GTF tag name to be used as exons' parents for building transcripts - use what's in your GTF">
+                    <sanitizer invalid_char="">
+                        <valid initial="string.printable"/>
+                     </sanitizer>
+                </param>
+
+                <param type="integer" name="sjdbOverhang" value="100" label="Splice junction overhang. If=0, splice junction database NOT used"
+                help="int>=0: length of the donor/acceptor sequence on each side, (mate_length - 1)" />
+
+            </when>
+            <when value='bed'>
+                <param type="data" format="bed" name="sjdbFileChrStartEnd" value="" label="Introns as a tabular bed (chr,start,end,strand) file matching the input genome"
+                   help="Required if you want to index splice junctions during index generation." />
+                <param type="integer" name="sjdbOverhang" value="100" label="Splice junction overhang. If=0, splice junction database NOT used"
+                help="int>=0: length of the donor/acceptor sequence on each side, (mate_length - 1)" />
+           </when>
+            <when value='None'>
+            </when>
+        </conditional>
+    </inputs>
+    <outputs>
+        <data name="out_file" format="data_manager_json"/>
+    </outputs>
+    <help>
+
+.. class:: infomark
+
+*What it does*
+
+This is a Galaxy datamanager for the rna STAR gap-aware RNA aligner.
+
+Please read the fine manual - that and the google group are the places to learn about the options above.
+
+*Note on sjdbOverhang*
+
+From https://groups.google.com/forum/#!topic/rna-star/h9oh10UlvhI::
+
+  James is right, using large enough --sjdbOverhang is safer and should not generally cause any problems with reads of varying length. If your reads are very short, &lt;50b, then I would strongly recommend using optimum --sjdbOverhang=mateLength-1
+  By mate length I mean the length of one of the ends of the read, i.e. it's 100 for 2x100b PE or 1x100b SE. For longer reads you can simply use generic --sjdbOverhang 100.
+  It is a bit confusing because of the way I named this parameter. --sjdbOverhang Noverhang is only used at the genome generation step  for constructing the reference sequence out of the annotations.
+  Basically, the Noverhang exonic bases from the donor site and Noverhang exonic bases from the acceptor site are spliced together for each of the junctions, and these spliced sequences are added to the genome sequence.
+
+  At the mapping stage, the reads are aligned to both genomic and splice sequences simultaneously. If a read maps to one of spliced sequences and crosses the "junction" in the middle of it, the coordinates of two pspliced pieces are translated back to genomic space and added to the collection of mapped pieces, which are then all "stitched" together to form the final alignment. Since in the process of "maximal mapped length" search the read is split into pieces of no longer than --seedSearchStartLmax (=50 by default) bases, even if the read (mate) is longer than --sjdbOverhang, it can still be mapped to the spliced reference, as long as --sjdbOverhang > --seedSearchStartLmax.
+
+  Cheers
+  Alex
+
+*Note on gene model requirements for splice junctions*
+
+From https://groups.google.com/forum/#!msg/rna-star/3Y_aaTuzBrE/lUylTB8h5vMJ::
+
+    When you generate a genome with annotations, you need to specify --sjdbOverhang value, which ideally should be equal to (oneMateLength-1), or you could use a generic value of ~100.
+
+    Your gtf lines look fine to me. STAR needs 3 features from a GTF file:
+    1. Chromosome names in col.1 that agree with chromosome names in genome .fasta files. If you have "chr2L" names in the genome .fasta files, and "2L" in the .gtf file, then you need to use --sjdbGTFchrPrefix chr option.
+    2. 'exon' in col.3 for the exons of all transcripts (this name can be changed with --sjdbGTFfeatureExon)
+    3. 'transcript_id' attribute that assigns each exon to a transcript (--this name can be changed with --sjdbGTFtagExonParentTranscript)
+
+    Cheers
+    Alex
+
+**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	Mon Sep 29 20:25:10 2014 -0400
@@ -0,0 +1,22 @@
+<?xml version="1.0"?>
+<data_managers>
+
+    <data_manager tool_file="data_manager/rnastar_index_builder.xml" id="rnastar_index_builder" version="0.0.1">
+        <data_table name="rnastar_indexes">
+            <output>
+                <column name="value" />
+                <column name="dbkey" />
+                <column name="name" />
+                <column name="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="${GALAXY_DATA_MANAGER_DATA_PATH}">${dbkey}/rnastar_index/${value}</target>
+                    </move>
+                    <value_translation>${GALAXY_DATA_MANAGER_DATA_PATH}/${dbkey}/rnastar_index/${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/all_fasta.loc.sample	Mon Sep 29 20:25:10 2014 -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/rnastar_index.loc.sample	Mon Sep 29 20:25:10 2014 -0400
@@ -0,0 +1,38 @@
+#This is a sample file distributed with Galaxy that enables tools
+#to use a directory of BWA indexed sequences data files. You will need
+#to create these data files and then create a bwa_index.loc file
+#similar to this one (store it in this directory) that points to
+#the directories in which those files are stored. The bwa_index.loc
+#file has this format (longer white space characters are TAB characters):
+#
+#<unique_build_id>   <dbkey>   <display_name>   <file_path>
+#
+#So, for example, if you had phiX indexed stored in
+#/depot/data2/galaxy/phiX/base/,
+#then the bwa_index.loc entry would look like this:
+#
+#phiX174   phiX   phiX Pretty   /depot/data2/galaxy/phiX/base/phiX.fa
+#
+#and your /depot/data2/galaxy/phiX/base/ directory
+#would contain phiX.fa.* files:
+#
+#-rw-r--r--  1 james    universe 830134 2005-09-13 10:12 phiX.fa.amb
+#-rw-r--r--  1 james    universe 527388 2005-09-13 10:12 phiX.fa.ann
+#-rw-r--r--  1 james    universe 269808 2005-09-13 10:12 phiX.fa.bwt
+#...etc...
+#
+#Your bwa_index.loc file should include an entry per line for each
+#index set you have stored. The "file" in the path does not actually
+#exist, but it is the prefix for the actual index files.  For example:
+#
+#phiX174				phiX	phiX174			/depot/data2/galaxy/phiX/base/phiX.fa
+#hg18canon				hg18	hg18 Canonical	/depot/data2/galaxy/hg18/base/hg18canon.fa
+#hg18full				hg18	hg18 Full		/depot/data2/galaxy/hg18/base/hg18full.fa
+#/orig/path/hg19.fa		hg19	hg19			/depot/data2/galaxy/hg19/base/hg19.fa
+#...etc...
+#
+#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. That is why the
+#hg19 entry above looks odd. New genomes can be better-looking.
+#
--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/tool_data_table_conf.xml.sample	Mon Sep 29 20:25:10 2014 -0400
@@ -0,0 +1,12 @@
+<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 indexes in the BWA mapper format -->
+    <table name="rnastar_indexes" comment_char="#">
+        <columns>value, dbkey, name, path</columns>
+        <file path="tool-data/rnastar_index.loc" />
+    </table>
+</tables>
--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/tool_dependencies.xml	Mon Sep 29 20:25:10 2014 -0400
@@ -0,0 +1,6 @@
+<?xml version="1.0"?>
+<tool_dependency>
+    <package name="rnastar" version="2.4.0d">
+        <repository changeset_revision="2ab1b6182b63" name="package_rnastar_240d" owner="fubar" toolshed="https://testtoolshed.g2.bx.psu.edu" />
+    </package>
+</tool_dependency>