# HG changeset patch
# User wolma
# Date 1561390567 14400
# Node ID 6127cd38980b5a104f7d43a77c00aa89d285bd83
# Parent 0c5c464b17b573bd0537bbc7c3e2428ea8763bb2
planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/data_managers/data_manager_star_index_builder commit 056ae20332ed001ad50a7e733df3595108172c6c-dirty
diff -r 0c5c464b17b5 -r 6127cd38980b data_manager/macros.xml
--- /dev/null Thu Jan 01 00:00:00 1970 +0000
+++ b/data_manager/macros.xml Mon Jun 24 11:36:07 2019 -0400
@@ -0,0 +1,68 @@
+
+
+
+ 2.7.1a
+
+ 2.7.1a
+
+
+
+ star
+ samtools
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ --readFilesCommand zcat
+
+
+
+ 10.1093/bioinformatics/bts635
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
diff -r 0c5c464b17b5 -r 6127cd38980b data_manager/rna_star_index_builder.py
--- /dev/null Thu Jan 01 00:00:00 1970 +0000
+++ b/data_manager/rna_star_index_builder.py Mon Jun 24 11:36:07 2019 -0400
@@ -0,0 +1,32 @@
+#!/usr/bin/env python
+
+import argparse
+import json
+
+
+def main():
+ parser = argparse.ArgumentParser()
+ parser.add_argument( '--config-file' )
+ parser.add_argument( '--value' )
+ parser.add_argument( '--dbkey' )
+ parser.add_argument( '--name' )
+ parser.add_argument( '--subdir' )
+ parser.add_argument( '--data-table' )
+ parser.add_argument( '--with-gene-model', action='store_true' )
+ parser.add_argument( '--index-version' )
+
+ args = parser.parse_args()
+
+ if args.dbkey in [ None, '', '?' ]:
+ raise Exception( '"%s" is not a valid dbkey. You must specify a valid dbkey.' % ( args.dbkey ) )
+
+ with_gene_model = "0"
+ if args.with_gene_model:
+ with_gene_model = "1"
+
+ data_manager_dict = {'data_tables': {args.data_table: [dict({"value": args.value, "dbkey": args.dbkey, "name": args.name, "path": args.subdir, "with_gene_model": with_gene_model, "version": args.index_version} )]}}
+ open( args.config_file, 'w' ).write( json.dumps( data_manager_dict ) )
+
+
+if __name__ == "__main__":
+ main()
diff -r 0c5c464b17b5 -r 6127cd38980b data_manager/rna_star_index_builder.xml
--- /dev/null Thu Jan 01 00:00:00 1970 +0000
+++ b/data_manager/rna_star_index_builder.xml Mon Jun 24 11:36:07 2019 -0400
@@ -0,0 +1,164 @@
+
+ builder
+
+
+ macros.xml
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ --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.
+ ]]>
+
+
diff -r 0c5c464b17b5 -r 6127cd38980b data_manager_conf.xml
--- /dev/null Thu Jan 01 00:00:00 1970 +0000
+++ b/data_manager_conf.xml Mon Jun 24 11:36:07 2019 -0400
@@ -0,0 +1,25 @@
+
+
+
+
+
+
+
+
diff -r 0c5c464b17b5 -r 6127cd38980b tool-data/all_fasta.loc.sample
--- /dev/null Thu Jan 01 00:00:00 1970 +0000
+++ b/tool-data/all_fasta.loc.sample Mon Jun 24 11:36:07 2019 -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):
+#
+#
+#
+#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 0c5c464b17b5 -r 6127cd38980b tool-data/rnastar_index2_versioned.loc.sample
--- /dev/null Thu Jan 01 00:00:00 1970 +0000
+++ b/tool-data/rnastar_index2_versioned.loc.sample Mon Jun 24 11:36:07 2019 -0400
@@ -0,0 +1,26 @@
+#This is a sample file distributed with Galaxy that enables tools
+#to use a directory of rna-star indexed sequences data files. You will
+#need to create these data files and then create a rnastar_index2.loc
+#file similar to this one (store it in this directory) that points to
+#the directories in which those files are stored. The rnastar_index2.loc
+#file has this format (longer white space characters are TAB characters):
+#
+#
+#
+#The column should be 1 or 0, indicating whether the index
+#was built with annotations (i.e., --sjdbGTFfile and --sjdbOverhang were used)
+#or not.
+#
+#The column indicates the STAR version that introduced the format of
+#the index, i.e., the oldest STAR version that could make use of the index.
+#
+#Note that STAR indices can become quite large. Consequently, it is only
+#advisable to create indices with annotations if it's known ahead of time that
+#(A) the annotations won't be frequently updated and (B) the read lengths used
+#will also rarely vary. If either of these is not the case, it's advisable to
+#create indices without annotations and then specify an annotation file and
+#maximum read length (minus 1) when running STAR.
+#
+#hg19 hg19 hg19 full /mnt/galaxyIndices/genomes/hg19/rnastar 0 2.7.1a
+#hg19Ensembl hg19Ensembl hg19 full with Ensembl annotation /mnt/galaxyIndices/genomes/hg19Ensembl/rnastar 1 2.7.1a
+