Mercurial > repos > iuc > data_manager_star_index_builder
comparison data_manager/rna_star_index_builder.xml @ 4:6ef6520f14fc draft
planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/data_managers/data_manager_star_index_builder commit 39b9b154845ecf517f7d9e9d76c386b473c3ebd2
author | iuc |
---|---|
date | Wed, 18 Jul 2018 13:26:12 -0400 |
parents | cdc4d8a998e1 |
children | f5eb9afa8f8a |
comparison
equal
deleted
inserted
replaced
3:50ca9af6db2e | 4:6ef6520f14fc |
---|---|
1 <tool id="rna_star_index_builder_data_manager" name="rnastar index2" tool_type="manage_data" version="0.0.4" profile="17.01"> | 1 <tool id="rna_star_index_builder_data_manager" name="rnastar index2" tool_type="manage_data" version="0.0.5" profile="17.01"> |
2 <description>builder</description> | 2 <description>builder</description> |
3 | 3 |
4 <macros> | 4 <macros> |
5 <import>macros.xml</import> | 5 <import>macros.xml</import> |
6 </macros> | 6 </macros> |
7 | 7 |
8 <expand macro="requirements" /> | 8 <expand macro="requirements" /> |
9 | 9 |
10 <command><![CDATA[ | 10 <command><![CDATA[ |
11 #import json, os | 11 if [ -z "\$GALAXY_MEMORY_MB" ] ; then |
12 #set params = json.loads( open( str($out_file) ).read() ) | 12 GALAXY_MEMORY_BYTES=31000000000 ; |
13 #set target_directory = $params[ 'output_data' ][0]['extra_files_path'].encode('ascii', 'replace') | 13 else |
14 #set subdir = os.path.basename(target_directory) | 14 GALAXY_MEMORY_BYTES=\$((GALAXY_MEMORY_MB * 1000000)) ; |
15 fi ; | |
15 | 16 |
16 mkdir -p '${target_directory}/${subdir}' && | 17 #import json, os |
18 #set params = json.loads(open(str($out_file)).read()) | |
19 #set target_directory = $params['output_data'][0]['extra_files_path'].encode('ascii', 'replace') | |
20 #set subdir = os.path.basename(target_directory) | |
17 | 21 |
18 STAR | 22 mkdir -p '${target_directory}/${subdir}' && |
19 --runMode genomeGenerate | |
20 --genomeFastaFiles '${all_fasta_source.fields.path}' | |
21 --genomeDir '${target_directory}/${subdir}' | |
22 #if str($GTFconditional.GTFselect) == "withGTF": | |
23 --sjdbGTFfile '${GTFconditional.sjdbGTFfile}' | |
24 --sjdbOverhang '${GTFconditional.sjdbOverhang}' | |
25 #end if | |
26 --runThreadN \${GALAXY_SLOTS:-2} && | |
27 | 23 |
28 python ${__tool_directory__}/rna_star_index_builder.py | 24 STAR |
29 --config-file '${out_file}' | 25 --runMode genomeGenerate |
30 --value '${all_fasta_source.fields.value}' | 26 --genomeFastaFiles '${all_fasta_source.fields.path}' |
31 --dbkey '${all_fasta_source.fields.dbkey}' | 27 --genomeDir '${target_directory}/${subdir}' |
32 #if $name: | 28 --limitGenomeGenerateRAM \${GALAXY_MEMORY_BYTES} |
33 --name '$name' | 29 #if $GTFconditional.GTFselect == "withGTF": |
34 #else | 30 --sjdbGTFfile '${GTFconditional.sjdbGTFfile}' |
35 --name '${all_fasta_source.fields.name}' | 31 --sjdbOverhang ${GTFconditional.sjdbOverhang} |
36 #end if | 32 #end if |
37 #if str($GTFconditional.GTFselect) == "withGTF": | 33 #if $advanced_options.advanced_options_selector == "advanced": |
38 --withGTF 1 | 34 --genomeSAindexNbases ${advanced_options.genomeSAindexNbases} |
39 #end if | 35 --genomeChrBinNbits ${advanced_options.genomeChrBinNbits} |
40 --data-table 'rnastar_index2' | 36 --genomeSAsparseD ${advanced_options.genomeSAsparseD} |
41 --subdir '${subdir}' | 37 #end if |
38 --runThreadN \${GALAXY_SLOTS:-2} && | |
39 | |
40 python '${__tool_directory__}/rna_star_index_builder.py' | |
41 --config-file '${out_file}' | |
42 --value '${all_fasta_source.fields.value}' | |
43 --dbkey '${all_fasta_source.fields.dbkey}' | |
44 #if $name: | |
45 --name '$name' | |
46 #else | |
47 --name '${all_fasta_source.fields.name}' | |
48 #end if | |
49 #if str($GTFconditional.GTFselect) == "withGTF": | |
50 --withGTF 1 | |
51 #end if | |
52 --data-table rnastar_index2 | |
53 --subdir '${subdir}' | |
42 ]]></command> | 54 ]]></command> |
43 <inputs> | 55 <inputs> |
44 <param name="all_fasta_source" type="select" label="Source FASTA Sequence"> | 56 <param name="all_fasta_source" type="select" label="Source FASTA Sequence"> |
45 <options from_data_table="all_fasta"/> | 57 <options from_data_table="all_fasta"/> |
46 </param> | 58 </param> |
47 <param name="name" | 59 <param name="name" type="text" value="" label="Informative name for sequence index" |
48 type="text" | 60 help="By using different settings, you may have several indices per reference genome. Give an appropriate description to the index to distinguish between indices"/> |
49 value="" | |
50 label="Informative name for sequence index" | |
51 help="By using different settings, you may have several indices per reference genome. Give an appropriate description to the index to distinguish between indices"/> | |
52 <conditional name="GTFconditional"> | 61 <conditional name="GTFconditional"> |
53 <param name="GTFselect" type="select" label="Reference genome with or without an annotation" help="Must the index have been created WITH a GTF file (if not you can specify one afterward)."> | 62 <param name="GTFselect" type="select" label="Reference genome with or without an annotation" help="Must the index have been created WITH a GTF file (if not you can specify one afterward)."> |
54 <option value="withoutGTF">use genome reference without builtin gene-model</option> | 63 <option value="withoutGTF">use genome reference without builtin gene-model</option> |
55 <option value="withGTF">use genome reference with builtin gene-model</option> | 64 <option value="withGTF">use genome reference with builtin gene-model</option> |
56 </param> | 65 </param> |
57 <when value="withGTF"> | 66 <when value="withGTF"> |
58 <param argument="--sjdbGTFfile" type="data" format="gff3,gtf" label="Gene model (gff3,gtf) file for splice junctions" optional="false" help="Exon junction information for mapping splices"/> | 67 <param argument="--sjdbGTFfile" type="data" format="gff3,gtf" label="Gene model (gff3,gtf) file for splice junctions" optional="false" help="Exon junction information for mapping splices"/> |
59 <param argument="--sjdbOverhang" type="integer" min="1" value="100" label="Length of the genomic sequence around annotated junctions" help="Used in constructing the splice junctions database. Ideal value is ReadLength-1"/> | 68 <param argument="--sjdbOverhang" type="integer" min="1" value="100" label="Length of the genomic sequence around annotated junctions" help="Used in constructing the splice junctions database. Ideal value is ReadLength-1"/> |
60 </when> | 69 </when> |
61 <when value="withoutGTF" /> | 70 <when value="withoutGTF" /> |
71 </conditional> | |
72 <conditional name="advanced_options"> | |
73 <param name="advanced_options_selector" type="select" label="Advanced options"> | |
74 <option value="default" selected="true">Use default options</option> | |
75 <option value="advanced">Set advanced options</option> | |
76 </param> | |
77 <when value="default" /> | |
78 <when value="advanced"> | |
79 <param argument="--genomeSAindexNbases" type="integer" min="1" value="14" | |
80 label="Length (bases) of the SA pre-indexing string" | |
81 help="Typically between 10 and 15. Longer strings will use much more memory, but allow | |
82 faster searches. For small genomes, the parameter –genomeSAindexNbases must be scaled | |
83 down to min(14, log2(GenomeLength)/2 - 1). For example, for 1 megaBase genome, this is | |
84 equal to 9, for 100 kiloBase genome, this is equal to 7."/> | |
85 <param argument="--genomeChrBinNbits" type="integer" min="1" value="18" | |
86 label="Log2(chrBin), where chrBin is the size of the bins for genome storage" | |
87 help="Each chromosome will occupy an integer number of bins. For a genome with large number | |
88 of contigs, it is recommended to scale this parameter as min(18, | |
89 log2[max(GenomeLength/NumberOfReferences,ReadLength)]). For example, for 3 gigaBase | |
90 genome with 100,000 chromosomes/scaffolds, this is equal to 15."/> | |
91 <param argument="--genomeSAsparseD" type="integer" min="1" value="1" label="Suffix array sparsity" | |
92 help="The distance between indices: use bigger numbers to decrease needed RAM at the cost of | |
93 mapping speed reduction"/> | |
94 </when> | |
62 </conditional> | 95 </conditional> |
63 </inputs> | 96 </inputs> |
64 | 97 |
65 <outputs> | 98 <outputs> |
66 <data name="out_file" format="data_manager_json"/> | 99 <data name="out_file" format="data_manager_json"/> |
77 <output name="out_file" file="test_star_01.data_manager_json"/> | 110 <output name="out_file" file="test_star_01.data_manager_json"/> |
78 </test> | 111 </test> |
79 </tests> | 112 </tests> |
80 --> | 113 --> |
81 | 114 |
82 <help> | 115 <help><![CDATA[ |
83 | |
84 .. class:: infomark | 116 .. class:: infomark |
85 | 117 |
86 <![CDATA[ | |
87 *What it does* | 118 *What it does* |
88 | 119 |
89 This is a Galaxy datamanager for the rna STAR gap-aware RNA aligner. | 120 This is a Galaxy datamanager for the rna STAR gap-aware RNA aligner. |
90 | 121 |
91 Please read the fine manual - that and the google group are the places to learn about the options above. | 122 Please read the fine manual - that and the google group are the places to learn about the options above. |
93 *Memory requirements* | 124 *Memory requirements* |
94 | 125 |
95 To run efficiently, RNA-STAR requires enough free memory to | 126 To run efficiently, RNA-STAR requires enough free memory to |
96 hold the SA-indexed reference genome in RAM. For Human Genome hg19 this | 127 hold the SA-indexed reference genome in RAM. For Human Genome hg19 this |
97 index is about 27GB and running RNA-STAR requires approximately ~30GB of RAM. | 128 index is about 27GB and running RNA-STAR requires approximately ~30GB of RAM. |
98 For custom genomes, the rule of thub is to multiply the size of the | 129 For custom genomes, the rule of thumb is to multiply the size of the |
99 reference FASTA file by 9 to estimated required amount of RAM. | 130 reference FASTA file by 9 to estimated required amount of RAM. |
100 | 131 |
101 *Note on sjdbOverhang* | 132 *Note on sjdbOverhang* |
102 | 133 |
103 From https://groups.google.com/forum/#!topic/rna-star/h9oh10UlvhI:: | 134 From https://groups.google.com/forum/#!topic/rna-star/h9oh10UlvhI:: |
124 3. 'transcript_id' attribute that assigns each exon to a transcript (--this name can be changed with --sjdbGTFtagExonParentTranscript) | 155 3. 'transcript_id' attribute that assigns each exon to a transcript (--this name can be changed with --sjdbGTFtagExonParentTranscript) |
125 | 156 |
126 Cheers | 157 Cheers |
127 Alex | 158 Alex |
128 | 159 |
129 **Notice:** If you leave name, description, or id blank, it will be generated automatically. | 160 **Notice:** If you leave name, description, or id blank, it will be generated automatically. |
130 ]]> | 161 ]]></help> |
131 </help> | |
132 <expand macro="citations" /> | 162 <expand macro="citations" /> |
133 </tool> | 163 </tool> |