Mercurial > repos > devteam > picard

comparison picard_CollectRnaSeqMetrics.xml @ 15:00fe2ff64467 draft

Find changesets by keywords (author, files, the commit message), revision number or hash, or revset expression.
planemo upload for repository https://github.com/galaxyproject/tools-devteam/tree/master/tools/picard commit f65b40f4eb3c3431b8d9213f86238deebfd6bc29
author devteam
date Thu, 08 Dec 2016 06:43:38 -0500
parents 465cbb0cf2eb
children 6741a8ace658
comparison
equal deleted inserted replaced
14:465cbb0cf2eb 15:00fe2ff64467
1 <tool name="CollectRnaSeqMetrics" id="picard_CollectRnaSeqMetrics" version="@TOOL_VERSION@.0"> 1 <tool name="CollectRnaSeqMetrics" id="picard_CollectRnaSeqMetrics" version="@TOOL_VERSION@.1">
2 <description> collect metrics about the alignment of RNA to various functional classes of loci in the genome</description> 2 <description> collect metrics about the alignment of RNA to various functional classes of loci in the genome</description>
3 <macros> 3 <macros>
4 <import>picard_macros.xml</import> 4 <import>picard_macros.xml</import>
5 </macros> 5 </macros>
6 <expand macro="requirements"> 6 <expand macro="requirements">
7 <requirement type="package" version="3.3.1">r</requirement> 7 <requirement type="package" version="3.3.1">r</requirement>
8 <requirement type="package" version="324">ucsc-gff3togenepred</requirement>
9 <requirement type="package" version="324">ucsc-gtftogenepred</requirement>
8 </expand> 10 </expand>
9 <command detect_errors="exit_code"><![CDATA[ 11 <command detect_errors="exit_code"><![CDATA[
10
11 ## Set up input files 12 ## Set up input files
12 @symlink_element_identifier@ 13 @symlink_element_identifier@
13 ## Reference sequences 14 ## Reference sequences
14 15
15 #set $reference_fasta_filename = "localref.fa" 16 #set $reference_fasta_filename = "localref.fa"
21 #end if 22 #end if
22 23
23 ## refFlat data 24 ## refFlat data
24 ## The awk line below converts a file obtained from UCSC as specified in the tool help to refFlat format 25 ## The awk line below converts a file obtained from UCSC as specified in the tool help to refFlat format
25 26
26 grep -v '^#' ${refFlat} | awk '{print $11"\t"$1"\t"$2"\t"$3"\t"$4"\t"$5"\t"$6"\t"$7"\t"$8"\t"$9"\t"$10}' > refFlat.tab && 27 #if str($gene_reference_source.gene_reference_source_selector) == "gtf"
28 #if $gene_reference_source.refFlat.ext != 'gff3'
29 gtfToGenePred '${gene_reference_source.refFlat}' refFlat.tab.raw &&
30 #else
31 gff3ToGenePred '${gene_reference_source.refFlat}' refFlat.tab.raw &&
32 #end if
33
34 grep -v '^#' refFlat.tab.raw | awk '{print $12"\t"$1"\t"$2"\t"$3"\t"$4"\t"$5"\t"$6"\t"$7"\t"$8"\t"$9"\t"$10}' > refFlat.tab &&
35 #else
36 grep -v '^#' ${refFlat} | awk '{print $11"\t"$1"\t"$2"\t"$3"\t"$4"\t"$5"\t"$6"\t"$7"\t"$8"\t"$9"\t"$10}' > refFlat.tab &&
37 #end if
38
27 39
28 ## Start picard command 40 ## Start picard command
29 41
30 @java_options@ 42 @java_options@
31 picard 43 picard
32 CollectRnaSeqMetrics 44 CollectRnaSeqMetrics
33 REF_FLAT=refFlat.tab 45 REF_FLAT=refFlat.tab
34 46
35 #if str( $ribosomal_intervals ) != "None": 47 #if str( $ribosomal_intervals ) != "None":
36 RIBOSOMAL_INTERVALS="${ribosomal_intervals}" 48 RIBOSOMAL_INTERVALS="${ribosomal_intervals}"
37 #end if 49 #end if
38 50
39 STRAND_SPECIFICITY="${strand_specificity}" 51 STRAND_SPECIFICITY="${strand_specificity}"
40 MINIMUM_LENGTH="${minimum_length}" 52 MINIMUM_LENGTH="${minimum_length}"
41 CHART_OUTPUT="${pdfFile}" 53 CHART_OUTPUT="${pdfFile}"
42 54
43 #for $sequence_to_ignore in $ignore_list: 55 #for $sequence_to_ignore in $ignore_list:
44 IGNORE_SEQUENCE="${sequence_to_ignore.sequence}" 56 IGNORE_SEQUENCE="${sequence_to_ignore.sequence}"
45 #end for 57 #end for
46 58
47 RRNA_FRAGMENT_PERCENTAGE="${rrna_fragment_percentage}" 59 RRNA_FRAGMENT_PERCENTAGE="${rrna_fragment_percentage}"
48 METRIC_ACCUMULATION_LEVEL="${metric_accumulation_level}" 60 METRIC_ACCUMULATION_LEVEL="${metric_accumulation_level}"
49 INPUT='$escaped_element_identifier' 61 INPUT='$escaped_element_identifier'
50 OUTPUT="${outFile}" 62 OUTPUT="${outFile}"
51 REFERENCE_SEQUENCE="${reference_fasta_filename}" 63 REFERENCE_SEQUENCE="${reference_fasta_filename}"
52 ASSUME_SORTED="${assume_sorted}" 64 ASSUME_SORTED="${assume_sorted}"
53 65
54 QUIET=true
55 VERBOSITY=ERROR
56 VALIDATION_STRINGENCY=${validation_stringency} 66 VALIDATION_STRINGENCY=${validation_stringency}
57 67
58 ]]></command> 68 ]]></command>
59 69
60 <inputs> 70 <inputs>
61 <param format="sam,bam" type="data" name="inputFile" label="Select SAM/BAM dataset or dataset collection" help="If empty, upload or import a SAM/BAM dataset" /> 71 <param format="sam,bam" type="data" name="inputFile" label="Select SAM/BAM dataset or dataset collection" help="If empty, upload or import a SAM/BAM dataset" />
62 <conditional name="reference_source"> 72 <conditional name="reference_source">
63 <param name="reference_source_selector" type="select" label="Load reference genome from"> 73 <param name="reference_source_selector" type="select" label="Load reference genome from">
64 <option value="cached">Local cache</option> 74 <option value="cached">Local cache</option>
65 <option value="history">History</option> 75 <option value="history">History</option>
66 </param> 76 </param>
67 <when value="cached"> 77 <when value="cached">
68 <param name="ref_file" type="select" label="Using reference genome" help="REFERENCE_SEQUENCE"> 78 <param name="ref_file" type="select" label="Using reference genome" help="REFERENCE_SEQUENCE">
69 <options from_data_table="all_fasta"></options> 79 <options from_data_table="all_fasta"></options>
70 <validator type="no_options" message="A built-in reference genome is not available for the build associated with the selected input file"/> 80 <validator type="no_options" message="A built-in reference genome is not available for the build associated with the selected input file"/>
71 </param> 81 </param>
72 </when> 82 </when>
73 <when value="history"> 83 <when value="history">
74 <param name="ref_file" type="data" format="fasta" label="Use the folloing dataset as the reference sequence" help="REFERENCE_SEQUENCE; You can upload a FASTA sequence to the history and use it as reference" /> 84 <param name="ref_file" type="data" format="fasta" label="Use the folloing dataset as the reference sequence" help="REFERENCE_SEQUENCE; You can upload a FASTA sequence to the history and use it as reference" />
75 </when> 85 </when>
76 </conditional> 86 </conditional>
77 <param format="tabular" name="refFlat" type="data" label="Gene annotations in refFlat form" help="See &quot;Obtaining gene annotations in refFlat format&quot; below for help" /> 87
88 <conditional name="gene_reference_source">
89 <param name="gene_reference_source_selector" type="select" label="Load gene annotation from">
90 <option value="gtf">GTF/GFF3</option>
91 <option value="refflat">refFlat</option>
92 </param>
93 <when value="gtf">
94 <param name="refFlat"
95 format="gtf,gff3"
96 type="data"
97 label="Gene annotation (GTF/GFF3)"/>
98 </when>
99 <when value="refflat">
100 <param name="refFlat"
101 format="tabular"
102 type="data"
103 label="Gene annotations in refFlat form"
104 help="See &quot;Obtaining gene annotations in refFlat format&quot; below for help"/>
105 </when>
106 </conditional>
107
108
78 <param name="ribosomal_intervals" format="picard_interval_list" type="data" optional="True" label="Location of rRNA sequences in genome, in interval_list format" help="RIBOSOMAL_INTERVALS; If not specified no bases will be identified as being ribosomal. The list of intervals can be geberated from BED or Interval datasets using Galaxy BedToIntervalList tool"/> 109 <param name="ribosomal_intervals" format="picard_interval_list" type="data" optional="True" label="Location of rRNA sequences in genome, in interval_list format" help="RIBOSOMAL_INTERVALS; If not specified no bases will be identified as being ribosomal. The list of intervals can be geberated from BED or Interval datasets using Galaxy BedToIntervalList tool"/>
79 <param name="strand_specificity" type="select" label="What is the RNA-seq library strand specificity" help="STRAND_SPECIFICITY; For unpaired reads, use FIRST_READ_TRANSCRIPTION_STRAND if the reads are expected to be on the transcription strand."> 110 <param name="strand_specificity" type="select" label="What is the RNA-seq library strand specificity" help="STRAND_SPECIFICITY; For unpaired reads, use FIRST_READ_TRANSCRIPTION_STRAND if the reads are expected to be on the transcription strand.">
80 <option value="NONE" selected="True">None</option> 111 <option value="NONE" selected="True">None</option>
81 <option value="FIRST_READ_TRANSCRIPTION_STRAND">First read transcription strand</option> 112 <option value="FIRST_READ_TRANSCRIPTION_STRAND">First read transcription strand</option>
82 <option value="SECOND_READ_TRANSCRIPTION_STRAND">Second read transcription strand</option> 113 <option value="SECOND_READ_TRANSCRIPTION_STRAND">Second read transcription strand</option>
106 <test> 137 <test>
107 <param name="reference_source_selector" value="history"/> 138 <param name="reference_source_selector" value="history"/>
108 <param name="ref_file" value="picard_CollectRnaSeqMetrics_ref.fa" ftype="fasta"/> 139 <param name="ref_file" value="picard_CollectRnaSeqMetrics_ref.fa" ftype="fasta"/>
109 <param name="inputFile" value="picard_CollectRnaSeqMetrics.bam" ftype="bam"/> 140 <param name="inputFile" value="picard_CollectRnaSeqMetrics.bam" ftype="bam"/>
110 <param name="assume_sorted" value="true" /> 141 <param name="assume_sorted" value="true" />
142
143 <param name="gene_reference_source_selector" value="refflat" />
111 <param name="refFlat" value="picard_CollectRnaSeqMetrics.refFlat" /> 144 <param name="refFlat" value="picard_CollectRnaSeqMetrics.refFlat" />
112 <param name="metric_accumulation_level" value="ALL_READS" /> 145 <param name="metric_accumulation_level" value="ALL_READS" />
113 <param name="minimum_length" value="500" /> 146 <param name="minimum_length" value="500" />
114 <param name="strand_specificity" value="NONE" /> 147 <param name="strand_specificity" value="NONE" />
115 <param name="rrna_fragment_percentage" value="0.8" /> 148 <param name="rrna_fragment_percentage" value="0.8" />
116 <output name="outFile" file="picard_CollectRnaSeqMetrics_test1.tab" ftype="tabular" lines_diff="4"/> 149 <output name="outFile" file="picard_CollectRnaSeqMetrics_test1.tab" ftype="tabular" lines_diff="4"/>
117 </test> 150 </test>
118 151
152 <test>
153 <param name="reference_source_selector" value="history"/>
154 <param name="ref_file" value="picard_CollectRnaSeqMetrics_ref.fa" ftype="fasta"/>
155 <param name="inputFile" value="picard_CollectRnaSeqMetrics.bam" ftype="bam"/>
156 <param name="assume_sorted" value="true" />
157
158 <param name="gene_reference_source_selector" value="gtf" />
159 <param name="refFlat" value="picard_CollectRnaSeqMetrics.gtf" ftype="gtf" />
160 <param name="metric_accumulation_level" value="ALL_READS" />
161 <param name="minimum_length" value="500" />
162 <param name="strand_specificity" value="NONE" />
163 <param name="rrna_fragment_percentage" value="0.8" />
164 <output name="outFile" file="picard_CollectRnaSeqMetrics_test2.tab" ftype="tabular" lines_diff="4"/>
165 </test>
166
167 <test>
168 <param name="reference_source_selector" value="history"/>
169 <param name="ref_file" value="picard_CollectRnaSeqMetrics_ref.fa" ftype="fasta"/>
170 <param name="inputFile" value="picard_CollectRnaSeqMetrics.bam" ftype="bam"/>
171 <param name="assume_sorted" value="true" />
172
173 <param name="gene_reference_source_selector" value="gtf" />
174 <param name="refFlat" value="picard_CollectRnaSeqMetrics.gff3" ftype="gff3" />
175 <param name="metric_accumulation_level" value="ALL_READS" />
176 <param name="minimum_length" value="500" />
177 <param name="strand_specificity" value="NONE" />
178 <param name="rrna_fragment_percentage" value="0.8" />
179 <output name="outFile" file="picard_CollectRnaSeqMetrics_test3.tab" ftype="tabular" lines_diff="4"/>
180 </test>
119 </tests> 181 </tests>
120 <help> 182 <help>
121 183
122 .. class:: infomark 184 .. class:: infomark
123 185