Mercurial > repos > iuc > featurecounts

comparison featurecounts.xml @ 13:c7085a3028ef 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-iuc/tree/master/tools/featurecounts commit 2bd06c2b43c295fb4cf172c4f156fed5475855a4
author iuc
date Sat, 19 May 2018 03:53:39 -0400
parents e270d0978616
children 786a00071b49
comparison
equal deleted inserted replaced
12:e270d0978616 13:c7085a3028ef
1 <tool id="featurecounts" name="featureCounts" version="1.6.0.4" profile="16.04"> 1 <tool id="featurecounts" name="featureCounts" version="1.6.0.5" profile="16.04">
2 <description>Measure gene expression in RNA-Seq experiments from SAM or BAM files.</description> 2 <description>Measure gene expression in RNA-Seq experiments from SAM or BAM files.</description>
3 <requirements> 3 <requirements>
4 <requirement type="package" version="1.6.0">subread</requirement> 4 <requirement type="package" version="1.6.0">subread</requirement>
5 </requirements> 5 </requirements>
6 6
79 $pe_parameters.only_both_ends 79 $pe_parameters.only_both_ends
80 $pe_parameters.exclude_chimerics 80 $pe_parameters.exclude_chimerics
81 81
82 '${alignment}' 82 '${alignment}'
83 83
84 ## Removal of comment 84 ## Remove comment and add sample name to header
85 && grep -v "^#" "output" 85 && grep -v "^#" "output"
86 86 | sed -e 's|${alignment}|${alignment.element_identifier}|g'
87 #if $format.value != "tabdel_short":
88 ## and remove column-header line
89 | tail -n+2
90 #else
91 ## update header
92 | sed --expression='s|${alignment}|${alignment.element_identifier}|g'
93 #end if
94 > body.txt 87 > body.txt
95 ## Set the right columns for the tabular formats 88 ## Set the right columns for the tabular formats
96 #if $format.value == "tabdel_medium": 89 #if $format.value == "tabdel_medium":
97 && cut -f 1,7 body.txt > expression_matrix.txt 90 && cut -f 1,7 body.txt > expression_matrix.txt
98 91
99 ## Paste doesn't allow a non ordered list of columns: -f 1,7,8,6 will only return columns 1,7 and 8 92 ## Paste doesn't allow a non ordered list of columns: -f 1,7,8,6 will only return columns 1,7 and 8
100 ## Thus the gene length column (last column) has to be added separately 93 ## Thus the gene length column (last column) has to be added separately
101 && cut -f 6 body.txt > gene_lengths.txt 94 && cut -f 6 body.txt > gene_lengths.txt
102 && paste expression_matrix.txt gene_lengths.txt > expression_matrix.txt.bak 95 && paste expression_matrix.txt gene_lengths.txt > expression_matrix.txt.bak
103 && mv -f expression_matrix.txt.bak '${output_medium}' 96 && mv -f expression_matrix.txt.bak '${output_medium}'
104 #elif $format.value == "tabdel_short" or $format.value == "tabdel_short_noheader": 97 #elif $format.value == "tabdel_short":
105 && cut -f 1,7 body.txt > '${output_short}' 98 && cut -f 1,7 body.txt > '${output_short}'
106 #else: 99 #else:
107 && cp body.txt '${output_full}' 100 && cp body.txt '${output_full}'
108 #end if 101 #end if
109 102
110 #if str($include_feature_length_file) == "true": 103 #if str($include_feature_length_file) == "true":
111 && cut -f 1,6 body.txt > '${output_feature_lengths}' 104 && cut -f 1,6 body.txt > '${output_feature_lengths}'
112 #end if 105 #end if
113 106
114 #if str($extended_parameters.exon_exon_junction_read_counting_enabled.count_exon_exon_junction_reads) == "-J": 107 #if str($extended_parameters.exon_exon_junction_read_counting_enabled.count_exon_exon_junction_reads) == "-J":
115 #if $format.value != "tabdel_short": 108 && sed -e 's|${alignment}|${alignment.element_identifier}|g' 'output.jcounts' > '${output_jcounts}'
116 && tail -n+2 'output.jcounts' > '${output_jcounts}'
117 #else:
118
119 && sed --expression='s|${alignment}|${alignment.element_identifier}|g' 'output.jcounts' > '${output_jcounts}'
120 #end if
121 #end if 109 #end if
122 110
123 #if $format.value != "tabdel_short": 111 && sed -e 's|${alignment}|${alignment.element_identifier}|g' 'output.summary' > '${output_summary}'
124 && tail -n+2 'output.summary' > '${output_summary}'
125 #else:
126 && sed --expression='s|${alignment}|${alignment.element_identifier}|g' 'output.summary' > '${output_summary}'
127 #end if
128 ]]></command> 112 ]]></command>
129 <inputs> 113 <inputs>
130 <param name="alignment" 114 <param name="alignment"
131 type="data" 115 type="data"
132 multiple="false" 116 multiple="false"
168 152
169 <param name="format" 153 <param name="format"
170 type="select" 154 type="select"
171 label="Output format" 155 label="Output format"
172 help="The output format will be tabular, select the preferred columns here"> 156 help="The output format will be tabular, select the preferred columns here">
173 <option value="tabdel_short_noheader" selected="true">Gene-ID "\t" read-count (DESeq2 IUC wrapper compatible)</option> 157 <option value="tabdel_short">Gene-ID "\t" read-count (MultiQC/DESeq2/edgeR/limma-voom compatible)</option>
174 <option value="tabdel_short">Gene-ID "\t" read-count (MultiQC/edgeR/limma-voom compatible, includes header in output)</option>
175 <option value="tabdel_medium">Gene-ID "\t" read-count "\t" gene-length</option> 158 <option value="tabdel_medium">Gene-ID "\t" read-count "\t" gene-length</option>
176 <option value="tabdel_full">featureCounts 1.4.0+ default (includes regions provided by the GTF file)</option> 159 <option value="tabdel_full">featureCounts 1.4.0+ default (includes regions provided by the GTF file)</option>
177 </param> 160 </param>
178 161
179 <param name="include_feature_length_file" 162 <param name="include_feature_length_file"
426 </data> 409 </data>
427 410
428 <data format="tabular" 411 <data format="tabular"
429 name="output_short" 412 name="output_short"
430 label="${tool.name} on ${on_string}"> 413 label="${tool.name} on ${on_string}">
431 <filter>format == "tabdel_short_noheader" or format == "tabdel_short"</filter> 414 <filter>format == "tabdel_short"</filter>
432 <actions> 415 <actions>
433 <action name="column_names" type="metadata" default="Geneid,${alignment.element_identifier}" /> 416 <action name="column_names" type="metadata" default="Geneid,${alignment.element_identifier}" />
434 </actions> 417 </actions>
435 </data> 418 </data>
436 419
468 default="PrimaryGene,SecondaryGene,Site1_chr,Site1_location,Site1_strand,Site2_chr,Site2_location,Site2_strand,${alignment.element_identifier}" /> 451 default="PrimaryGene,SecondaryGene,Site1_chr,Site1_location,Site1_strand,Site2_chr,Site2_location,Site2_strand,${alignment.element_identifier}" />
469 </actions> 452 </actions>
470 </data> 453 </data>
471 </outputs> 454 </outputs>
472 <tests> 455 <tests>
473 <test expect_num_outputs="4">
474 <param name="alignment" value="featureCounts_input1.bam" ftype="bam" dbkey="hg38" />
475 <param name="anno_select" value="history"/>
476 <param name="reference_gene_sets" value="featureCounts_guide.gff" ftype="gff" dbkey="hg38" />
477 <param name="format" value="tabdel_short_noheader" />
478 <param name="include_feature_length_file" value="true"/>
479 <param name="count_exon_exon_junction_reads" value="-J"/>
480 <output name="output_short" file="output_1_short.tab">
481 <metadata name="column_names" value="Geneid,featureCounts_input1.bam"/>
482 </output>
483 <output name="output_summary" file="output_1_summary.tab">
484 <metadata name="column_names" value="Status,featureCounts_input1.bam"/>
485 </output>
486 <output name="output_jcounts" file="output_1_jcounts.tab">
487 <metadata name="column_names" value="PrimaryGene,SecondaryGene,Site1_chr,Site1_location,Site1_strand,Site2_chr,Site2_location,Site2_strand,featureCounts_input1.bam"/>
488 </output>
489 </test>
490 <test expect_num_outputs="3"> 456 <test expect_num_outputs="3">
491 <param name="alignment" value="featureCounts_input1.bam" ftype="bam" dbkey="hg38" /> 457 <param name="alignment" value="featureCounts_input1.bam" ftype="bam" dbkey="hg38" />
492 <param name="anno_select" value="history"/> 458 <param name="anno_select" value="history"/>
493 <param name="reference_gene_sets" value="featureCounts_guide.gff" ftype="gff" dbkey="hg38" /> 459 <param name="reference_gene_sets" value="featureCounts_guide.gff" ftype="gff" dbkey="hg38" />
494 <param name="format" value="tabdel_medium" /> 460 <param name="format" value="tabdel_medium" />
521 <param name="anno_select" value="history"/> 487 <param name="anno_select" value="history"/>
522 <param name="reference_gene_sets" value="featureCounts_guide.gff" ftype="gff" dbkey="hg38" /> 488 <param name="reference_gene_sets" value="featureCounts_guide.gff" ftype="gff" dbkey="hg38" />
523 <param name="format" value="tabdel_short" /> 489 <param name="format" value="tabdel_short" />
524 <param name="include_feature_length_file" value="true"/> 490 <param name="include_feature_length_file" value="true"/>
525 <param name="count_exon_exon_junction_reads" value="-J"/> 491 <param name="count_exon_exon_junction_reads" value="-J"/>
526 <output name="output_short" file="output_1_short_with_header.tab"> 492 <output name="output_short" file="output_1_short.tab">
527 <metadata name="column_names" value="Geneid,featureCounts_input1.bam"/> 493 <metadata name="column_names" value="Geneid,featureCounts_input1.bam"/>
528 </output> 494 </output>
529 <output name="output_summary" file="output_1_summary_with_header.tab"> 495 <output name="output_summary" file="output_1_summary.tab">
530 <metadata name="column_names" value="Status,featureCounts_input1.bam"/> 496 <metadata name="column_names" value="Status,featureCounts_input1.bam"/>
531 </output> 497 </output>
532 <output name="output_jcounts" file="output_1_jcounts_with_header.tab"> 498 <output name="output_jcounts" file="output_1_jcounts.tab">
533 <metadata name="column_names" value="PrimaryGene,SecondaryGene,Site1_chr,Site1_location,Site1_strand,Site2_chr,Site2_location,Site2_strand,featureCounts_input1.bam"/> 499 <metadata name="column_names" value="PrimaryGene,SecondaryGene,Site1_chr,Site1_location,Site1_strand,Site2_chr,Site2_location,Site2_strand,featureCounts_input1.bam"/>
534 </output> 500 </output>
535 </test> 501 </test>
536 <!-- Ensure featureCounts built-in annotation works --> 502 <!-- Ensure featureCounts built-in annotation works -->
537 <test expect_num_outputs="2"> 503 <test expect_num_outputs="2">
580 546
581 Alternatively, the featureCounts built-in annotations for genomes hg38, hg19, mm10 and mm9 can be used through selecting the built-in option above. These annotations were downloaded from NCBI RefSeq database and then adapted by merging overlapping exons from the same gene to form a set of disjoint exons for each gene. Genes with the same Entrez gene identifiers were also merged into one gene. See the Subread_ User's Guide for more information. 547 Alternatively, the featureCounts built-in annotations for genomes hg38, hg19, mm10 and mm9 can be used through selecting the built-in option above. These annotations were downloaded from NCBI RefSeq database and then adapted by merging overlapping exons from the same gene to form a set of disjoint exons for each gene. Genes with the same Entrez gene identifiers were also merged into one gene. See the Subread_ User's Guide for more information.
582 548
583 Output format 549 Output format
584 ------------- 550 -------------
585 FeatureCounts produces a table containing counted reads, per gene, per row. Optionally the last column can be set to be the effective gene-length. These tables are compatible with the DESeq2 Galaxy wrapper by IUC. Column names are added as metadata object. 551 FeatureCounts produces a table containing counted reads, per gene, per row. Optionally the last column can be set to be the effective gene-length. These tables are compatible with the DESeq2, edgeR and limma-voom Galaxy wrappers by IUC.
586 552
587 .. _Subread: http://bioinf.wehi.edu.au/subread-package/SubreadUsersGuide.pdf 553 .. _Subread: http://bioinf.wehi.edu.au/subread-package/SubreadUsersGuide.pdf
588 ]]></help> 554 ]]></help>
589 <citations> 555 <citations>
590 <citation type="doi">10.1093/bioinformatics/btt656</citation> 556 <citation type="doi">10.1093/bioinformatics/btt656</citation>