Mercurial > repos > iuc > limma_voom

comparison limma_voom.xml @ 14:94f82c79fa66 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/limma_voom commit c915bd7e68cb3a2944397aaf184c2b1db97cb3a5
author iuc
date Fri, 04 Jan 2019 04:11:21 -0500
parents a984bbe87e2a
children 107c169a0b31
comparison
equal deleted inserted replaced
13:a984bbe87e2a 14:94f82c79fa66
1 <tool id="limma_voom" name="limma" version="3.34.9.9"> 1 <tool id="limma_voom" name="limma" version="3.34.9.10">
2 <description> 2 <description>
3 Perform differential expression with limma-voom or limma-trend 3 Perform differential expression with limma-voom or limma-trend
4 </description> 4 </description>
5 5
6 <requirements> 6 <requirements>
118 118
119 && 119 &&
120 mkdir ./output_dir 120 mkdir ./output_dir
121 121
122 && 122 &&
123 #if $anno.annoOpt=='yes':
124 cp -r ./glimma* '$outReport.files_path' &&
125 #end if
126
127 cp '$outReport.files_path'/*tsv output_dir/ 123 cp '$outReport.files_path'/*tsv output_dir/
124
125 #if 'i' in str($out.plots).split( "," ):
126 && cp -r ./glimma* '$outReport.files_path'
127 #end if
128 128
129 #if $out.filtCounts or $out.normCounts: 129 #if $out.filtCounts or $out.normCounts:
130 && cp '$outReport.files_path'/*counts output_dir/ 130 && cp '$outReport.files_path'/*counts output_dir/
131 #end if 131 #end if
132 132
210 </conditional> 210 </conditional>
211 211
212 <!-- Gene Annotations --> 212 <!-- Gene Annotations -->
213 <conditional name="anno"> 213 <conditional name="anno">
214 <param name="annoOpt" type="select" label="Use Gene Annotations?" 214 <param name="annoOpt" type="select" label="Use Gene Annotations?"
215 help="If you provide an annotation file, annotations will be added to the table(s) of differential expression results to provide descriptions for each gene, and used to label the top genes in the Volcano plot. An interactive Glimma MD plot and table will also be generated. See Help section below."> 215 help="If you provide an annotation file, annotations will be added to the table(s) of differential expression results to provide descriptions for each gene, and used to label the top genes in the Volcano plot. Interactive Glimma Volcano and MD plots will also be generated. See Help section below.">
216 <option value="no">No</option> 216 <option value="no">No</option>
217 <option value="yes">Yes</option> 217 <option value="yes">Yes</option>
218 </param> 218 </param>
219 <when value="yes"> 219 <when value="yes">
220 <param name="geneanno" type="data" format="tabular" label="Gene Annotations"/> 220 <param name="geneanno" type="data" format="tabular" label="Gene Annotations"/>
270 </conditional> 270 </conditional>
271 </section> 271 </section>
272 272
273 <!-- Output Options --> 273 <!-- Output Options -->
274 <section name="out" expanded="false" title="Output Options"> 274 <section name="out" expanded="false" title="Output Options">
275 <param name="plots" type="select" display="checkboxes" multiple="True" optional="True" label="Additional Plots" help="Select additional plots to output in the report and as PDFs"> 275 <param name="plots" type="select" display="checkboxes" multiple="True" optional="True" label="Additional Plots" help="Select additional plots to output in the report">
276 <option value="i" selected="True">Glimma Interactive Plots</option>
276 <option value="d">Density Plots (if filtering)</option> 277 <option value="d">Density Plots (if filtering)</option>
277 <option value="c">CpmsVsCounts Plots (if filtering on cpms)</option> 278 <option value="c">CpmsVsCounts Plots (if filtering on cpms)</option>
278 <option value="b">Box Plots (if normalising)</option> 279 <option value="b">Box Plots (if normalising)</option>
279 <option value="x">MDS Extra (Dims 2vs3 and 3vs4)</option> 280 <option value="x">MDS Extra (Dims 2vs3 and 3vs4)</option>
280 <option value="m">MD Plots for individual samples</option> 281 <option value="m">MD Plots for individual samples</option>
382 </element> 383 </element>
383 </output_collection> 384 </output_collection>
384 <output name="outReport" > 385 <output name="outReport" >
385 <assert_contents> 386 <assert_contents>
386 <has_text text="Limma Analysis Output" /> 387 <has_text text="Limma Analysis Output" />
388 <has_text text="Glimma Interactive Results" />
387 <not_has_text text="RData" /> 389 <not_has_text text="RData" />
388 </assert_contents> 390 </assert_contents>
389 </output> 391 </output>
390 </test> 392 </test>
391 <!-- Ensure annotation file input works --> 393 <!-- Ensure annotation file input works -->
462 <has_text_matching expression="11304.*0.4590" /> 464 <has_text_matching expression="11304.*0.4590" />
463 </assert_contents> 465 </assert_contents>
464 </element> 466 </element>
465 </output_collection> 467 </output_collection>
466 </test> 468 </test>
467 <!-- Ensure factors file input works --> 469 <!-- Ensure factors file with unordered samples works -->
468 <test> 470 <test>
469 <param name="format" value="matrix" /> 471 <param name="format" value="matrix" />
470 <param name="ffile" value="yes" /> 472 <param name="ffile" value="yes" />
471 <param name="finfo" value="factorinfo.txt" /> 473 <param name="finfo" value="factorinfo.txt" />
472 <param name="counts" value="matrix.txt" /> 474 <param name="counts" value="matrix.txt" />
651 <help><![CDATA[ 653 <help><![CDATA[
652 .. class:: infomark 654 .. class:: infomark
653 655
654 **What it does** 656 **What it does**
655 657
656 Given a matrix of counts (e.g. from featureCounts) and optional information about the genes, performs differential expression (DE) using the limma_ Bioconductor package and produces plots and tables useful in DE analysis. If an annotation file is provided, interactive Glimma_ plots and a table of differentially expressed genes will also be generated. See an example workflow here_. 658 Given a matrix of counts (e.g. from featureCounts) and optional information about the genes, this tool performs differential expression (DE) using the limma_ Bioconductor package and produces plots and tables useful in DE analysis. Interactive Glimma_ plots and tables can also be generated and links to the Glimma plots will be provided in the report. See an example workflow here_.
657 659
658 In the `limma approach`_ to RNA-seq, read counts are converted to log2-counts-per-million (logCPM) and the mean-variance relationship is modelled either with precision weights or with an empirical Bayes prior trend. The precision weights approach is called “voom” and the prior trend approach is called “limma-trend”. For more information, see the Help section below. 660 In the `limma approach`_ to RNA-seq, read counts are converted to log2-counts-per-million (logCPM) and the mean-variance relationship is modelled either with precision weights or with an empirical Bayes prior trend. The precision weights approach is called “voom” and the prior trend approach is called “limma-trend”. For more information, see the Help section below.
659 661
660 ----- 662 -----
661 663
697 ========== ======= ======= ======= ======== ======== ======== 699 ========== ======= ======= ======= ======== ======== ========
698 700
699 **Gene Annotations:** 701 **Gene Annotations:**
700 Optional input for gene annotations, this can contain more 702 Optional input for gene annotations, this can contain more
701 information about the genes than just an ID number. The annotations will 703 information about the genes than just an ID number. The annotations will
702 be available in the differential expression results table and the optional normalised counts table. They will also be used to generate interactive Glimma_ MD plots and table of differential expression, a link to the Glimma plots will be provided in the report. The input annotation file must contain a header row and have the gene IDs in the first column. The second column will be used to label the genes in the Volcano plot and interactive Glimma plots, additional columns will be available in the Glimma interactive table. The number of rows should match that of the counts files, add NA for any gene IDs with no annotation. The Galaxy tool **annotateMyIDs** can be used to obtain annotations for human, mouse, fly and zebrafish. 704 be available in the differential expression results table and the optional normalised counts table. They will also be used to generate interactive Glimma_ Volcano, MD plots and tables of differential expression. The input annotation file must contain a header row and have the gene IDs in the first column. The second column will be used to label the genes in the Volcano plot and interactive Glimma plots, additional columns will be available in the Glimma interactive table. The number of rows should match that of the counts files, add NA for any gene IDs with no annotation. The Galaxy tool **annotateMyIDs** can be used to obtain annotations for human, mouse, fly and zebrafish.
703 705
704 Example: 706 Example:
705 707
706 ========== ========== =================================================== 708 ========== ========== ===================================================
707 **GeneID** **Symbol** **GeneName** 709 **GeneID** **Symbol** **GeneName**
713 11304 Abca4 ATP-binding cassette, sub-family A (ABC1), member 4 715 11304 Abca4 ATP-binding cassette, sub-family A (ABC1), member 4
714 11305 Abca2 ATP-binding cassette, sub-family A (ABC1), member 2 716 11305 Abca2 ATP-binding cassette, sub-family A (ABC1), member 2
715 ========== ========== =================================================== 717 ========== ========== ===================================================
716 718
717 **Factor Information:** 719 **Factor Information:**
718 Enter factor names and groups in the tool form, or provide a tab-separated file that has the samples in the same order as listed in the columns of the counts matrix. The second column should contain the primary factor levels (e.g. WT, Mut) with optional additional columns for any secondary factors. 720 Enter factor names and groups in the tool form, or provide a tab-separated file that has the names of the samples in the first column and one header row. The sample names must be the same as the names in the columns of the count matrix. The second column should contain the primary factor levels (e.g. WT, Mut) with optional additional columns for any secondary factors.
719 721
720 Example: 722 Example:
721 723
722 ========== ============ ========= 724 ========== ============ =========
723 **Sample** **Genotype** **Batch** 725 **Sample** **Genotype** **Batch**
728 Mut1 Mut b1 730 Mut1 Mut b1
729 Mut2 Mut b2 731 Mut2 Mut b2
730 Mut3 Mut b3 732 Mut3 Mut b3
731 ========== ============ ========= 733 ========== ============ =========
732 734
733 *Factor Name:* The name of the experimental factor being investigated e.g. Genotype, Treatment. One factor must be entered and spaces must not be used. Optionally, additional factors can be included, these are variables that might influence your experiment e.g. Batch, Gender, Subject. If additional factors are entered, edgeR will fit an additive linear model. 735 *Factor Name:* The name of the experimental factor being investigated e.g. Genotype, Treatment. One factor must be entered and spaces must not be used. Optionally, additional factors can be included, these are variables that might influence your experiment e.g. Batch, Gender, Subject. If additional factors are entered, an additive linear model will be used.
734 736
735 *Groups:* The names of the groups for the factor. These must be entered in the same order as the samples (to which the groups correspond) are listed in the columns of the counts matrix. Spaces must not be used and if entered into the tool form above, the values should be separated by commas. 737 *Groups:* The names of the groups for the factor. These must be entered in the same order as the samples (to which the groups correspond) are listed in the columns of the counts matrix. Spaces must not be used and if entered into the tool form above, the values should be separated by commas.
736 738
737 739
738 **Contrasts of Interest:** 740 **Contrasts of Interest:**
833 835
834 This tool outputs 836 This tool outputs
835 837
836 * a table of differentially expressed genes for each contrast of interest 838 * a table of differentially expressed genes for each contrast of interest
837 * a HTML report with plots and additional information 839 * a HTML report with plots and additional information
838 * an interactive Glimma MD plot and table (if annotation file provided)
839 840
840 Optionally, under **Output Options** you can choose to output 841 Optionally, under **Output Options** you can choose to output
841 842
843 * interactive Glimma plots and tables: MDS plot, and (if annotation file is input) Volcano plot and MD plot (default: Yes)
844 * additional plots in the report and as PDFs
842 * a normalised counts table 845 * a normalised counts table
843 * a library size information file 846 * a library size information file
844 * the R script used by this tool 847 * the R script used by this tool
845 * an RData file 848 * an RData file
846 849
897 900
898 Please report problems or suggestions to: su.s@wehi.edu.au 901 Please report problems or suggestions to: su.s@wehi.edu.au
899 902
900 .. _limma: http://www.bioconductor.org/packages/release/bioc/html/limma.html 903 .. _limma: http://www.bioconductor.org/packages/release/bioc/html/limma.html
901 .. _Glimma: https://bioconductor.org/packages/release/bioc/html/Glimma.html 904 .. _Glimma: https://bioconductor.org/packages/release/bioc/html/Glimma.html
902 .. _here: https://f1000research.com/articles/5-1408/v2 905 .. _here: https://f1000research.com/articles/5-1408/v3
903 .. _limma approach: https://www.ncbi.nlm.nih.gov/pubmed/25605792 906 .. _limma approach: https://www.ncbi.nlm.nih.gov/pubmed/25605792
904 .. _limma User's Guide: http://bioconductor.org/packages/release/bioc/vignettes/limma/inst/doc/usersguide.pdf 907 .. _limma User's Guide: http://bioconductor.org/packages/release/bioc/vignettes/limma/inst/doc/usersguide.pdf
905 .. _edgeR: http://www.bioconductor.org/packages/release/bioc/html/edgeR.html 908 .. _edgeR: http://www.bioconductor.org/packages/release/bioc/html/edgeR.html
906 .. _edgeR User's Guide: https://bioconductor.org/packages/release/bioc/vignettes/edgeR/inst/doc/edgeRUsersGuide.pdf 909 .. _edgeR User's Guide: https://bioconductor.org/packages/release/bioc/vignettes/edgeR/inst/doc/edgeRUsersGuide.pdf
907 .. _McCarthy and Smyth, 2009: https://www.ncbi.nlm.nih.gov/pubmed/19176553 910 .. _McCarthy and Smyth, 2009: https://www.ncbi.nlm.nih.gov/pubmed/19176553