Mercurial > repos > malex > secimtools
diff principal_component_analysis.xml @ 1:2e7d47c0b027 draft
"planemo upload for repository https://malex@toolshed.g2.bx.psu.edu/repos/malex/secimtools"
author | malex |
---|---|
date | Mon, 08 Mar 2021 22:04:06 +0000 |
parents | |
children |
line wrap: on
line diff
--- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/principal_component_analysis.xml Mon Mar 08 22:04:06 2021 +0000 @@ -0,0 +1,95 @@ +<tool id="secimtools_principal_component_analysis" name="Principal Component Analysis (PCA)" version="@WRAPPER_VERSION@"> + <description>for visual summaries of the components.</description> + <macros> + <import>macros.xml</import> + </macros> + <expand macro="requirements" /> + <command detect_errors="exit_code"><![CDATA[ +principal_component_analysis.py +--input $input +--design $design +--ID $uniqID +--load_out $loadings +--score_out $scores +--summary_out $summary +--figure $figures + +#if $group + --group $group +#end if + ]]></command> + <inputs> + <param name="input" type="data" format="tabular" label="Wide Dataset" help="Input your tab-separated wide format dataset. If file is not tab separated see TIP below."/> + <param name="design" type="data" format="tabular" label="Design File" help="Input your design file (tab-separated). Note you need a 'sampleID' column. If not tab separated see TIP below."/> + <param name="uniqID" type="text" size="30" value="" label="Unique Feature ID" help="Name of the column in your wide dataset that has unique identifiers."/> + <param name="group" type="text" size="30" label="Group/Treatment [Optional]" help="Name of the column in your design file that contains group classifications."/> + </inputs> + <outputs> + <data format="tabular" name="loadings" label="${tool.name} on ${on_string}: loadings"/> + <data format="tabular" name="scores" label="${tool.name} on ${on_string}: scores"/> + <data format="tabular" name="summary" label="${tool.name} on ${on_string}: summary"/> + <data format="pdf" name="figures" label="${tool.name} on ${on_string}: scatter plots"/> + </outputs> + <tests> + <test> + <param name="input" value="ST000006_data.tsv"/> + <param name="design" value="ST000006_design.tsv"/> + <param name="uniqID" value="Retention_Index" /> + <param name="group" value="White_wine_type_and_source" /> + <output name="loadings" file="ST000006_principal_component_analysis_load_out.tsv" /> + <output name="scores" file="ST000006_principal_component_analysis_score_out.tsv" /> + <output name="summary" file="ST000006_principal_component_analysis_summary_out.tsv" /> + <output name="figures" file="ST000006_principal_component_analysis_figure.pdf" compare="sim_size" delta="10000" /> + </test> + </tests> + <help><![CDATA[ + +@TIP_AND_WARNING@ + +**Tool Description** + +The tool performs principal component analysis (PCA) of the data. +Visual summaries are provided in the from of 2D and 3D scatter plots for the first three principal components. +Samples in the scatter plots are colored based on the group classification. + +-------------------------------------------------------------------------------- + +**Note** + +- This tool currently treats all variables as continuous numeric variables. Running the tool on categorical variables might result in incorrect results. +- Rows containing non-numeric (or missing) data in any of the chosen columns will be skipped from the analysis. + +-------------------------------------------------------------------------------- + +**Input** + + - Two input datasets are required. + +@WIDE@ + +**NOTE:** The sample IDs must match the sample IDs in the Design File (below). +Extra columns will automatically be ignored. + + +@METADATA@ + +@UNIQID@ + +@GROUP_OPTIONAL@ + +-------------------------------------------------------------------------------- + +**Output** + +Four different outputs are produced by the Principal Component Analysis tool: + +(1) a TSV file containing eigenvectors/variable loadings +(2) a TSV file containing scores of input data on principal components +(3) a TSV file with the summary for each component +(4) and a PDF file of scatter plots of the first three principal components + +There are a total of four scatterplots: three pairwise plots for the first three components and a single 3D plot of the first three components. + + ]]></help> + <expand macro="citations"/> +</tool>