Mercurial > repos > eschen42 > w4mclassfilter
diff w4mclassfilter.xml @ 5:2cdf7d5982c8 draft
planemo upload for repository https://github.com/HegemanLab/w4mclassfilter_galaxy_wrapper/tree/master commit a2d17eac4a1343a34cf2908d9ab31b3202a21f64
| author | eschen42 |
|---|---|
| date | Thu, 07 Sep 2017 17:41:09 -0400 |
| parents | 499c7ecfa834 |
| children | 38ccf6722d54 |
line wrap: on
line diff
--- a/w4mclassfilter.xml Mon Jun 19 23:42:33 2017 -0400 +++ b/w4mclassfilter.xml Thu Sep 07 17:41:09 2017 -0400 @@ -1,10 +1,10 @@ -<tool id="w4mclassfilter" name="Sample_Subset" version="0.98.2"> +<tool id="w4mclassfilter" name="Sample_Subset" version="0.98.3"> <description>Filter W4M data by sample class</description> <requirements> - <requirement type="package" version="3.3.1">r-base</requirement> + <requirement type="package" version="3.3.2">r-base</requirement> <requirement type="package" version="1.1_4">r-batch</requirement> - <requirement type="package" version="0.98.2">w4mclassfilter</requirement> + <requirement type="package" version="0.98.3">w4mclassfilter</requirement> </requirements> <stdio> @@ -34,7 +34,29 @@ <param name="samplenameColumn" label="Column that names the sample" type="text" value = "sampleMetadata" help="name of the column in the sample metadata file that has the name of the sample - defaults to 'sampleMetadata'" /> <param name="classnameColumn" label="Column that names the sample-class" type="text" value = "class" help="name of the column in sample metadata that has the values to be tested against the 'classes' input parameter - defaults to 'class'" /> <param name="sampleclassNames" label="Names of sample classes" type="text" value = "" help="comma-separated names (or comma-less regular expressions to match names) of sample-classes to filter in or out; defaults to no names"> - <sanitizer sanitize="False"/> + <sanitizer> + <valid initial="string.letters"> + <add preset="string.digits"/> + <add value="$" /> <!-- dollar, dollar-sign --> + <add value="(" /> <!-- left-paren --> + <add value=")" /> <!-- right-paren --> + <add value="*" /> <!-- splat, asterisk --> + <add value="+" /> <!-- plus --> + <add value="," /> <!-- comma --> + <add value="." /> <!-- dot, period --> + <add value=":" /> <!-- colon --> + <add value=";" /> <!-- semi, semicolon --> + <add value="?" /> <!-- what, question mark --> + <add value="[" /> <!-- l-squib, left-squre-bracket --> + <add value="\" /> <!-- whack, backslash --> + <add value="]" /> <!-- r-squib, right-squre-bracket --> + <add value="^" /> <!-- hat, caret --> + <add value="{" /> <!-- l-cube, left-curly-bracket --> + <add value="|" /> <!-- pipe --> + <add value="}" /> <!-- r-cube, right-curly-bracket --> + </valid> + </sanitizer> + </param> <param name="wildcards" label="Use wild-cards or regular-expressions" type="select" help="wild-cards (the default) - use '*' and '?' to match class names; regular-expressions - use comma-less regular expressions to match class names"> <option value="TRUE" selected="true">wild-cards</option> @@ -106,7 +128,42 @@ <param name="sampleMetadata_in" value="input_sampleMetadata.tsv"/> <param name="variableMetadata_in" value="input_variableMetadata.tsv"/> <param name="classnameColumn" value="gender"/> + <param name="sampleclassNames" value="*"/> + <param name="wildcards" value="TRUE"/> + <param name="samplenameColumn" value="sampleMetadata"/> + <param name="inclusive" value="filter-in"/> + <output name="sampleMetadata_out"> + <assert_contents> + <not_has_text text="HU_204" /> + <has_text text="HU_028" /> + <has_text text="HU_051" /> + <has_text text="HU_060" /> + <has_text text="HU_110" /> + <has_text text="HU_149" /> + <has_text text="HU_152" /> + <has_text text="HU_175" /> + <has_text text="HU_178" /> + <has_text text="HU_185" /> + <has_text text="HU_208" /> + <has_text text="HU_017" /> + <has_text text="HU_034" /> + <has_text text="HU_078" /> + <has_text text="HU_091" /> + <has_text text="HU_093" /> + <has_text text="HU_099" /> + <has_text text="HU_130" /> + <has_text text="HU_134" /> + <has_text text="HU_138" /> + </assert_contents> + </output> + </test> + <test> + <param name="dataMatrix_in" value="input_dataMatrix.tsv"/> + <param name="sampleMetadata_in" value="input_sampleMetadata.tsv"/> + <param name="variableMetadata_in" value="input_variableMetadata.tsv"/> + <param name="classnameColumn" value="gender"/> <param name="sampleclassNames" value="M"/> + <param name="wildcards" value="FALSE"/> <param name="samplenameColumn" value="sampleMetadata"/> <param name="inclusive" value="filter-in"/> <output name="sampleMetadata_out"> @@ -140,6 +197,7 @@ <param name="variableMetadata_in" value="input_variableMetadata.tsv"/> <param name="classnameColumn" value="gender"/> <param name="sampleclassNames" value="M"/> + <param name="wildcards" value="FALSE"/> <param name="samplenameColumn" value="sampleMetadata"/> <param name="inclusive" value="filter-in"/> <output name="variableMetadata_out"> @@ -169,6 +227,7 @@ <param name="variableMetadata_in" value="input_variableMetadata.tsv"/> <param name="classnameColumn" value="gender"/> <param name="sampleclassNames" value="M"/> + <param name="wildcards" value="FALSE"/> <param name="samplenameColumn" value="sampleMetadata"/> <param name="inclusive" value="filter-in"/> <output name="variableMetadata_out"> @@ -198,6 +257,7 @@ <param name="variableMetadata_in" value="input_variableMetadata.tsv"/> <param name="classnameColumn" value="gender"/> <param name="sampleclassNames" value="[Mm],[fF]"/> + <param name="wildcards" value="FALSE"/> <param name="samplenameColumn" value="sampleMetadata"/> <param name="inclusive" value="filter-in"/> <output name="sampleMetadata_out"> @@ -231,6 +291,7 @@ <param name="variableMetadata_in" value="input_variableMetadata.tsv"/> <param name="classnameColumn" value=""/> <param name="sampleclassNames" value="M"/> + <param name="wildcards" value="FALSE"/> <param name="samplenameColumn" value="sampleMetadata"/> <param name="inclusive" value="filter-in"/> <output name="sampleMetadata_out"> @@ -262,11 +323,10 @@ - <help> - <![CDATA[ + <help><![CDATA[ -**Author** Arthur Eschenlauer (University of Minnesota, esch0041@umn.edu) +**Author** Arthur Eschenlauer (University of Minnesota, esch0041@umn.edu) -------------------------------------------------------------------------- @@ -309,11 +369,11 @@ Data for a sample are collected as MS intensities, each of which is associated with a position on a 2D plane with dimensions of m/z ratio and chromatographic retention time. Ideally, features would be sufficiently reproducible from sample-run to sample-run to identify features that are commmon among samples and those that differ. However, the chromatographic retention time for a chemical can vary from one run to another. -In the Workflow4Metabolomics (W4M, [Giacomoni *et al.*, 2014]) "flavor" of Galaxy, the XCMS [Smith *et al.*, 2006] preprocessing tools provide for "retention time correction" to align features among samples, but features may be better aligned if pooled samples and blanks are included. +In the Workflow4Metabolomics (W4M, [Giacomoni *et al.*, 2014, Guitton *et al.* 2017]) "flavor" of Galaxy, the XCMS [Smith *et al.*, 2006] preprocessing tools provide for "retention time correction" to align features among samples, but features may be better aligned if pooled samples and blanks are included. Multivariate statistical techniques may be used to discover clusters of similar samples, and sometimes it is desirable to apply clustering iteratively to smaller and smaller subsets of samples until observable separation of clusters is no longer significant. Once feature-alignment has been achieved among samples in GC-MS and LC-MS datasets, however, the presence of pools and blanks may confound identification and separation of clusters. -Multivariate statistical algorithms also may be impacted by missing values or dimensions that have zero variance. +Multivariate statistical algorithms also may be impacted by missing values or dimensions that have zero variance (Thévenot *et al.*, 2015). The w4mclassfilter tool provides a way to choose subsets of samples for further analysis. The tool takes as input the data matrix, sample metadata, and variable metadata Galaxy datasets produced by W4M and produces the same trio of datasets with data only for the selected samples. @@ -400,7 +460,7 @@ Wild card patterns to match class-names --------------------------------------- -Beginning with v0.98.2, w4mclassfilter supports use of R regular expression patterns to select class-names. +Beginning with v0.98.2, w4mclassfilter supports use of R "wild card" patterns to select class-names. - use '``?``' to match a single character - use '``*``' to match zero or more characters @@ -416,7 +476,7 @@ Regular expression patterns to match class-names ------------------------------------------------ -Beginning with v0.98.2, w4mclassfilter supports use of R regular expression patterns to select class-names. +Beginning with v0.98.2, w4mclassfilter supports use of R "regular expression" patterns to select class-names. R uses POSIX 1003.2 standard regular expressions, which allow precise pattern-matching and are exhaustively defined at: http://pubs.opengroup.org/onlinepubs/9699919799/basedefs/V1_chap09.html @@ -508,6 +568,15 @@ NEWS ---- +CHANGES IN VERSION 0.98.3 +========================= + +INTERNAL MODIFICATIONS + +* Improved input handling. +* Now uses w4mclassfilter R package v0.98.3, although that version has no functional implications for this tool. +* Improved reference-list. + CHANGES IN VERSION 0.98.2 ========================= @@ -536,11 +605,16 @@ none - ]]> - </help> + ]]></help> <citations> + <!-- Giacomoni_2014 W4M 2.5 --> + <citation type="doi">10.1093/bioinformatics/btu813</citation> + <!-- Guitton_2017 W4M 3.0 --> + <citation type="doi">10.1016/j.biocel.2017.07.002</citation> + <!-- Smith_2006 XCMS --> <citation type="doi">10.1021/ac051437y</citation> - <citation type="doi">10.1093/bioinformatics/btu813</citation> + <!-- Th_venot_2015 Urinary metabolome statistics --> + <citation type="doi">10.1021/acs.jproteome.5b00354</citation> </citations> <!-- vim:noet:sw=4:ts=4