Mercurial > repos > eschen42 > w4mclassfilter
diff w4mclassfilter.xml @ 6:38ccf6722d54 draft
planemo upload for repository https://github.com/HegemanLab/w4mclassfilter_galaxy_wrapper/tree/master commit a06ae79d25b31d02217b934b9cd61a5aba3f640f
| author | eschen42 |
|---|---|
| date | Mon, 15 Jan 2018 14:06:39 -0500 |
| parents | 2cdf7d5982c8 |
| children | 582a8a42a93b |
line wrap: on
line diff
--- a/w4mclassfilter.xml Thu Sep 07 17:41:09 2017 -0400 +++ b/w4mclassfilter.xml Mon Jan 15 14:06:39 2018 -0500 @@ -1,10 +1,11 @@ -<tool id="w4mclassfilter" name="Sample_Subset" version="0.98.3"> +<tool id="w4mclassfilter" name="Sample_Subset" version="0.98.6"> <description>Filter W4M data by sample class</description> <requirements> - <requirement type="package" version="3.3.2">r-base</requirement> + <!-- <requirement type="package" version="6.2">readline</requirement> --> + <requirement type="package" version="3.4.1">r-base</requirement> <requirement type="package" version="1.1_4">r-batch</requirement> - <requirement type="package" version="0.98.3">w4mclassfilter</requirement> + <requirement type="package" version="0.98.6">w4mclassfilter</requirement> </requirements> <stdio> @@ -22,6 +23,7 @@ wildcards '$wildcards' classnameColumn '$classnameColumn' samplenameColumn '$samplenameColumn' + variable_range_filter '$variableRangeFilter' dataMatrix_out '$dataMatrix_out' sampleMetadata_out '$sampleMetadata_out' variableMetadata_out '$variableMetadata_out' @@ -56,8 +58,8 @@ <add value="}" /> <!-- r-cube, right-curly-bracket --> </valid> </sanitizer> + </param> - </param> <param name="wildcards" label="Use wild-cards or regular-expressions" type="select" help="wild-cards (the default) - use '*' and '?' to match class names; regular-expressions - use comma-less regular expressions to match class names"> <option value="TRUE" selected="true">wild-cards</option> <option value="FALSE">regular-expressions</option> @@ -66,6 +68,18 @@ <option value="TRUE">filter-in</option> <option value="FALSE" selected="true">filter-out</option> </param> + + <param name="variableRangeFilter" label="Variable range-filters" type="text" value = "" help="comma-separated filters, each specified as 'variableMetadataColumnName:min:max'; default is no filters. (See help below.)"> + <sanitizer> + <valid initial="string.letters"> + <add preset="string.digits"/> + <add value="," /> <!-- comma --> + <add value=":" /> <!-- colon --> + <add value="." /> <!-- dot, period --> + </valid> + </sanitizer> + </param> + </inputs> <outputs> <data name="dataMatrix_out" label="${tool.name}_${dataMatrix_in.name}" format="tabular" ></data> @@ -78,6 +92,60 @@ <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="class"/> + <param name="sampleclassNames" value=""/> + <param name="wildcards" value="FALSE"/> + <param name="samplenameColumn" value="sampleMetadata"/> + <param name="inclusive" value="filter-out"/> + <param name="variableRangeFilter" value="FEATMAX:2e6:,mz:200:,rt::800"/> + <output name="sampleMetadata_out"> + <assert_contents> + <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" /> + <not_has_text text="HU_204" /> + <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> + <output name="variableMetadata_out"> + <assert_contents> + <has_text text="HMDB00191" /> + <has_text text="HMDB00208" /> + <not_has_text text="HMDB00251" /> + <not_has_text text="HMDB00299" /> + <not_has_text text="HMDB00512" /> + <not_has_text text="HMDB00518" /> + <not_has_text text="HMDB00715" /> + <not_has_text text="HMDB00822" /> + <has_text text="HMDB01032" /> + <has_text text="HMDB01101.1" /> + <not_has_text text="HMDB03193" /> + <not_has_text text="HMDB04824" /> + <not_has_text text="HMDB10348" /> + <has_text text="HMDB13189" /> + <not_has_text text="HMDB59717" /> + </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="samplenameColumn" value="sampleMetadata"/> @@ -436,6 +504,10 @@ | '``filter-out``' - exclude only the named sample classes | +Variable-range filters (default = no filters) + | comma-separated names of variable-range filters (see 'Variable-range filters' below) + | + ------------ @@ -512,28 +584,58 @@ - '``^[A-Z][A-Z]*[0-9][0-9]$``' - NO MATCH - the name does not end with the pattern '``[A-Z][0-9][0-9]$``', i.e., it ends with four digits, not two. - '``^[A-Z][0-9]*$``' - NO MATCH - the pattern specifies that second character and all those that follow, if present, must be digits. +---------------------- +Variable-range filters +---------------------- ---------------- -Working example ---------------- +An array of range-specification strings may be supplied in the `variableRangeFilter` +argument. If supplied, only features having numerical values in the specified column +of `variableMetadata` that fall within the specified ranges will be retained +in the output. Each range is a string of three colon-separated values (e.g., "mz:200:800") in the +following order: + +- the **name of a column of `variableMetadata`** which must have numerical data (e.g., "mz"); +- the **minimum allowed value** in that column for the feature to be retained (e.g., 200); +- the **maximum allowed value** (e.g., 800). + +Note for the range specification strings: + +- **If the "maximum" is less than the "minimum", then the range is exclusive** (e.g., "mz:800:200" means retain only features whose mz is NOT in the range 200-800) +- **If the name supplied in the first field is 'FEATMAX',** then the string is defining the minimum (and possibly, though less useful, maximum) intensity for each feature in the dataMatrix. For example, "FEATMAX:1e6:" would specify that any feature would be excluded if no sample had an intensity for that feature greater than 1000000. + + - Note, however, that when the "maximum" is greater than the "minimum" for the FEATMAX range specification, then the specification is ignored. + +----------------------------------------------------------------------------- + +---------------- +WORKING EXAMPLES +---------------- .. class:: infomark -**Input files** +----------- +Input Files +----------- -+-------------------+--------------------------------------------------------------------------------------------------------------+ -| Input File | Download from URL | -+===================+==============================================================================================================+ -| Data matrix | https://raw.githubusercontent.com/HegemanLab/w4mclassfilter/master/tests/testthat/input_dataMatrix.tsv | -+-------------------+--------------------------------------------------------------------------------------------------------------+ -| Sample metadata | https://raw.githubusercontent.com/HegemanLab/w4mclassfilter/master/tests/testthat/input_sampleMetadata.tsv | -+-------------------+--------------------------------------------------------------------------------------------------------------+ -| Variable metadata | https://raw.githubusercontent.com/HegemanLab/w4mclassfilter/master/tests/testthat/input_variableMetadata.tsv | -+-------------------+--------------------------------------------------------------------------------------------------------------+ ++------------------------------------------------------------------------------------------------------------------------+ +| Input File URL | ++========================================================================================================================+ +| https://raw.githubusercontent.com/HegemanLab/w4mclassfilter_galaxy_wrapper/master/test-data/input_dataMatrix.tsv | ++------------------------------------------------------------------------------------------------------------------------+ +| https://raw.githubusercontent.com/HegemanLab/w4mclassfilter_galaxy_wrapper/master/test-data/input_sampleMetadata.tsv | ++------------------------------------------------------------------------------------------------------------------------+ +| https://raw.githubusercontent.com/HegemanLab/w4mclassfilter_galaxy_wrapper/master/test-data/input_variableMetadata.tsv | ++------------------------------------------------------------------------------------------------------------------------+ .. class:: infomark -**Other input parameters** +------------------------------- +Running Without Range-Filtering +------------------------------- + +This example retains only samples whose 'gender' attribute is 'M'. + +**Input parameters** +------------------------------------+-----------------+ | Input Parameter | Value | @@ -547,20 +649,54 @@ | Column that names the sample | sampleMetadata | +------------------------------------+-----------------+ +**Expected outputs** + ++-------------------+---------------------------------------------------------------------------------------------------------------------------+ +| Expected Output | Download from URL | ++===================+===========================================================================================================================+ +| Data matrix | https://raw.githubusercontent.com/HegemanLab/w4mclassfilter_galaxy_wrapper/master/test-data/expected_dataMatrix.tsv | ++-------------------+---------------------------------------------------------------------------------------------------------------------------+ +| Sample metadata | https://raw.githubusercontent.com/HegemanLab/w4mclassfilter_galaxy_wrapper/master/test-data/expected_sampleMetadata.tsv | ++-------------------+---------------------------------------------------------------------------------------------------------------------------+ +| Variable metadata | https://raw.githubusercontent.com/HegemanLab/w4mclassfilter_galaxy_wrapper/master/test-data/expected_variableMetadata.tsv | ++-------------------+---------------------------------------------------------------------------------------------------------------------------+ + .. class:: infomark +---------------------------- +Running With Range-Filtering +---------------------------- + +This example retains only features whose mz is greater than 200, whose rt is less than 800, and whose maximum intensity across all samples is 2,000,000. +This example retains all samples (except those having zero variance for all feature), although it would be possible to filter on samples as well. + +**Input parameters** + ++------------------------------------+-------------------------------+ +| Input Parameter | Value | ++====================================+===============================+ +| Names of sample classes | (Leave this field empty.) | ++------------------------------------+-------------------------------+ +| Include named classes | filter-out | ++------------------------------------+-------------------------------+ +| Column that names the sample-class | class | ++------------------------------------+-------------------------------+ +| Column that names the sample | sampleMetadata | ++------------------------------------+-------------------------------+ +| Variable range-filters | FEATMAX:2e6:,mz:200:,rt::800 | ++------------------------------------+-------------------------------+ + **Expected outputs** -+-------------------+-----------------------------------------------------------------------------------------------------------------+ -| Expected Output | Download from URL | -+===================+=================================================================================================================+ -| Data matrix | https://raw.githubusercontent.com/HegemanLab/w4mclassfilter/master/tests/testthat/expected_dataMatrix.tsv | -+-------------------+-----------------------------------------------------------------------------------------------------------------+ -| Sample metadata | https://raw.githubusercontent.com/HegemanLab/w4mclassfilter/master/tests/testthat/expected_sampleMetadata.tsv | -+-------------------+-----------------------------------------------------------------------------------------------------------------+ -| Variable metadata | https://raw.githubusercontent.com/HegemanLab/w4mclassfilter/master/tests/testthat/expected_variableMetadata.tsv | -+-------------------+-----------------------------------------------------------------------------------------------------------------+ - ++-------------------+------------------------------------------------------------------------------------------------------------------------------+ +| Expected Output | Download from URL | ++===================+==============================================================================================================================+ +| Data matrix | https://raw.githubusercontent.com/HegemanLab/w4mclassfilter_galaxy_wrapper/master/test-data/rangefilter_dataMatrix.tsv | ++-------------------+------------------------------------------------------------------------------------------------------------------------------+ +| Sample metadata | https://raw.githubusercontent.com/HegemanLab/w4mclassfilter_galaxy_wrapper/master/test-data/rangefilter_sampleMetadata.tsv | ++-------------------+------------------------------------------------------------------------------------------------------------------------------+ +| Variable metadata | https://raw.githubusercontent.com/HegemanLab/w4mclassfilter_galaxy_wrapper/master/test-data/rangefilter_variableMetadata.tsv | ++-------------------+------------------------------------------------------------------------------------------------------------------------------+ ----------------------------------------------------------------------------- @@ -568,42 +704,54 @@ NEWS ---- -CHANGES IN VERSION 0.98.3 +Changes in version 0.98.6 ========================= -INTERNAL MODIFICATIONS +New features + +* Added support for filtering out features whose attributes fall outside specified ranges. + For more detail, see "Variable-range filters" above. + +Internal modifications + +* Now uses w4mclassfilter R package v0.98.6. +* Now sorts sample names and feature names in output files because some statistical tools expect the same order in `dataMatrix` row and column names as in the corresponding metadata files. + +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 +Changes in version 0.98.2 ========================= -NEW FEATURES +New features * Added support for R-flavored regular expression pattern-matching when selecting names of sample-classes. * Empty classes argument or zero-length class_column result in no samples filtered out. -INTERNAL MODIFICATIONS +Internal modifications * Support and tests for new features. - -CHANGES IN VERSION 0.98.1 +Changes in version 0.98.1 ========================= -NEW FEATURES - First release - Wrap the w4mclassfilter R package that implements filtering of W4M data matrix, variable metadata, and sample metadata by class of sample. -*dataMatrix* *is* modified by the tool, so it *does* appear as an output file -*sampleMetadata* *is* modified by the tool, so it *does* appear as an output file -*variableMetadata* *is* modified by the tool, so it *does* appear as an output file +New features -INTERNAL MODIFICATIONS +* *dataMatrix* *is* modified by the tool, so it *does* appear as an output file +* *sampleMetadata* *is* modified by the tool, so it *does* appear as an output file +* *variableMetadata* *is* modified by the tool, so it *does* appear as an output file -none +Internal modifications + +* N/A ]]></help> <citations>