<tool id="w4mclassfilter" name="Sample_Subset" version="0.98.2">
  <description>Filter W4M data by sample class</description>

  <requirements>
    <requirement type="package" version="3.3.1">r-base</requirement>
    <requirement type="package" version="1.1_4">r-batch</requirement>
    <requirement type="package" version="0.98.2">w4mclassfilter</requirement>
  </requirements>

  <stdio>
    <exit_code range="1:" level="fatal" />
  </stdio>


  <command detect_errors="aggressive"><![CDATA[
  Rscript $__tool_directory__/w4mclassfilter_wrapper.R
  dataMatrix_in '$dataMatrix_in'
  sampleMetadata_in '$sampleMetadata_in'
  variableMetadata_in '$variableMetadata_in'
  sampleclassNames '$sampleclassNames'
  inclusive '$inclusive'
  wildcards '$wildcards'
  classnameColumn '$classnameColumn'
  samplenameColumn '$samplenameColumn'
  dataMatrix_out '$dataMatrix_out'
  sampleMetadata_out '$sampleMetadata_out'
  variableMetadata_out '$variableMetadata_out'
  ]]></command>

  <inputs>
    <param name="dataMatrix_in" label="Data matrix file" type="data" format="tabular" help="variable x sample, decimal: '.', missing: NA, mode: numerical, separator: tab" />
    <param name="sampleMetadata_in" label="Sample metadata file" type="data" format="tabular" help="sample x metadata columns, separator: tab" />
    <param name="variableMetadata_in" label="Variable metadata file" type="data" format="tabular" help="variable x metadata columns, separator: tab" />
    <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"/>
    </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>
    </param>
    <param name="inclusive" label="Include named classes" type="select" help="filter-in - include only the named sample classes; filter-out (the default) - exclude only the named sample classes">
      <option value="TRUE">filter-in</option>
      <option value="FALSE" selected="true">filter-out</option>
    </param>
  </inputs>
  <outputs>
    <data name="dataMatrix_out" label="${tool.name}_${dataMatrix_in.name}" format="tabular" ></data>
    <data name="sampleMetadata_out" label="${tool.name}_${sampleMetadata_in.name}" format="tabular" ></data>
    <data name="variableMetadata_out" label="${tool.name}_${variableMetadata_in.name}" format="tabular" ></data>
  </outputs>

  <tests>
    <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"/>
      <param name="inclusive" value="filter-in"/>
      <output name="dataMatrix_out">
        <assert_contents>
          <not_has_text text="HU_028" />
          <not_has_text text="HU_051" />
          <not_has_text text="HU_060" />
          <not_has_text text="HU_110" />
          <not_has_text text="HU_149" />
          <not_has_text text="HU_152" />
          <not_has_text text="HU_175" />
          <not_has_text text="HU_178" />
          <not_has_text text="HU_185" />
          <not_has_text text="HU_204" />
          <not_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" />
          <has_text     text="HMDB03193" />
          <not_has_text text="HMDB00822" />
          <has_text     text="HMDB01101" />
          <has_text     text="HMDB01101.1" />
          <has_text     text="HMDB10348" />
          <has_text     text="HMDB59717" />
          <has_text     text="HMDB13189" />
          <has_text     text="HMDB00299" />
          <has_text     text="HMDB00191" />
          <has_text     text="HMDB00518" />
          <has_text     text="HMDB00715" />
          <has_text     text="HMDB01032" />
          <has_text     text="HMDB00208" />
          <has_text     text="HMDB04824" />
          <has_text     text="HMDB00512" />
          <has_text     text="HMDB00251" />
        </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"/>
      <param name="inclusive" value="filter-in"/>
      <output name="sampleMetadata_out">
        <assert_contents>
          <not_has_text text="HU_028" />
          <not_has_text text="HU_051" />
          <not_has_text text="HU_060" />
          <not_has_text text="HU_110" />
          <not_has_text text="HU_149" />
          <not_has_text text="HU_152" />
          <not_has_text text="HU_175" />
          <not_has_text text="HU_178" />
          <not_has_text text="HU_185" />
          <not_has_text text="HU_204" />
          <not_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="samplenameColumn" value="sampleMetadata"/>
      <param name="inclusive" value="filter-in"/>
      <output name="variableMetadata_out">
        <assert_contents>
          <has_text     text="HMDB03193" />
          <not_has_text text="HMDB00822" />
          <has_text     text="HMDB01101" />
          <has_text     text="HMDB01101.1" />
          <has_text     text="HMDB10348" />
          <has_text     text="HMDB59717" />
          <has_text     text="HMDB13189" />
          <has_text     text="HMDB00299" />
          <has_text     text="HMDB00191" />
          <has_text     text="HMDB00518" />
          <has_text     text="HMDB00715" />
          <has_text     text="HMDB01032" />
          <has_text     text="HMDB00208" />
          <has_text     text="HMDB04824" />
          <has_text     text="HMDB00512" />
          <has_text     text="HMDB00251" />
        </assert_contents>
      </output>
    </test>
    <test>
      <param name="dataMatrix_in" value="input_nofilter_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"/>
      <param name="inclusive" value="filter-in"/>
      <output name="variableMetadata_out">
        <assert_contents>
          <has_text     text="HMDB03193" />
          <not_has_text text="HMDB00822" />
          <has_text     text="HMDB01101" />
          <has_text     text="HMDB01101.1" />
          <has_text     text="HMDB10348" />
          <has_text     text="HMDB59717" />
          <not_has_text text="HMDB13189" />
          <has_text     text="HMDB00299" />
          <has_text     text="HMDB00191" />
          <has_text     text="HMDB00518" />
          <has_text     text="HMDB00715" />
          <has_text     text="HMDB01032" />
          <has_text     text="HMDB00208" />
          <has_text     text="HMDB04824" />
          <has_text     text="HMDB00512" />
          <has_text     text="HMDB00251" />
        </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="[Mm],[fF]"/>
      <param name="samplenameColumn" value="sampleMetadata"/>
      <param name="inclusive" value="filter-in"/>
      <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>
    </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=""/>
      <param name="sampleclassNames" value="M"/>
      <param name="samplenameColumn" value="sampleMetadata"/>
      <param name="inclusive" value="filter-in"/>
      <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>
    </test>
  </tests>



	<help>
		<![CDATA[


**Author**	Arthur Eschenlauer (University of Minnesota, esch0041@umn.edu)

--------------------------------------------------------------------------


**R package**

The *w4mclassfilter* package is available from the Hegeman lab github repository (https://github.com/HegemanLab/w4mclassfilter/releases).

-----------------------------------------------------------------------------------------------------------------------------------------


**Tool updates**

See the **NEWS** section at the bottom of this page

---------------------------------------------------

==============================================
Filter Workflow4Metabolomics data matrix files
==============================================

-----------
Description
-----------

Filter a set of retention-corrected W4M files (dataMatrix, sampleMetadata, variableMetadata) by sample-class

-----------------
Workflow Position
-----------------

- Upstream tool category: Preprocessing
- Downstream tool categories: Normalisation, Statistical Analysis, Quality Control, Filter and Sort

----------
Motivation
----------

GC-MS1 and LC-MS1 experiments seek to resolve chemicals as features that have distinct chromatographic behavior and (after ionization) mass-to-charge ratio.
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.

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.

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.
The tool uses a "sample-class" column in the sample metadata as the basis for including or eliminating samples for further analysis.
Class-values to be considered are provided by the user as a comma-separated list.
The user also provides an indication whether the list specifies classes to be included in further analysis ("filter-in") or rather to be excluded from it ("filter-out").
Next, missing and negative intensites for features of the remaining samples are imputed to zero.
Finally, samples or features with zero variance are eliminated.

-----------
Input files
-----------

+---------------------------+------------+
| File                      |   Format   |
+===========================+============+
|     Data matrix           |   tabular  |
+---------------------------+------------+
|     Sample metadata       |   tabular  |
+---------------------------+------------+
|     Variable metadata     |   tabular  |
+---------------------------+------------+


----------
Parameters
----------

Data matrix file
	| variable x sample **dataMatrix** (tabular separated values) file of the numeric data matrix, with . as decimal, and NA for missing values; the table must not contain metadata apart from row and column names; the row and column names must be identical to the rownames of the sample and variable metadata, respectively (see below)
	|

Sample metadata file
	| sample x metadata **sampleMetadata** (tabular separated values) file of the numeric and/or character sample metadata, with . as decimal and NA for missing values
	|

Variable metadata file
	| variable x metadata **variableMetadata** (tabular separated values) file of the numeric and/or character variable metadata, with . as decimal and NA for missing values
	|

Column that names the sample (default = '``sampleMetadata``')
	| name of the column in sample metadata that has the name of the sample
	|

Column that names the sample-class (default = '``class``')
	| name of the column in sample metadata that has the values to be tested against the '``classes``' input parameter
	|

Names of sample classes (default = no names)
	| comma-separated names of sample classes to include or exclude
	|

Wild-cards (default = '``wild-cards``')
	| '``wild-cards``' - use wild-cards to match names of sample classes (see 'Wild card patterns to match class-names' below)
	| '``regular-expressions``' - exclude only the named sample classes (see 'Regular expression patterns to match class-names' below)
	|

Include named classes (default = '``filter-out``')
	| '``filter-in``' - include only the named sample classes
	| '``filter-out``' - exclude only the named sample classes
	|



------------
Output files
------------


sampleMetadata
	| (tabular separated values) file identical to the **sampleMetadata** file given as an input argument, excepting lacking rows for samples (xC-MS features) that have been filtered out (by the sample-class filter or because of zero variance)
	|

variableMetadata
	| (tabular separated values) file identical to the **variableMetadata** file given as an input argument, excepting lacking rows for variables (xC-MS features) that have been filtered out (because of zero variance)
	|

dataMatrix
	| (tabular separated values) file identical to the **dataMatrix** file given as an input argument, excepting lacking rows for variables (xC-MS features) that have been filtered out (because of zero variance) and columns that have been filtered out (by the sample-class filter or because of zero variance)
	|


---------------------------------------
Wild card patterns to match class-names
---------------------------------------

Beginning with v0.98.2, w4mclassfilter supports use of R regular expression patterns to select class-names.

- use '``?``' to match a single character
- use '``*``' to match zero or more characters
- the entire pattern must match the sample name

For example

- '``??.samp*``' matches '``my.sample``' but not '``my.own.sample``'
- '``*.sample``' matches '``my.sample``' and '``my.own.sample``'
- '``*.sampl``' matches neither '``my.sample``' nor '``my.own.sample``'

------------------------------------------------
Regular expression patterns to match 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

However, only a few basic building blocks of regular expressions need to be mastered for most cases:

- '``^``' matches the beginning of a class-name
- '``$``' matches the end of a class-name
- '``.``' outside of square brackets matches a single character
- '``*``' matches character specified immediately before zero or more times
- square brackets specify a set of characters to be matched.

Within square brackets

- '``^``' as the first character specifies that the list of characters are those that should **not** be matched.
- '``-``' is used to specify ranges of characters

Caveat: The tool wrapper uses the comma ('``,``') to split a list of sample-class names, so **commas may not be used within regular expressions for this tool**

First Example: Consider a field of class-names consisting of '``marq3,marq6,marq9,marq12,front3,front6,front9,front12``'

- The regular expression '``^front[0-9][0-9]*$``' will match the same sample-classes as '``front3,front6,front9,front12``'
- The regular expression '``^[a-z][a-z]3$``' will match the same sample-classes as '``front3,marq3``'
- The regular expression '``^[a-z][a-z]12$``' will match the same sample-classes as '``front12,marq12``'
- The regular expression '``^[a-z][a-z][0-9]$``' will match the same sample-classes as '``front3,front6,front9,marq3,marq6,marq9``'

Second Example: Consider these regular expression patterns as possible matches to a sample-class name '``AB0123``':

- '``^[A-Z][A-Z][0-9][0-9]*$``' - MATCHES '``**^AB0123$**``'
- '``^[A-Z][A-Z]*[0-9][0-9]*$``' - MATCHES '``**^AB0123$**``'
- '``^[A-Z][0-9]*``' - MATCHES  '``**^A** B0123$``' - first character is a letter, '``*``' can specify zero characters, and end of line did not need to be matched.
- '``^[A-Z][A-Z][0-9]``' - MATCHES  '``**^AB0** 123$``' - first two characters are letters aind the third is a digit.
- '``^[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.


---------------
Working example
---------------

.. class:: infomark

**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 |
+-------------------+--------------------------------------------------------------------------------------------------------------+

.. class:: infomark

**Other input parameters**

+------------------------------------+-----------------+
| Input Parameter                    | Value           |
+====================================+=================+
| Names of sample classes            | M               |
+------------------------------------+-----------------+
| Include named classes              | filter-in       |
+------------------------------------+-----------------+
| Column that names the sample-class | gender          |
+------------------------------------+-----------------+
| Column that names the sample       | sampleMetadata  |
+------------------------------------+-----------------+

.. class:: infomark

**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 |
+-------------------+-----------------------------------------------------------------------------------------------------------------+


-----------------------------------------------------------------------------

----
NEWS
----

CHANGES IN VERSION 0.98.2
=========================

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

* Support and tests for new features.


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

INTERNAL MODIFICATIONS

none

    ]]>
  </help>
  <citations>
    <citation type="doi">10.1021/ac051437y</citation>
    <citation type="doi">10.1093/bioinformatics/btu813</citation>
  </citations>
  <!--
     vim:noet:sw=4:ts=4
--> </tool>