Mercurial > repos > eschen42 > w4mjoinpn
changeset 1:dcfaffec48c8 draft default tip
planemo upload for repository https://github.com/HegemanLab/w4mjoinpn_galaxy_wrapper/tree/master commit 919fba0dbfcdb553bbb6e1c765c3a8c9f26a47f9
| author | eschen42 |
|---|---|
| date | Wed, 08 Aug 2018 19:40:57 -0400 |
| parents | 948bac693947 |
| children | |
| files | README.md w4mjoinpn.xml |
| diffstat | 2 files changed, 159 insertions(+), 122 deletions(-) [+] |
line wrap: on
line diff
--- a/README.md Sun Oct 29 10:05:05 2017 -0400 +++ /dev/null Thu Jan 01 00:00:00 1970 +0000 @@ -1,33 +0,0 @@ -[](https://doi.org/10.5281/zenodo.1038289) - -# w4mjoinpn_galaxy_wrapper - -This tool joins two sets of MS1 datasets for **exactly** the same set of samples, where one was gathered in positive -ionization-mode and the other in negative ionization-mode, for reasons set forth below. - -Workflow4Metabolomics (W4M, Giacomoni *et al.*, 2014, http://dx.doi.org/10.1093/bioinformatics/btu813; http://workflow4metabolomics.org; -https://github.com/workflow4metabolomics) provides a suite of Galaxy tools for processing and analyzing metabolomics data. - -W4M uses the XCMS package (Smith *et al.*, 2006 http://dx.doi.org/10.1021/ac051437y) to extract features and align -their retention times among multiple samples. - -After peak extraction and alignment, W4M uses the CAMERA package (Kuhl *et al.*, 2012, http://dx.doi.org/10.1021/ac202450g) -"to postprocess XCMS feature lists and to collect all features related to a compound into a compound spectrum." - -Both of these steps are done using data collected in a single ionization mode (i.e., only negative or only positive) -because it would not make sense to attempt to use CAMERA otherwise. - -However, multivariate analysis in general, and particularly the "False Discovery Rate" adjustment in hypothesis testing, -would both benefit from having all variables (features), negative and positive, combined for one analysis. It is also -cumbersome to be forced to do an analysis twice, once for each ionization mode. - -This tool will fail: - * when the samples are not listed in exactly the same order in the negative-mode dataMatrix and the positive-mode dataMatrix - * when the samples are not listed in exactly the same order in the negative-mode sampleMetadata and the positive-mode sampleMetadata - -Otherwise - * the two dataMatrix files are concatenated, and the names of features identified from positive ionization-mode data -are prefixed with "P"; negative, with "N". - * the two variableMetadata files are concatenated, and the names of features are prefixed in the same way. - * if sampleMetadata has a polarity column, its value is set to "posneg" in the output. - * Technically, the sampleMetadata file in the output is derived from the negative ionization-mode sampleMetadata.
--- a/w4mjoinpn.xml Sun Oct 29 10:05:05 2017 -0400 +++ b/w4mjoinpn.xml Wed Aug 08 19:40:57 2018 -0400 @@ -1,40 +1,123 @@ -<tool id="w4mjoinpn" name="Join +/- Ions" version="0.98.1"> - <description>Join positive and negative ionization-mode W4M datasets for the same samples</description> - <requirements> - <requirement type="package" version="8.25">coreutils</requirement> - <requirement type="package" version="4.2.3.dev0">sed</requirement> - </requirements> - <stdio> - <exit_code range="1:" level="fatal" /> - </stdio> - <command><![CDATA[ - echo "These are the the paths to the tools used by this script:" 1>&2 ; - which cut sed head paste cat cp bash test 1>&2 ; - $__tool_directory__/w4mjoinpn.sh - dmneg $dmneg - dmpos $dmpos - dmout $dmout - smneg $smneg - smpos $smpos - smout $smout - vmneg $vmneg - vmpos $vmpos - vmout $vmout - ]]></command> - <inputs> - <param name="dmpos" label="Data matrix positive" type="data" format="tabular" help="Positive ionization-mode: Features x samples (tabular data - decimal: '.'; missing: NA; mode: numerical; separator: tab character)" /> - <param name="smpos" label="Sample metadata positive" type="data" format="tabular" help="Positive ionization-mode: Samples x metadata (tabular data - decimal: '.'; missing: NA; mode: character or numerical; separator: tab character)" /> - <param name="vmpos" label="Variable metadata positive" type="data" format="tabular" help="Positive ionization-mode: Features x metadata (tabular data - decimal: '.'; missing: NA; mode: character or numerical; separator: tab character)" /> - <param name="dmneg" label="Data matrix negative" type="data" format="tabular" help="Negative ionization-mode: Features x samples (tabular data - decimal: '.'; missing: NA; mode: numerical; separator: tab character)" /> - <param name="smneg" label="Sample metadata negative" type="data" format="tabular" help="Negative ionization-mode: Samples x metadata (tabular data - decimal: '.'; missing: NA; mode: character or numerical; separator: tab character)" /> - <param name="vmneg" label="Variable metadata negative" type="data" format="tabular" help="Negative ionization-mode: Features x metadata (tabular data - decimal: '.'; missing: NA; mode: character or numerical; separator: tab character)" /> - </inputs> - <outputs> - <data name="dmout" label="${dmneg.name}.posneg" format="tabular" ></data> - <data name="smout" label="${smneg.name}.posneg" format="tabular" ></data> - <data name="vmout" label="${vmneg.name}.posneg" format="tabular" ></data> - </outputs> - <help><![CDATA[ +<tool id="w4mjoinpn" name="Join +/- Ions" version="0.98.2"> + <description>Join positive and negative ionization-mode W4M datasets for the same samples</description> + <requirements> + <requirement type="package" version="8.25">coreutils</requirement> + <!-- + <requirement type="package" version="4.2.3.dev0">sed</requirement> + --> + <requirement type="package" version="4.4">sed</requirement> + </requirements> + <stdio> + <exit_code range="1:" level="fatal" /> + </stdio> + <command detect_errors="aggressive"><![CDATA[ + pwd + ; + echo $__tool_directory__/w4mjoinpn.sh + vmneg $vmneg + vmpos $vmpos + vmout $vmout + dmneg $dmneg + dmpos $dmpos + dmout $dmout + smneg $smneg + smpos $smpos + smout $smout + ; + $__tool_directory__/w4mjoinpn.sh + vmneg $vmneg + vmpos $vmpos + vmout $vmout + dmneg $dmneg + dmpos $dmpos + dmout $dmout + smneg $smneg + smpos $smpos + smout $smout + ]]></command> + <inputs> + <param name="dmpos" label="Data matrix positive" type="data" format="tabular" + help="Positive ionization-mode: variables ✖ samples" /> + <param name="smpos" label="Sample metadata positive" type="data" format="tabular" + help="Positive ionization-mode: sample metadata, one row per sample" /> + <param name="vmpos" label="Variable metadata positive" type="data" format="tabular" + help="Positive ionization-mode: variable metadata, one row per variable" /> + <param name="dmneg" label="Data matrix negative" type="data" format="tabular" + help="Negative ionization-mode: variables ✖ samples" /> + <param name="smneg" label="Sample metadata negative" type="data" format="tabular" + help="Negative ionization-mode: sample metadata, one row per sample" /> + <param name="vmneg" label="Variable metadata negative" type="data" format="tabular" + help="Negative ionization-mode: variable metadata, one row per variable" /> + </inputs> + <outputs> + <data name="dmout" label="${dmneg.name}.posneg" format="tabular" ></data> + <data name="smout" label="${smneg.name}.posneg" format="tabular" ></data> + <data name="vmout" label="${vmneg.name}.posneg" format="tabular" ></data> + </outputs> + <tests> + <!-- test 1 --> + <test> + <param name="dmpos" value="input_dataMatrix_pos.tsv"/> + <param name="dmneg" value="input_dataMatrix_neg.tsv"/> + <param name="smpos" value="input_sampleMetadata_pos.tsv"/> + <param name="smneg" value="input_sampleMetadata_neg.tsv"/> + <param name="vmpos" value="input_variableMetadata_pos.tsv"/> + <param name="vmneg" value="input_variableMetadata_neg.tsv"/> + <output name="dmout"> + <assert_contents> + <has_text text="NM295T781" /> + <has_text text="1177836.83774999" /> + <has_text text="3552840.90153851" /> + </assert_contents> + </output> + <output name="vmout"> + <assert_contents> + <has_text text="NM295T781" /> + <has_text text="M295.125T780.95" /> + <has_text text="780.953277587891" /> + </assert_contents> + </output> + <output name="smout"> + <assert_contents> + <has_text text="Y5_1_RA4_01_212" /> + <has_text text="posneg" /> + <has_text text="Y13_1_RA6_01_214" /> + </assert_contents> + </output> + </test> + <!-- test 2 --> + <test> + <param name="dmpos" value="input_dataMatrix_pos.tsv"/> + <param name="dmneg" value="input_dataMatrix_neg.tsv"/> + <param name="smpos" value="input_sampleMetadata_pos.tsv"/> + <param name="smneg" value="input_sampleMetadata_neg_4col.tsv"/> + <param name="vmpos" value="input_variableMetadata_pos.tsv"/> + <param name="vmneg" value="input_variableMetadata_neg.tsv"/> + <output name="dmout"> + <assert_contents> + <has_text text="NM295T781" /> + <has_text text="1177836.83774999" /> + <has_text text="3552840.90153851" /> + </assert_contents> + </output> + <output name="vmout"> + <assert_contents> + <has_text text="NM295T781" /> + <has_text text="M295.125T780.95" /> + <has_text text="780.953277587891" /> + </assert_contents> + </output> + <output name="smout"> + <assert_contents> + <has_text text="Y5_1_RA4_01_212" /> + <has_text text="posneg" /> + <has_text text="y5" /> + <has_text text="bar" /> + </assert_contents> + </output> + </test> + </tests> + <help><![CDATA[ **Join positive and negative ionization-mode W4M datasets for the same samples** -------------------------------------------------------------------------------- @@ -46,7 +129,7 @@ Workflow4Metabolomics (W4M, Giacomoni *et al.*, 2014; http://workflow4metabolomics.org; https://github.com/workflow4metabolomics) provides a suite of Galaxy tools for processing and analyzing metabolomics data. - + W4M uses the XCMS package (Smith *et al.*, 2006) to extract features and align their retention times among multiple samples. @@ -88,56 +171,43 @@ **Input files** - +---------------------------------------------+-----------------------------------------------------------------------------------------------------------------------+ - | Input File | Download from URL | - +=============================================+=======================================================================================================================+ - | Data matrix, negative ionization-mode | https://raw.githubusercontent.com/HegemanLab/w4mjoinpn_galaxy_wrapper/master/test-data/input_dataMatrix_neg.tsv | - +---------------------------------------------+-----------------------------------------------------------------------------------------------------------------------+ - | Sample metadata, negative ionization-mode | https://raw.githubusercontent.com/HegemanLab/w4mjoinpn_galaxy_wrapper/master/test-data/input_sampleMetadata_neg.tsv | - +---------------------------------------------+-----------------------------------------------------------------------------------------------------------------------+ - | Variable metadata, negative ionization-mode | https://raw.githubusercontent.com/HegemanLab/w4mjoinpn_galaxy_wrapper/master/test-data/input_variableMetadata_neg.tsv | - +---------------------------------------------+-----------------------------------------------------------------------------------------------------------------------+ - | Data matrix, positive ionization-mode | https://raw.githubusercontent.com/HegemanLab/w4mjoinpn_galaxy_wrapper/master/test-data/input_dataMatrix_pos.tsv | - +---------------------------------------------+-----------------------------------------------------------------------------------------------------------------------+ - | Sample metadata, positive ionization-mode | https://raw.githubusercontent.com/HegemanLab/w4mjoinpn_galaxy_wrapper/master/test-data/input_sampleMetadata_pos.tsv | - +---------------------------------------------+-----------------------------------------------------------------------------------------------------------------------+ - | Variable metadata, positive ionization-mode | https://raw.githubusercontent.com/HegemanLab/w4mjoinpn_galaxy_wrapper/master/test-data/input_variableMetadata_pos.tsv | - +---------------------------------------------+-----------------------------------------------------------------------------------------------------------------------+ - -**Output files** + +---------------------------------------------+------------------------------------------------------------------------------------------------------------------------------------------+ + | Input File | Download from URL | + +=============================================+==========================================================================================================================================+ + | Data matrix, negative ionization-mode | https://raw.githubusercontent.com/HegemanLab/w4mjoinpn_galaxy_wrapper/master/tools/w4mjoinpn/test-data/input_dataMatrix_neg.tsv | + +---------------------------------------------+------------------------------------------------------------------------------------------------------------------------------------------+ + | Sample metadata, negative ionization-mode | https://raw.githubusercontent.com/HegemanLab/w4mjoinpn_galaxy_wrapper/master/tools/w4mjoinpn/test-data/input_sampleMetadata_neg.tsv | + +---------------------------------------------+------------------------------------------------------------------------------------------------------------------------------------------+ + | Variable metadata, negative ionization-mode | https://raw.githubusercontent.com/HegemanLab/w4mjoinpn_galaxy_wrapper/master/tools/w4mjoinpn/test-data/input_variableMetadata_neg.tsv | + +---------------------------------------------+------------------------------------------------------------------------------------------------------------------------------------------+ + | Data matrix, positive ionization-mode | https://raw.githubusercontent.com/HegemanLab/w4mjoinpn_galaxy_wrapper/master/tools/w4mjoinpn/test-data/input_dataMatrix_pos.tsv | + +---------------------------------------------+------------------------------------------------------------------------------------------------------------------------------------------+ + | Sample metadata, positive ionization-mode | https://raw.githubusercontent.com/HegemanLab/w4mjoinpn_galaxy_wrapper/master/tools/w4mjoinpn/test-data/input_sampleMetadata_pos.tsv | + +---------------------------------------------+------------------------------------------------------------------------------------------------------------------------------------------+ + | Variable metadata, positive ionization-mode | https://raw.githubusercontent.com/HegemanLab/w4mjoinpn_galaxy_wrapper/master/tools/w4mjoinpn/test-data/input_variableMetadata_pos.tsv | + +---------------------------------------------+------------------------------------------------------------------------------------------------------------------------------------------+ + +**Output files** + + +---------------------------------------------+------------------------------------------------------------------------------------------------------------------------------------------+ + | Output File | Download from URL | + +=============================================+==========================================================================================================================================+ + | Data matrix | https://raw.githubusercontent.com/HegemanLab/w4mjoinpn_galaxy_wrapper/master/tools/w4mjoinpn/test-data/expected_dataMatrix.tsv | + +---------------------------------------------+------------------------------------------------------------------------------------------------------------------------------------------+ + | Sample metadata | https://raw.githubusercontent.com/HegemanLab/w4mjoinpn_galaxy_wrapper/master/tools/w4mjoinpn/test-data/expected_sampleMetadata.tsv | + +---------------------------------------------+------------------------------------------------------------------------------------------------------------------------------------------+ + | Variable metadata | https://raw.githubusercontent.com/HegemanLab/w4mjoinpn_galaxy_wrapper/master/tools/w4mjoinpn/test-data/expected_variableMetadata.tsv | + +---------------------------------------------+------------------------------------------------------------------------------------------------------------------------------------------+ - +---------------------------------------------+-----------------------------------------------------------------------------------------------------------------------+ - | Output File | Download from URL | - +=============================================+=======================================================================================================================+ - | Data matrix | https://raw.githubusercontent.com/HegemanLab/w4mjoinpn_galaxy_wrapper/master/test-data/output_dataMatrix.tsv | - +---------------------------------------------+-----------------------------------------------------------------------------------------------------------------------+ - | Sample metadata | https://raw.githubusercontent.com/HegemanLab/w4mjoinpn_galaxy_wrapper/master/test-data/output_sampleMetadata.tsv | - +---------------------------------------------+-----------------------------------------------------------------------------------------------------------------------+ - | Variable metadata | https://raw.githubusercontent.com/HegemanLab/w4mjoinpn_galaxy_wrapper/master/test-data/output_variableMetadata.tsv | - +---------------------------------------------+-----------------------------------------------------------------------------------------------------------------------+ - - ]]></help> - <citations> - <citation type="doi">10.5281/zenodo.1038289</citation> + ]]></help> + <citations> + <!-- Giacomoni, 2014 Workflow4Metabolomics: a collaborative research infrastructure for computational metabolomics --> + <citation type="doi">10.1093/bioinformatics/btu813</citation> + <!-- Kuhl et al., 2012 CAMERA: An Integrated Strategy for Compound Spectra Extraction and Annotation of LC-MS Data Sets --> + <citation type="doi">10.1021/ac202450g</citation> + <!-- Smith, 2006 XCMS: Processing Mass Spectrometry Data for Metabolite Profiling Using Nonlinear Peak Alignment, Matching, and Identification. --> + <citation type="doi">10.1021/ac051437y</citation> + </citations> <!-- - <citation type="bibtex"> - @misc{ - w4mjoinpn_galaxy_wrapper, - author = {Eschenlauer, Arthur}, - year = {2017}, - title = {w4mjoinpn_galaxy_wrapper}, - publisher = {GitHub}, - journal = {GitHub repository}, - url = {https://github.com/HegemanLab/w4mjoinpn_galaxy_wrapper}, - doi = 10.5281/zenodo.1038290 - } - </citation> - --> - <!-- Giacomoni, 2014 Workflow4Metabolomics: a collaborative research infrastructure for computational metabolomics --> - <citation type="doi">10.1093/bioinformatics/btu813</citation> - <!-- Kuhl et al., 2012 --> - <citation type="doi">10.1021/ac202450g</citation> - <!-- Smith, 2006 XCMS: Processing Mass Spectrometry Data for Metabolite Profiling Using Nonlinear Peak Alignment, Matching, and Identification. --> - <citation type="doi">10.1021/ac051437y</citation> - </citations> -</tool> + vim:et:sw=4:ts=4 +--> </tool>