comparison w4mcorcov.xml @ 12:ddaf84e15d06 draft

planemo upload for repository https://github.com/HegemanLab/w4mcorcov_galaxy_wrapper/tree/master commit 6775c83b89d9d903c81a2229cdc200fc93538dfe-dirty

11:ddcc33ff3205

<tool id="w4mcorcov" name="OPLS-DA_Contrasts" version="0.98.15">
    <description>OPLS-DA Contrasts of Univariate Results</description>
    <macros>
        <xml name="paramPairSigFeatOnly">
            <param name="pairSigFeatOnly" type="boolean" checked="true" truevalue="TRUE" falsevalue="FALSE"
                label="Retain only pairwise-significant features"

          <has_text text="vip4p" />
          <has_text text="vip4o" />
          <has_text text="level1Level2Sig" />
          <!-- first matched line -->
          <has_text text="M349.2383T700" />
          <has_text text="-0.3704185" />
          <has_text text="-36.6668927" />
          <has_text text="0.4914638" />
          <has_text text="0.01302117" />
          <!-- second matched line -->
          <has_text text="M207.9308T206" />
          <has_text text="0.3235022" />
          <has_text text="5.97529097" />
          <has_text text="0.207196379" />
          <has_text text="0.04438632" />
        </assert_contents>
      </output>

          <has_text text="vip4p" />
          <has_text text="vip4o" />
          <has_text text="level1Level2Sig" />
          <!-- first matched line -->
          <has_text text="M200.005T296" />
          <has_text text="-0.24533821" />
          <has_text text="-3.3573953" />
          <has_text text="0.1157346" />
          <has_text text="0.0647860" />
        </assert_contents>
      </output>

          <has_text text="covariance" />
          <has_text text="vip4p" />
          <has_text text="vip4o" />
          <!-- first matched line -->
          <has_text text="M349.2383T700" />
          <has_text text="-0.37867079" />
          <has_text text="-37.71066" />
          <has_text text="0.5246766" />
          <has_text text="0.0103341" />
          <!-- second matched line -->
          <has_text text="M207.9308T206" />
          <has_text text="0.31570433" />
          <has_text text="5.86655640" />
          <has_text text="0.2111623" />
          <has_text text="0.0488654" />
        </assert_contents>
      </output>

          <has_text text="vip4o" />
          <!-- first matched line -->
          <has_text text="NM516T251" />
          <has_text text="flower_yes" />
          <has_text text="other" />
          <has_text text="0.03402807" />
          <has_text text="0.03526926" />
          <has_text text="0.43664386" />
          <has_text text="0.587701897" />
          <has_text text="0.026082688" />
          <has_text text="0.0437742145" />

          <has_text text="covariance" />
          <has_text text="vip4p" />
          <has_text text="vip4o" />
          <!-- first matched line -->
          <has_text text="M349.2383T700" />
          <has_text text="0.43361563" />
          <has_text text="37.76875778" />
          <has_text text="0.54672558" />
          <has_text text="0.3920409" />
          <!-- second matched line -->
          <has_text text="M207.9308T206" />
          <has_text text="-0.3365475" />
          <has_text text="-6.337903" />
          <has_text text="0.270297" />
          <has_text text="0.037661" />
        </assert_contents>
      </output>

          <has_text text="covariance" />
          <has_text text="vip4p" />
          <has_text text="vip4o" />
          <!-- first matched line -->
          <has_text text="M349.2383T700" />
          <has_text text="-0.0435663" />
          <has_text text="-1.9068114" />
          <has_text text="0.0304592" />
          <has_text text="0.104748883" />
        </assert_contents>
      </output>
    </test>
    <!-- test #6 - issue 8 -->
    <test>
      <param name="dataMatrix_in" value="input_dataMatrix.tsv"/>
      <param name="sampleMetadata_in" value="issue8_input_sampleMetadata.tsv"/>
      <param name="variableMetadata_in" value="input_variableMetadata.tsv"/>
      <param name="tesC" value="none"/>

**Run PLS-DA Contrasts of Univariate Results**
----------------------------------------------

**Author** - Arthur Eschenlauer (University of Minnesota, [e-mail])


Motivation
----------

OPLS-DA and the SIMCA S-PLOT (Wiklund *et al.*, 2008) may be employed to draw attention to metabolomic features that are potential biomarkers, i.e. features that are potentially useful to discriminate to which class a sample should be assigned (e.g. Sun *et al.*, 2016).  Workflow4Metabolomics (W4M, Giacomoni *et al.*, 2014, Guitton *et al.*, 2017) provides a suite of tools for preprocessing and statistical analysis of LC-MS, GC-MS, and NMR metabolomics data; however, it does not (as of release 3.0) include a tool for making the equivalent of an S-PLOT.

[IN] Label how many extreme features
  | Specify the number of features at each of the loading-extremes that should be labelled (with the name of the feature) on the covariance-vs.-correlation plot; specify 'ALL' to label all features; this choice has no effect on the OPLS-DA loadings plot.
  |

[OUT] Contrast-detail output PDF
  | Several plots for each two-projection OPLS-DA analysis:

- (first row, left) **correlation-versus-covariance plot** of OPLS-DA results (a work-alike for the S-PLOT, computed using formula in Supplement to Wiklund, *op. cit.*); point-color becomes saturated as the "variable importance in projection to the predictive components" (VIP\ :subscript:`4,p` from Galindo-Prieto *et al.* 2014) ranges from 0.83 and 1.21 (Mehmood *et al.* 2012), for use to identify features for consideration as biomarkers.
- (second row, left) **model-overview plot** for the two projections; grey bars are the correlation coefficient for the fitted data; black bars indicate performance in cross-validation tests (Th]]>&#233;<![CDATA[venot, 2017)
- (first row, right) OPLS-DA **scores-plot** for the two projections (Th]]>&#233;<![CDATA[venot *et al.*, 2015)
- (second row, right) **correlation-versus-covariance plot** of OPLS-DA results **orthogonal to the predictor** (see section "S-Plot of Orthogonal Component" in Wiklund, *op. cit.*, pp. 120-121; this characterizes features with the greatest variation independent of the predictor).
- (third row, left, when "**predictor C-plot**" is chosen under "Extra plots to include") plot of the covariance or correlation vs. the VIP for the projection *parallel to the predictor*, for use to identify features for consideration as biomarkers.
- (third row, right, when "**orthogonal C-plot**" is chosen under "Extra plots to include") plotof the covariance or correlation vs. the VIP for the projection *orthogonal to the predictor*, for use to identify features varying considerably without regard to the predictor.

  | This file has the following columns:

- **featureID** - feature-identifier
- **factorLevel1** - factor-level 1
- **factorLevel2** - factor-level 2 (or "other" when contrasting factor-level 1 with all other levels)
- **correlation** - correlation of the features projection explaining the difference between the features, < 0 when intensity for level 1 is greater (from formula in Supplement to Wiklund, *op. cit.*).  Note that, for a given contrast, there is a linear relationship between 'loadp' and 'correlation'.
- **covariance** - covariance of the features projection explaining the difference between the features, < 0 when intensity for level 1 is greater (from formula in *ibid.*)
- **vip4p** - "variable importance in projection" to the predictive projection, VIP\ :subscript:`4,p` (Galindo-Prieto *op. cit.*)
- **vip4o** - "variable importance in projection" to the orthogonal projection, VIP\ :subscript:`4,o` (*ibid.*)
- **loadp** - variable loading for the predictive projection (Wiklund *op. cit.*)
- **loado** - variable loading for the orthogonal projection (*ibid.*)
- **level1Level2Sig** - (Only present when a test other than "none" is chosen) '1' when feature varies significantly across all classes (i.e., not pair-wise); '0' otherwise

[OUT] Feature "Salience" data TABULAR
  | Metrics for the "salient level" for each feature, i.e., the level at which the feature is more prominent than any other level.  This is *not* at all related to the SIMCA OPLS-DA S-PLOT; rather, it is intended as a potential way to discover features for consideration as potential biomarkers without dimensionally reducting the data.  This is a tab-separated values file having the following columns:

  ]]></help>
  <citations>
    <!-- this tool -->
    <citation type="doi">10.5281/zenodo.1034784</citation>
    <!-- Galindo_Prieto_2014 Variable influence on projection (VIP) for OPLS -->
    <citation type="doi">10.1002/cem.2627</citation>
    <!-- Giacomoni_2014 W4M 2.5 -->
    <citation type="doi">10.1093/bioinformatics/btu813</citation>
    <!-- Guitton_2017 W4M 3.0 -->

    <citation type="doi">10.1016/j.chemolab.2008.08.004</citation>
    <!-- Rinuardo 2016 -->
    <citation type="doi">10.3389/fmolb.2016.00026</citation>
    <!-- Sun_2016 Urinary Biomarkers for adolescent idiopathic scoliosis -->
    <citation type="doi">10.1038/srep22274</citation>
    <!-- Thevenot_2015 Urinary metabolome statistics -->
    <citation type="doi">10.1021/acs.jproteome.5b00354</citation>
    <!-- ropls package -->
    <citation type="bibtex"><![CDATA[
    @incollection{Thevenot_ropls_2017,

      address = {Roswell Park Cancer Institute},
    }
    ]]></citation>
    <!-- Wiklund_2008 OPLS PLS-DA and S-PLOT -->
    <citation type="doi">10.1021/ac0713510</citation>
  </citations>
  <!--
     vim:et:sw=4:ts=4
-->
</tool>

12:ddaf84e15d06

<tool id="w4mcorcov" name="OPLS-DA_Contrasts" version="0.98.16">
    <description>OPLS-DA Contrasts of Univariate Results</description>
    <macros>
        <xml name="paramPairSigFeatOnly">
            <param name="pairSigFeatOnly" type="boolean" checked="true" truevalue="TRUE" falsevalue="FALSE"
                label="Retain only pairwise-significant features"

          <has_text text="vip4p" />
          <has_text text="vip4o" />
          <has_text text="level1Level2Sig" />
          <!-- first matched line -->
          <has_text text="M349.2383T700" />
          <has_text text="-0.462909875" />
          <has_text text="-36.6668927" />
          <has_text text="0.4914638" />
          <has_text text="0.01302117" />
          <!-- second matched line -->
          <has_text text="M207.9308T206" />
          <has_text text="0.504885262" />
          <has_text text="5.97529097" />
          <has_text text="0.207196379" />
          <has_text text="0.04438632" />
        </assert_contents>
      </output>

          <has_text text="vip4p" />
          <has_text text="vip4o" />
          <has_text text="level1Level2Sig" />
          <!-- first matched line -->
          <has_text text="M200.005T296" />
          <has_text text="-0.28035717" />
          <has_text text="-3.3573953" />
          <has_text text="0.1157346" />
          <has_text text="0.0647860" />
        </assert_contents>
      </output>

          <has_text text="covariance" />
          <has_text text="vip4p" />
          <has_text text="vip4o" />
          <!-- first matched line -->
          <has_text text="M349.2383T700" />
          <has_text text="-0.4732226665" />
          <has_text text="-37.71066" />
          <has_text text="0.5246766" />
          <has_text text="0.0103341" />
          <!-- second matched line -->
          <has_text text="M207.9308T206" />
          <has_text text="0.4927151212" />
          <has_text text="5.86655640" />
          <has_text text="0.2111623" />
          <has_text text="0.0488654" />
        </assert_contents>
      </output>

          <has_text text="vip4o" />
          <!-- first matched line -->
          <has_text text="NM516T251" />
          <has_text text="flower_yes" />
          <has_text text="other" />
          <has_text text="0.3499550705" />
          <has_text text="0.03526926" />
          <has_text text="0.43664386" />
          <has_text text="0.587701897" />
          <has_text text="0.026082688" />
          <has_text text="0.0437742145" />

          <has_text text="covariance" />
          <has_text text="vip4p" />
          <has_text text="vip4o" />
          <!-- first matched line -->
          <has_text text="M349.2383T700" />
          <has_text text="0.61594030" />
          <has_text text="37.76875778" />
          <has_text text="0.54672558" />
          <has_text text="0.3920409" />
          <!-- second matched line -->
          <has_text text="M207.9308T206" />
          <has_text text="-0.89716403" />
          <has_text text="-6.337903" />
          <has_text text="0.270297" />
          <has_text text="0.037661" />
        </assert_contents>
      </output>

          <has_text text="covariance" />
          <has_text text="vip4p" />
          <has_text text="vip4o" />
          <!-- first matched line -->
          <has_text text="M349.2383T700" />
          <has_text text="-0.331230562" />
          <has_text text="-2.47167915" />
          <has_text text="0.0892595" />
          <has_text text="0.0049228872" />
        </assert_contents>
      </output>
    </test>
    <!-- test #7 - issue 8 -->
    <test>
      <param name="dataMatrix_in" value="input_dataMatrix.tsv"/>
      <param name="sampleMetadata_in" value="issue8_input_sampleMetadata.tsv"/>
      <param name="variableMetadata_in" value="input_variableMetadata.tsv"/>
      <param name="tesC" value="none"/>

**Run PLS-DA Contrasts of Univariate Results**
----------------------------------------------

**Author** - Arthur Eschenlauer (University of Minnesota, [e-mail])

**Release Notes** - https://github.com/HegemanLab/w4mcorcov_galaxy_wrapper#release-notes

Motivation
----------

OPLS-DA and the SIMCA S-PLOT (Wiklund *et al.*, 2008) may be employed to draw attention to metabolomic features that are potential biomarkers, i.e. features that are potentially useful to discriminate to which class a sample should be assigned (e.g. Sun *et al.*, 2016).  Workflow4Metabolomics (W4M, Giacomoni *et al.*, 2014, Guitton *et al.*, 2017) provides a suite of tools for preprocessing and statistical analysis of LC-MS, GC-MS, and NMR metabolomics data; however, it does not (as of release 3.0) include a tool for making the equivalent of an S-PLOT.

[IN] Label how many extreme features
  | Specify the number of features at each of the loading-extremes that should be labelled (with the name of the feature) on the covariance-vs.-correlation plot; specify 'ALL' to label all features; this choice has no effect on the OPLS-DA loadings plot.
  |

[OUT] Contrast-detail output PDF
  | File containing several plots for each two-projection OPLS-DA analysis.

- (first row, left) **correlation-versus-covariance plot** of OPLS-DA results

    - This is a work-alike for the S-PLOT, computed using formula in equations 1 and 2 from Wiklund, (*op. cit.*);
    - point-color becomes saturated as the "variable importance in projection to the predictive components" (VIP\ :subscript:`4,p` from Galindo-Prieto *et al.* 2014) increases through the range from 0.83 and 1.21 (Mehmood *et al.* 2012), for use to identify features for consideration as biomarkers;
    - plot symbols are diamonds when the adjusted p-value of correlation is greater than 0.05, circles when it is less than 0.01, and triangles when it between these limits.
- (second row, left) **model-overview plot** for the two projections; grey bars are the correlation coefficient for the fitted data; black bars indicate performance in cross-validation tests (Th]]>&#233;<![CDATA[venot, 2017)
- (first row, right) OPLS-DA **scores-plot** for the two projections (Th]]>&#233;<![CDATA[venot *et al.*, 2015)
- (second row, right) **correlation-versus-covariance plot** of OPLS-DA results **orthogonal to the predictor** (see section "S-Plot of Orthogonal Component" in Wiklund, *op. cit.*, pp. 120-121; this characterizes features with the greatest variation independent of the predictor).
- (third row, left, when "**predictor C-plot**" is chosen under "Extra plots to include") plot of the covariance or correlation vs. the VIP for the projection *parallel to the predictor*, for use to identify features for consideration as biomarkers.
- (third row, right, when "**orthogonal C-plot**" is chosen under "Extra plots to include") plotof the covariance or correlation vs. the VIP for the projection *orthogonal to the predictor*, for use to identify features varying considerably without regard to the predictor.

  | This file has the following columns:

- **featureID** - feature-identifier
- **factorLevel1** - factor-level 1
- **factorLevel2** - factor-level 2 (or "other" when contrasting factor-level 1 with all other levels)
- **correlation** - correlation of the features projection explaining the difference between the features, < 0 when intensity for level 1 is greater (from equation 2 in Wiklund, *op. cit.*).  Note that, for a given contrast, there is a linear relationship between 'loadp' and 'correlation'.
- **covariance** - relative covariance of the features projection explaining the difference between the features, < 0 when intensity for level 1 is greater (from formula in *ibid.*, but scaled so that the greatest value has a magnitude of 1)
- **vip4p** - "variable importance in projection" to the predictive projection, VIP\ :subscript:`4,p` (Galindo-Prieto *op. cit.*)
- **vip4o** - "variable importance in projection" to the orthogonal projection, VIP\ :subscript:`4,o` (*ibid.*)
- **loadp** - variable loading for the predictive projection (Wiklund *op. cit.*)
- **loado** - variable loading for the orthogonal projection (*ibid.*)
- **cor_p_val_raw** - p-value for Fisher-transformed correlation (Fisher, 1921; Snedecor, 1980; see also https://en.wikipedia.org/wiki/Fisher_transformation), with no family-wise error-rate correction.
- **cor_p_value** - p-value for Fisher-transformed correlation, adjusted for family-wise error rate (Yekutieli *et al.*, 2001).  Caveat: any previous selection for features that vary notably by factor level may result in too little adjustment.
- **cor_ci_lower** - lower limit of 95% confidence interval for correlation (see e.g. https://en.wikipedia.org/wiki/Fisher_transformation)
- **cor_ci_upper** - upper limit of 95% confidence interval for correlation (*ibid.*)
- **mz** - *m/z* ratio for feature, copied from input variableMetadata
- **rt** - retention time for feature, copied from input variableMetadata
- **level1Level2Sig** - (Only present when a test other than "none" is chosen) '1' when feature varies significantly across all classes (i.e., not pair-wise); '0' otherwise

[OUT] Feature "Salience" data TABULAR
  | Metrics for the "salient level" for each feature, i.e., the level at which the feature is more prominent than any other level.  This is *not* at all related to the SIMCA OPLS-DA S-PLOT; rather, it is intended as a potential way to discover features for consideration as potential biomarkers without dimensionally reducting the data.  This is a tab-separated values file having the following columns:

  ]]></help>
  <citations>
    <!-- this tool -->
    <citation type="doi">10.5281/zenodo.1034784</citation>
    <!-- Fisher_1921: Fisher z-transformation of correlation coefficient -->
    <citation type="bibtex"><![CDATA[
    @article{Fisher_1921,
      author = {Fisher, R. A.},
      title = {{On the probable error of a coefficient of correlation deduced from a small sample}},
      journal = {Metron},
      year = {1921},
      volume = {1},
      pages = {3--32},
      note = {Defines the Fisher z-transformation of a coefficient of correlation.  Citation adapted from http://www.citeulike.org/group/894/article/2344770},
      url = {https://digital.library.adelaide.edu.au/dspace/bitstream/2440/15169/1/14.pdf},
    }
    ]]></citation>
    <!-- Galindo_Prieto_2014 Variable influence on projection (VIP) for OPLS -->
    <citation type="doi">10.1002/cem.2627</citation>
    <!-- Giacomoni_2014 W4M 2.5 -->
    <citation type="doi">10.1093/bioinformatics/btu813</citation>
    <!-- Guitton_2017 W4M 3.0 -->

    <citation type="doi">10.1016/j.chemolab.2008.08.004</citation>
    <!-- Rinuardo 2016 -->
    <citation type="doi">10.3389/fmolb.2016.00026</citation>
    <!-- Sun_2016 Urinary Biomarkers for adolescent idiopathic scoliosis -->
    <citation type="doi">10.1038/srep22274</citation>
    <!-- Snedecor_1980: Fisher z-transformation of correlation coefficient -->
    <citation type="bibtex"><![CDATA[
    @book{Snedecor_1980,
      author = {Snedecor, George W. and Cochran, William G.},
      title = {Statistical methods},
      publisher = {Iowa State University Press},
      year = {1980},
      pages = {186},
      isbn = {0813815606},
      language = {eng},
      keyword = {Statistics, Statistics as Topic -- methods},
      lccn = {80014582},
      edition = {7th ed..},
      address = {Ames, Iowa},
    }
    ]]></citation>
    <!-- Thevenot_2015 Urinary metabolome statistics -->
    <citation type="doi">10.1021/acs.jproteome.5b00354</citation>
    <!-- ropls package -->
    <citation type="bibtex"><![CDATA[
    @incollection{Thevenot_ropls_2017,

      address = {Roswell Park Cancer Institute},
    }
    ]]></citation>
    <!-- Wiklund_2008 OPLS PLS-DA and S-PLOT -->
    <citation type="doi">10.1021/ac0713510</citation>
    <!-- Yekutieli_2001 The control of the false discovery rate in multiple testing under dependency -->
    <citation type="doi">10.1214/aos/1013699998</citation>
  </citations>
  <!--
     vim:et:sw=4:ts=4
-->
</tool>