annotate feature_alignment.xml @ 0:7ac5166f8bbc draft default tip

"planemo upload for repository https://github.com/msproteomicstools/msproteomicstools/blob/master/TRIC-README.md commit 75f5dee4cc5cb3dbfac3d1d32d8bceb2a22634d7"

<tool id="feature_alignment" name="TRIC" version="@TOOL_VERSION@+galaxy@GALAXY_VERSION@">
    <description>integrates information from all available runs via a graph-based alignment strategy</description>
    <macros>
        <token name="@TOOL_VERSION@">0.11.0</token>
        <token name="@GALAXY_VERSION@">0</token>
        <import>macros.xml</import>
    </macros>
    <requirements>
        <requirement type="package" version="@TOOL_VERSION@">msproteomicstools</requirement>
        <requirement type="package" version="2.8.6">rpy2</requirement>
    </requirements>
    <version_command>feature_alignment.py --version</version_command>
    <command detect_errors="exit_code"><![CDATA[
    feature_alignment.py 
        --in #echo '' ''.join([ str($file) for $file in $inputs ])
        --out out.tsv
        --out_matrix out_matrix.tsv
        --out_ids out_ids.tsv
        --file_format '$iformat'
        --method '$method_sel.method'
        --matrix_output_method '$matrix_output_method'
        --realign_method '$realign_method'
        #if $max_rt_diff_cond.max_rt_diff_sel == 'opt_max_rt_diff_enabled':
            --max_rt_diff '$max_rt_diff_cond.max_rt_diff'
        #end if
        #if $iso_max_rt_diff_cond.iso_max_rt_diff_sel == 'opt_iso_max_rt_diff_enabled':
            --iso_max_rt_diff '$iso_max_rt_diff_cond.iso_max_rt_diff'
        #end if
        #if $frac_selected_cond.frac_selected_sel == 'opt_frac_selected_enabled':
            --frac_selected '$frac_selected_cond.frac_selected'
        #end if
        #if $fdr_cond.fdr_sel == 'opt_target_fdr':
            --target_fdr '$fdr_cond.target_fdr'
        #elif $fdr_cond.fdr_sel == 'opt_fdr_cutoff':
            --fdr_cutoff '$fdr_cond.fdr_cutoff'
        #else:
            --target_fdr '0'
        #end if
        --max_fdr_quality '$max_fdr_quality'
        #if $method_sel.method == 'LocalMST' or $method_sel.method == 'LocalMSTAllCluster':
            --mst:useRTCorrection '$method_sel.mst_useRTCorrection'
            --mst:Stdev_multiplier '$method_sel.mst_Stdev_multiplier'
            --mst:useLocalStdev '$method_sel.mst_useLocalStdev'
            --mst:useReference '$method_sel.mst_useReference'
        #end if
        #if $further_params.disable_isotopic_grouping:
            --disable_isotopic_grouping
        #end if
        #if $further_params.dscore_cond.dscore_sel == 'opt_dscore_enabled':
            --use_dscore_filter
            --dscore_cutoff '$further_params.dscore_cond.dscore_cutoff'
        #end if
        #if $further_params.nr_high_conf_exp_cond.nr_high_conf_exp_sel == 'opt_nr_high_conf_exp_enabled':
            --nr_high_conf_exp '$further_params.nr_high_conf_exp_cond.nr_high_conf_exp'
        #end if
        #if $further_params.readmethod != 'disabled':
            --readmethod '$further_params.readmethod'
        #end if
        #if $further_params.alignment_score_cond.alignment_score_sel == 'opt_alignment_score_enabled':
            --alignment_score '$further_params.alignment_score_cond.alignment_score'
        #end if

    #if $iformat == 'openswath':
        && cat out.tsv > '$out'
    #end if
    && cat out_matrix.tsv > '$out_matrix'
    && cat out_ids.tsv > '$out_ids'
    ]]></command>
    <inputs>
        <param name="inputs" type="data" multiple="True" format="txt" label="Output files containing all peakgroups from OpenSWATH (using either mProphet or pyProphet) or Peakview." help="(--in)"/>
        <param name="iformat" type="select" label="Which input file format is used" help="(--file_format)">
            <option value="openswath" selected="True">OpenSwath</option>
            <option value="mprophet">mProphet (mQuest)</option>
            <option value="peakview">PeakView</option>
        </param>
        <conditional name="method_sel">
            <param name="method" type="select" label="Which method to use for the clustering"
                help="Note that the MST options will perform a local, MST guided alignment while the other options will use a reference-guided alignment. The global option will also move peaks which are below the selected FDR threshold. (--method)" >
                <option value="best_overall" selected="True">best overall</option>
                <option value="best_cluster_score">best cluster score</option>
                <option value="global_best_cluster_score">global best cluster score</option>
                <option value="global_best_overall">global best overall</option>
                <option value="LocalMST">LocalMST</option>
                <option value="LocalMSTAllCluster">LocalMSTAllCluster</option>
            </param>
            <when value="best_overall"/>
            <when value="best_cluster_score"/>
            <when value="global_best_cluster_score"/>
            <when value="global_best_overall"/>
            <when value="LocalMST">
                <expand macro="mst_params"/>
            </when>
            <when value="LocalMSTAllCluster">
                <expand macro="mst_params"/>
            </when>
        </conditional>
        <param name="matrix_output_method" type="select"
            label="Which columns are written besides Intensity" help="(--matrix_output_method)">
            <option value="none" selected="True">None</option>
            <option value="RT">RT</option>
            <option value="score">Score</option>
            <option value="source">Source</option>
            <option value="full">Full</option>
        </param>
        <param name="realign_method" type="select" label="How to re-align runs in retention time" help="(--realign_method)">
            <option value="diRT" selected="True">Use only deltaiRT (diRT) from the input file</option>
            <option value="linear">Perform a linear regression using best peakgroups</option>
            <option value="lowess">Use Robust locally weighted regression (lowess smoother)</option>
            <option value="splinePy">Use Python native spline from scikits.datasmooth (slow!)</option>
            <option value="CVSpline">Splines with cross-validation</option>
            <option value="nonCVSpline">Splines without cross-validation</option>
            <option value="WeightedNearestNeighbour">WeightedNearestNeighbour</option>
            <option value="SmoothLLDMedian">SmoothLLDMedian</option>
            <option value="splineR">Perform a spline fit using R</option>
            <option value="splineR_external">Perform a spline fit using R (external)</option>
            <option value="Earth">Use Multivariate Adaptive Regression Splines using py-earth</option>
            <option value="lowess_cython">lowess_cython</option>
        </param>
        <conditional name="max_rt_diff_cond">
            <param name="max_rt_diff_sel" type="select" label="Enable difference in RT for two aligned features" help="Maximal difference in RT for two aligned features">
                <option value="opt_max_rt_diff_disabled" selected="True">disabled</option>
                <option value="opt_max_rt_diff_enabled">set difference in RT</option>
            </param>
            <when value="opt_max_rt_diff_disabled"/>
            <when value="opt_max_rt_diff_enabled">
                <param name="max_rt_diff" type="integer" value="30" label="Difference in RT (in seconds) for two aligned features" help="(--max_rt_diff)"/>
            </when>
        </conditional>
        <conditional name="iso_max_rt_diff_cond">
            <param name="iso_max_rt_diff_sel" type="select" label="Enable difference in RT for two isotopic channels" help="Maximal difference in RT (in seconds) for two isotopic channels in the same run">
                <option value="opt_iso_max_rt_diff_disabled" selected="True">disabled</option>
                <option value="opt_iso_max_rt_diff_enabled">set difference in RT</option>
            </param>
            <when value="opt_iso_max_rt_diff_disabled"/>
            <when value="opt_iso_max_rt_diff_enabled">
                <param name="iso_max_rt_diff" type="integer" value="30" label="Difference in RT (in seconds) for two isotopic channels." help="(--iso_max_rt_diff)" />
            </when>
        </conditional>
        <conditional name="frac_selected_cond">
            <param name="frac_selected_sel" type="select" label="Enable fraction of runs" help="Do not write peakgroup if selected in less than this fraction of runs">
                <option value="opt_frac_selected_disabled" selected="True">disabled</option>
                <option value="opt_frac_selected_enabled">set fraction of runs</option>
            </param>
            <when value="opt_frac_selected_disabled"/>
            <when value="opt_frac_selected_enabled">
                <param name="frac_selected" type="float" value="0.0" min="0" max="1" label="Fraction of runs" help="(--frac_selected)"/>
            </when>
        </conditional>
        <conditional name="fdr_cond">
            <param name="fdr_sel" type="select" label="Choose FDR method" help="">
                <option value="opt_fdr_disabled">disabled</option>
                <option value="opt_target_fdr" selected="True">Target FDR</option>
                <option value="opt_fdr_cutoff">FDR cutoff</option>
            </param>
            <when value="opt_fdr_disabled"/>
            <when value="opt_target_fdr">
                <param name="target_fdr" type="float" value="0.01" label="Target FDR" help="Refers to the desired FDR on assay level. (--target_fdr)"/>
            </when>
            <when value="opt_fdr_cutoff">
                <param name="fdr_cutoff" type="float" value="0.01" label="Seeding score cutoff" help="A fixed m-score cutoff which does not take into account the number of runs (use target_fdr instead). (--fdr_cutoff)" />
            </when>
        </conditional>
        <param name="max_fdr_quality" type="float" value="0.05" min="0" label="Extension score cutoff"
               help="During the extension phase of the algorithm, peakgroups of this quality will still be considered for alignment (in FDR) - it is possible to give a range in the format lower,higher+stepsize,stepsize - e.g. 0,0.31,0.01  (-1 will set it to fdr_cutoff) (--max_fdr_quality)"/>
        <section name="further_params" title="Further parameters" expanded="False">
            <param name="disable_isotopic_grouping" type="boolean" truevalue="True" falsevalue="False" checked="false" label="Disable grouping of isotopic variants"
                   help="Disable grouping of isotopic variants by peptide_group_label, thus disabling matching of isotopic variants of the same peptide across channels. If turned off, each isotopic channel will be matched independently of the other. If enabled, the more certain identification will be used to infer the location of the peak in the other channel. (--disable_isotopic_grouping)"/>
            <conditional name="dscore_cond">
                <param name="dscore_sel" type="select" label="Enable the filter by d score (this is mainly for speedup)" help="">
                    <option value="opt_dscore_disabled" selected="True">disabled</option>
                    <option value="opt_dscore_enabled">Use d score filter</option>
                </param>
                <when value="opt_dscore_disabled"/>
                <when value="opt_dscore_enabled">
                    <param name="dscore_cutoff" type="float" value="1.96" label="d score cut-off"
                           help="Quality cutoff to still consider a feature for alignment using the d_score: everything below this d-score is discarded (this is mainly for speedup). (--dscore_cutoff)"/>
                </when>
            </conditional>
            <conditional name="nr_high_conf_exp_cond">
                <param name="nr_high_conf_exp_sel" type="select" label="Enable the filter by d score (this is mainly for speedup)" help="">
                    <option value="opt_nr_high_conf_exp_disabled" selected="True">disabled</option>
                    <option value="opt_nr_high_conf_exp_enabled">Use number of experiments</option>
                </param>
                <when value="opt_nr_high_conf_exp_disabled"/>
                <when value="opt_nr_high_conf_exp_enabled">
                    <param name="nr_high_conf_exp" type="integer" value="1" optional="True" label="Number of experiments with high confidence"
                           help="Number of experiments in which the peptide needs to be identified with high confidence (e.g. above fdr_curoff). (--nr_high_conf_exp)"/>
                </when>
            </conditional>
            <param name="readmethod" type="select" label="Read full or minimal transition groups" optional="True" help="(--readmethod)">
                <option value="disabled" selected="True">disabled</option>
                <option value="minimal">minimal</option>
                <option value="full">full</option>
            </param>
            <conditional name="alignment_score_cond">
                <param name="alignment_score_sel" type="select" label="Enable the filter by d score (this is mainly for speedup)" help="">
                    <option value="opt_alignment_score_disabled" selected="True">disabled</option>
                    <option value="opt_alignment_score_enabled">Use number of experiments</option>
                </param>
                <when value="opt_alignment_score_disabled"/>
                <when value="opt_alignment_score_enabled">
                    <param name="alignment_score" type="float" value="0.0001" optional="True" label="Alignment score"
                           help="Minimal score needed for a feature to be considered for alignment between runs (e.g. score needed to be considered an 'anchor point' for pairwise alignment). (--alignment_score)"/>
                </when>
            </conditional>
        </section>
    </inputs>
    <outputs>
        <!-- Matrix containing one peak group per row -->
        <data format="tabular" name="out_matrix"/>
        <!-- Id file only containing the ids -->
        <data format="tabular" name="out_ids"/>
        <!-- Output file with filtered peakgroups for quantification -->
        <data format="tabular" name="out">
            <filter>iformat == 'openswath'</filter>
        </data>
    </outputs>
    <tests>
        <test>
            <param name="inputs" value="feature_alignment_openswath_input_1.csv" ftype="txt" />
            <param name="iformat" value="openswath" />
            <param name="method" value="best_cluster_score" />
            <param name="fdr_sel" value="opt_fdr_disabled" />
            <param name="max_fdr_quality" value="0.4" />
            <param name="matrix_output_method" value="RT" />
            <output name="out_matrix" file="feature_alignment_1_openswath_output_matrix.csv" lines_diff="2" ftype="tabular" />
            <output name="out_ids" file="feature_alignment_1_openswath_output_cluster_ids.csv" ftype="tabular" />
        </test>
        <test>
            <param name="inputs" value="feature_alignment_openswath_input_1.csv" ftype="txt" />
            <param name="iformat" value="openswath" />
            <param name="method" value="best_overall" />
            <param name="fdr_sel" value="opt_fdr_disabled" />
            <param name="max_fdr_quality" value="0.4" />
            <param name="matrix_output_method" value="RT" />
            <output name="out_matrix" file="feature_alignment_2_output_2_matrix.csv" lines_diff="2" ftype="tabular" />
            <output name="out_ids" file="feature_alignment_2_output_1_ids.csv" ftype="tabular" />
        </test>
        <test>
            <param name="inputs" value="feature_alignment_3_openswath_input.csv" ftype="txt" />
            <param name="iformat" value="openswath" />
            <param name="realign_method" value="splineR" />
            <param name="method" value="best_cluster_score" />
            <param name="fdr_sel" value="opt_fdr_disabled" />
            <param name="max_fdr_quality" value="0.4" />
            <param name="matrix_output_method" value="RT" />
            <output name="out_ids" file="feature_alignment_3_openswath_output_splineR_cluster_ids.csv" ftype="tabular" />
        </test>
        <test>
            <param name="inputs" value="feature_alignment_3_openswath_input.csv" ftype="txt" />
            <param name="iformat" value="openswath" />
            <param name="realign_method" value="splinePy" />
            <param name="method" value="best_cluster_score" />
            <param name="fdr_sel" value="opt_fdr_disabled" />
            <param name="max_fdr_quality" value="0.4" />
            <param name="matrix_output_method" value="RT" />
            <output name="out_ids" file="feature_alignment_3_openswath_output_splinePy_cluster_ids.csv" ftype="tabular" />
        </test>
        <test>
            <param name="inputs" value="feature_alignment_peakview_input_2.csv" ftype="txt" />
            <param name="iformat" value="peakview" />
            <param name="method" value="best_cluster_score" />
            <param name="max_rt_diff_sel" value="opt_max_rt_diff_enabled" />
            <param name="iso_max_rt_diff_sel" value="opt_iso_max_rt_diff_enabled" />
            <param name="frac_selected_sel" value="opt_frac_selected_enabled" />
            <param name="disable_isotopic_grouping" value="True" />
            <param name="nr_high_conf_exp_sel" value="opt_nr_high_conf_exp_enabled" />
            <param name="alignment_score_sel" value="opt_alignment_score_enabled" />
            <param name="max_fdr_quality" value="0.0001" />
            <param name="fdr_sel" value="opt_fdr_cutoff" />
            <param name="fdr_cutoff" value="0.000000001" />
            <param name="matrix_output_method" value="RT" />
            <output name="out_matrix" file="feature_alignment_5_peakview_output_matrix.csv" lines_diff="2" ftype="tabular" />
        </test>
    </tests>
    <help>
<![CDATA[

**What it does**

TRIC uses a graph-based alignment strategy based on non-linear retention time correction to integrate information from all available runs. The input consists of a set of csv files derived from a targeted proteomics experiment generated by OpenSWATH (using either mProphet or pyProphet) or generated by Peakview.

There are two basic running modes available. The first one uses a reference-based alignment where a single run is chosen as a reference and all other runs are aligned to it. This is a useful choice for a small number of runs that are chromatographically similar. The second mode generates a guidance tree based on chromatographic similarity of the input runs and uses this tree to align the targeted proteomics runs (the nodes in the tree are runs and the edges are pairwise alignments). Generally this mode is better for a large number of runs or for chromatographically dissimilar samples.

TRIC is part of msproteomicstools. For additional help please visit the `TRIC documentation <https://github.com/msproteomicstools/msproteomicstools/blob/master/TRIC-README.md>`_

]]>
    </help>
    <citations>
    </citations>
</tool>