annotate MapAlignerIdentification.xml @ 4:bf50f9eb1dcb draft

"planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/openms commit 020906fb54bde7fc143c356f41975c378a741315"

<?xml version='1.0' encoding='UTF-8'?>
<!--This is a configuration file for the integration of a tools into Galaxy (https://galaxyproject.org/). This file was automatically generated using CTDConverter.-->
<!--Proposed Tool Section: [Map Alignment]-->
<tool id="MapAlignerIdentification" name="MapAlignerIdentification" version="@TOOL_VERSION@+galaxy@GALAXY_VERSION@" profile="20.05">
  <description>Corrects retention time distortions between maps based on common peptide identifications.</description>
  <macros>
    <token name="@EXECUTABLE@">MapAlignerIdentification</token>
    <import>macros.xml</import>
    <import>macros_autotest.xml</import>
    <import>macros_test.xml</import>
  </macros>
  <expand macro="requirements"/>
  <expand macro="stdio"/>
  <command detect_errors="exit_code"><![CDATA[@QUOTE_FOO@
@EXT_FOO@
#import re

## Preprocessing
mkdir in &&
${ ' '.join(["ln -s '%s' 'in/%s.%s' &&" % (_, re.sub('[^\w\-_]', '_', _.element_identifier), $gxy2omsext(_.ext)) for _ in $in if _]) }
#if "out_FLAG" in str($OPTIONAL_OUTPUTS).split(',')
  mkdir out &&
#end if
#if "trafo_out_FLAG" in str($OPTIONAL_OUTPUTS).split(',')
  mkdir trafo_out &&
#end if
#if $design:
  mkdir design &&
  ln -s '$design' 'design/${re.sub("[^\w\-_]", "_", $design.element_identifier)}.$gxy2omsext($design.ext)' &&
#end if
#if $reference.file:
  mkdir reference.file &&
  ln -s '$reference.file' 'reference.file/${re.sub("[^\w\-_]", "_", $reference.file.element_identifier)}.$gxy2omsext($reference.file.ext)' &&
#end if

## Main program call

set -o pipefail &&
@EXECUTABLE@ -write_ctd ./ &&
python3 '$__tool_directory__/fill_ctd.py' '@EXECUTABLE@.ctd' '$args_json' '$hardcoded_json' &&
@EXECUTABLE@ -ini @EXECUTABLE@.ctd
-in
${' '.join(["'in/%s.%s'"%(re.sub('[^\w\-_]', '_', _.element_identifier), $gxy2omsext(_.ext)) for _ in $in if _])}
#if "out_FLAG" in str($OPTIONAL_OUTPUTS).split(',')
  -out
  ${' '.join(["'out/%s.%s'"%(re.sub('[^\w\-_]', '_', _.element_identifier), _.ext) for _ in $in if _])}
#end if
#if "trafo_out_FLAG" in str($OPTIONAL_OUTPUTS).split(',')
  -trafo_out
  ${' '.join(["'trafo_out/%s.%s'"%(re.sub('[^\w\-_]', '_', _.element_identifier), $gxy2omsext("trafoxml")) for _ in $in if _])}
#end if
#if $design:
  -design
  'design/${re.sub("[^\w\-_]", "_", $design.element_identifier)}.$gxy2omsext($design.ext)'
#end if
#if $reference.file:
  -reference:file
  'reference.file/${re.sub("[^\w\-_]", "_", $reference.file.element_identifier)}.$gxy2omsext($reference.file.ext)'
#end if
#if len(str($OPTIONAL_OUTPUTS).split(',')) == 0
  | tee '$stdout'
#end if

## Postprocessing
#if "trafo_out_FLAG" in str($OPTIONAL_OUTPUTS).split(',')
  ${' '.join(["&& mv -n 'in/%(id)s.%(gext)s' 'trafo_out/%(id)s'"%{"id": re.sub('[^\w\-_]', '_', _.element_identifier), "gext": $gxy2omsext("trafoxml")} for _ in $trafo_out if _])}
#end if
#if "ctd_out_FLAG" in $OPTIONAL_OUTPUTS
  && mv '@EXECUTABLE@.ctd' '$ctd_out'
#end if]]></command>
  <configfiles>
    <inputs name="args_json" data_style="paths"/>
    <configfile name="hardcoded_json"><![CDATA[{"log": "log.txt", "threads": "\${GALAXY_SLOTS:-1}", "no_progress": true}]]></configfile>
  </configfiles>
  <inputs>
    <param name="in" argument="-in" type="data" format="consensusxml,featurexml,idxml" multiple="true" optional="false" label="Input files to align (all must have the same file type)" help=" select consensusxml,featurexml,idxml data sets(s)"/>
    <param name="design" argument="-design" type="data" format="tabular" optional="true" label="input file containing the experimental design" help=" select tabular data sets(s)"/>
    <section name="reference" title="Options to define a reference file (use either 'file' or 'index', not both)" help="" expanded="false">
      <param name="file" argument="-reference:file" type="data" format="consensusxml,featurexml,idxml" optional="true" label="File to use as reference" help=" select consensusxml,featurexml,idxml data sets(s)"/>
      <param name="index" argument="-reference:index" type="integer" optional="true" min="0" value="0" label="Use one of the input files as reference ('1' for the first file, etc.)" help="If '0', no explicit reference is set - the algorithm will select a reference"/>
    </section>
    <section name="algorithm" title="Algorithm parameters section" help="" expanded="false">
      <param name="score_cutoff" argument="-algorithm:score_cutoff" type="boolean" truevalue="true" falsevalue="false" checked="false" label="If only IDs above a score cutoff should be used" help="Used together with min_score"/>
      <param name="min_score" argument="-algorithm:min_score" type="float" optional="true" value="0.05" label="Minimum score for an ID to be considered" help="Applies to the last score calculated.. Unless you have very few runs or identifications, increase this value to focus on more informative peptides"/>
      <param name="min_run_occur" argument="-algorithm:min_run_occur" type="integer" optional="true" min="2" value="2" label="Minimum number of runs (incl" help="reference, if any) in which a peptide must occur to be used for the alignment.. Unless you have very few runs or identifications, increase this value to focus on more informative peptides"/>
      <param name="max_rt_shift" argument="-algorithm:max_rt_shift" type="float" optional="true" min="0.0" value="0.5" label="Maximum realistic RT difference for a peptide (median per run vs" help="reference). Peptides with higher shifts (outliers) are not used to compute the alignment.. If 0, no limit (disable filter); if &gt; 1, the final value in seconds; if &lt;= 1, taken as a fraction of the range of the reference RT scale"/>
      <param name="use_unassigned_peptides" argument="-algorithm:use_unassigned_peptides" type="boolean" truevalue="true" falsevalue="false" checked="true" label="Should unassigned peptide identifications be used when computing an alignment of feature or consensus maps" help="If 'false', only peptide IDs assigned to features will be used"/>
      <param name="use_feature_rt" argument="-algorithm:use_feature_rt" type="boolean" truevalue="true" falsevalue="false" checked="false" label="When aligning feature or consensus maps, don't use the retention time of a peptide identification directly; instead, use the retention time of the centroid of the feature (apex of the elution profile) that the peptide was matched to" help="If different identifications are matched to one feature, only the peptide closest to the centroid in RT is used.. Precludes 'use_unassigned_peptides'"/>
    </section>
    <section name="model" title="Options to control the modeling of retention time transformations from data" help="" expanded="false">
      <param name="type" argument="-model:type" display="radio" type="select" optional="false" label="Type of model" help="">
        <option value="linear">linear</option>
        <option value="b_spline" selected="true">b_spline</option>
        <option value="lowess">lowess</option>
        <option value="interpolated">interpolated</option>
        <expand macro="list_string_san"/>
      </param>
      <section name="linear" title="Parameters for 'linear' model" help="" expanded="false">
        <param name="symmetric_regression" argument="-model:linear:symmetric_regression" type="boolean" truevalue="true" falsevalue="false" checked="false" label="Perform linear regression on 'y - x' vs" help="'y + x', instead of on 'y' vs. 'x'"/>
        <param name="x_weight" argument="-model:linear:x_weight" display="radio" type="select" optional="true" label="Weight x values" help="">
          <option value="">default (nothing chosen)</option>
          <option value="1/x">1/x</option>
          <option value="1/x2">1/x2</option>
          <option value="ln(x)">ln(x)</option>
          <option value=""></option>
          <expand macro="list_string_san"/>
        </param>
        <param name="y_weight" argument="-model:linear:y_weight" display="radio" type="select" optional="true" label="Weight y values" help="">
          <option value="">default (nothing chosen)</option>
          <option value="1/y">1/y</option>
          <option value="1/y2">1/y2</option>
          <option value="ln(y)">ln(y)</option>
          <option value=""></option>
          <expand macro="list_string_san"/>
        </param>
        <param name="x_datum_min" argument="-model:linear:x_datum_min" type="float" optional="true" value="1e-15" label="Minimum x value" help=""/>
        <param name="x_datum_max" argument="-model:linear:x_datum_max" type="float" optional="true" value="1000000000000000.0" label="Maximum x value" help=""/>
        <param name="y_datum_min" argument="-model:linear:y_datum_min" type="float" optional="true" value="1e-15" label="Minimum y value" help=""/>
        <param name="y_datum_max" argument="-model:linear:y_datum_max" type="float" optional="true" value="1000000000000000.0" label="Maximum y value" help=""/>
      </section>
      <section name="b_spline" title="Parameters for 'b_spline' model" help="" expanded="false">
        <param name="wavelength" argument="-model:b_spline:wavelength" type="float" optional="true" min="0.0" value="0.0" label="Determines the amount of smoothing by setting the number of nodes for the B-spline" help="The number is chosen so that the spline approximates a low-pass filter with this cutoff wavelength. The wavelength is given in the same units as the data; a higher value means more smoothing. '0' sets the number of nodes to twice the number of input points"/>
        <param name="num_nodes" argument="-model:b_spline:num_nodes" type="integer" optional="true" min="0" value="5" label="Number of nodes for B-spline fitting" help="Overrides 'wavelength' if set (to two or greater). A lower value means more smoothing"/>
        <param name="extrapolate" argument="-model:b_spline:extrapolate" display="radio" type="select" optional="false" label="Method to use for extrapolation beyond the original data range" help="'linear': Linear extrapolation using the slope of the B-spline at the corresponding endpoint. 'b_spline': Use the B-spline (as for interpolation). 'constant': Use the constant value of the B-spline at the corresponding endpoint. 'global_linear': Use a linear fit through the data (which will most probably introduce discontinuities at the ends of the data range)">
          <option value="linear" selected="true">linear</option>
          <option value="b_spline">b_spline</option>
          <option value="constant">constant</option>
          <option value="global_linear">global_linear</option>
          <expand macro="list_string_san"/>
        </param>
        <param name="boundary_condition" argument="-model:b_spline:boundary_condition" type="integer" optional="true" min="0" max="2" value="2" label="Boundary condition at B-spline endpoints: 0 (value zero), 1 (first derivative zero) or 2 (second derivative zero)" help=""/>
      </section>
      <section name="lowess" title="Parameters for 'lowess' model" help="" expanded="false">
        <param name="span" argument="-model:lowess:span" type="float" optional="true" min="0.0" max="1.0" value="0.666666666666667" label="Fraction of datapoints (f) to use for each local regression (determines the amount of smoothing)" help="Choosing this parameter in the range .2 to .8 usually results in a good fit"/>
        <param name="num_iterations" argument="-model:lowess:num_iterations" type="integer" optional="true" min="0" value="3" label="Number of robustifying iterations for lowess fitting" help=""/>
        <param name="delta" argument="-model:lowess:delta" type="float" optional="true" value="-1.0" label="Nonnegative parameter which may be used to save computations (recommended value is 0.01 of the range of the input" help="e.g. for data ranging from 1000 seconds to 2000 seconds, it could be set to 10). Setting a negative value will automatically do this"/>
        <param name="interpolation_type" argument="-model:lowess:interpolation_type" display="radio" type="select" optional="false" label="Method to use for interpolation between datapoints computed by lowess" help="'linear': Linear interpolation. 'cspline': Use the cubic spline for interpolation. 'akima': Use an akima spline for interpolation">
          <option value="linear">linear</option>
          <option value="cspline" selected="true">cspline</option>
          <option value="akima">akima</option>
          <expand macro="list_string_san"/>
        </param>
        <param name="extrapolation_type" argument="-model:lowess:extrapolation_type" display="radio" type="select" optional="false" label="Method to use for extrapolation outside the data range" help="'two-point-linear': Uses a line through the first and last point to extrapolate. 'four-point-linear': Uses a line through the first and second point to extrapolate in front and and a line through the last and second-to-last point in the end. 'global-linear': Uses a linear regression to fit a line through all data points and use it for interpolation">
          <option value="two-point-linear">two-point-linear</option>
          <option value="four-point-linear" selected="true">four-point-linear</option>
          <option value="global-linear">global-linear</option>
          <expand macro="list_string_san"/>
        </param>
      </section>
      <section name="interpolated" title="Parameters for 'interpolated' model" help="" expanded="false">
        <param name="interpolation_type" argument="-model:interpolated:interpolation_type" display="radio" type="select" optional="false" label="Type of interpolation to apply" help="">
          <option value="linear">linear</option>
          <option value="cspline" selected="true">cspline</option>
          <option value="akima">akima</option>
          <expand macro="list_string_san"/>
        </param>
        <param name="extrapolation_type" argument="-model:interpolated:extrapolation_type" display="radio" type="select" optional="false" label="Type of extrapolation to apply: two-point-linear: use the first and last data point to build a single linear model, four-point-linear: build two linear models on both ends using the first two / last two points, global-linear: use all points to build a single linear model" help="Note that global-linear may not be continuous at the border">
          <option value="two-point-linear" selected="true">two-point-linear</option>
          <option value="four-point-linear">four-point-linear</option>
          <option value="global-linear">global-linear</option>
          <expand macro="list_string_san"/>
        </param>
      </section>
    </section>
    <expand macro="adv_opts_macro">
      <param name="force" argument="-force" type="boolean" truevalue="true" falsevalue="false" checked="false" label="Overwrite tool specific checks" help=""/>
      <param name="test" argument="-test" type="hidden" optional="true" value="False" label="Enables the test mode (needed for internal use only)" help="">
        <expand macro="list_string_san"/>
      </param>
    </expand>
    <param name="OPTIONAL_OUTPUTS" type="select" multiple="true" label="Optional outputs" optional="false">
      <option value="out_FLAG">out (Type of extrapolation to apply: two-point-linear: use the first and last data point to build a single linear model, four-point-linear: build two linear models on both ends using the first two / last two points, global-linear: use all points to build a single linear model)</option>
      <option value="trafo_out_FLAG">trafo_out (Type of extrapolation to apply: two-point-linear: use the first and last data point to build a single linear model, four-point-linear: build two linear models on both ends using the first two / last two points, global-linear: use all points to build a single linear model)</option>
      <option value="ctd_out_FLAG">Output used ctd (ini) configuration file</option>
    </param>
  </inputs>
  <outputs>
    <collection type="list" name="out" label="${tool.name} on ${on_string}: out">
      <discover_datasets directory="out" pattern="__name_and_ext__"/>
      <filter>OPTIONAL_OUTPUTS is not None and "out_FLAG" in OPTIONAL_OUTPUTS</filter>
    </collection>
    <collection type="list" name="trafo_out" label="${tool.name} on ${on_string}: trafo_out">
      <discover_datasets directory="trafo_out" format="trafoxml" pattern="__name__"/>
      <filter>OPTIONAL_OUTPUTS is not None and "trafo_out_FLAG" in OPTIONAL_OUTPUTS</filter>
    </collection>
    <data name="stdout" format="txt" label="${tool.name} on ${on_string}: stdout">
      <filter>OPTIONAL_OUTPUTS is None</filter>
    </data>
    <data name="ctd_out" format="xml" label="${tool.name} on ${on_string}: ctd">
      <filter>OPTIONAL_OUTPUTS is not None and "ctd_out_FLAG" in OPTIONAL_OUTPUTS</filter>
    </data>
  </outputs>
  <tests>
    <expand macro="autotest_MapAlignerIdentification"/>
    <expand macro="manutest_MapAlignerIdentification"/>
  </tests>
  <help><![CDATA[Corrects retention time distortions between maps based on common peptide identifications.


For more information, visit http://www.openms.de/documentation/TOPP_MapAlignerIdentification.html]]></help>
  <expand macro="references"/>
</tool>