annotate MapAlignerPoseClustering.xml @ 2:304c13ce9577 draft

planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/openms commit 58476cadaaf10b494317a604ad81d41c2d15f29b

<?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="MapAlignerPoseClustering" name="MapAlignerPoseClustering" version="2.3.0">
  <description>Corrects retention time distortions between maps using a pose clustering approach.</description>
  <macros>
    <token name="@EXECUTABLE@">MapAlignerPoseClustering</token>
    <import>macros.xml</import>
  </macros>
  <expand macro="references"/>
  <expand macro="stdio"/>
  <expand macro="requirements"/>
  <command><![CDATA[

  mkdir -p ./results_trafoxml ./results_out &&
  MapAlignerPoseClustering

-in
#for $infile in $param_in:
    '$infile'
#end for

-out
#for $counter,$infile in enumerate($param_in):
    ./results_out/${infile.element_identifier}.${infile.extension}
#end for

-trafo_out
#for $counter,$infile in enumerate($param_in):
    ./results_trafoxml/${infile.element_identifier}.trafoxml
#end for

#if $param_reference_file:
  -reference:file $param_reference_file
#end if
#if $param_reference_index:
  -reference:index $param_reference_index
#end if
#if $param_algorithm_max_num_peaks_considered:
  -algorithm:max_num_peaks_considered $param_algorithm_max_num_peaks_considered
#end if
#if $param_algorithm_superimposer_mz_pair_max_distance:
  -algorithm:superimposer:mz_pair_max_distance $param_algorithm_superimposer_mz_pair_max_distance
#end if
#if $param_algorithm_superimposer_num_used_points:
  -algorithm:superimposer:num_used_points $param_algorithm_superimposer_num_used_points
#end if
#if $param_algorithm_superimposer_scaling_bucket_size:
  -algorithm:superimposer:scaling_bucket_size $param_algorithm_superimposer_scaling_bucket_size
#end if
#if $param_algorithm_superimposer_shift_bucket_size:
  -algorithm:superimposer:shift_bucket_size $param_algorithm_superimposer_shift_bucket_size
#end if
#if $param_algorithm_pairfinder_second_nearest_gap:
  -algorithm:pairfinder:second_nearest_gap $param_algorithm_pairfinder_second_nearest_gap
#end if
#if $param_algorithm_pairfinder_use_identifications:
  -algorithm:pairfinder:use_identifications
#end if
#if $param_algorithm_pairfinder_ignore_charge:
  -algorithm:pairfinder:ignore_charge
#end if
#if $param_algorithm_pairfinder_distance_RT_max_difference:
  -algorithm:pairfinder:distance_RT:max_difference $param_algorithm_pairfinder_distance_RT_max_difference
#end if
#if $param_algorithm_pairfinder_distance_MZ_max_difference:
  -algorithm:pairfinder:distance_MZ:max_difference $param_algorithm_pairfinder_distance_MZ_max_difference
#end if
#if $param_algorithm_pairfinder_distance_MZ_unit:
  -algorithm:pairfinder:distance_MZ:unit
  #if " " in str($param_algorithm_pairfinder_distance_MZ_unit):
    "$param_algorithm_pairfinder_distance_MZ_unit"
  #else
    $param_algorithm_pairfinder_distance_MZ_unit
  #end if
#end if
#if $adv_opts.adv_opts_selector=='advanced':
    #if $adv_opts.param_force:
  -force
#end if
    #if $adv_opts.param_algorithm_superimposer_rt_pair_distance_fraction:
  -algorithm:superimposer:rt_pair_distance_fraction $adv_opts.param_algorithm_superimposer_rt_pair_distance_fraction
#end if
    #if $adv_opts.param_algorithm_superimposer_max_shift:
  -algorithm:superimposer:max_shift $adv_opts.param_algorithm_superimposer_max_shift
#end if
    #if $adv_opts.param_algorithm_superimposer_max_scaling:
  -algorithm:superimposer:max_scaling $adv_opts.param_algorithm_superimposer_max_scaling
#end if
    #if $adv_opts.param_algorithm_superimposer_dump_buckets:
  -algorithm:superimposer:dump_buckets     "$adv_opts.param_algorithm_superimposer_dump_buckets"
#end if
    #if $adv_opts.param_algorithm_superimposer_dump_pairs:
  -algorithm:superimposer:dump_pairs     "$adv_opts.param_algorithm_superimposer_dump_pairs"
#end if
    #if $adv_opts.param_algorithm_pairfinder_distance_RT_exponent:
  -algorithm:pairfinder:distance_RT:exponent $adv_opts.param_algorithm_pairfinder_distance_RT_exponent
#end if
    #if $adv_opts.param_algorithm_pairfinder_distance_RT_weight:
  -algorithm:pairfinder:distance_RT:weight $adv_opts.param_algorithm_pairfinder_distance_RT_weight
#end if
    #if $adv_opts.param_algorithm_pairfinder_distance_MZ_exponent:
  -algorithm:pairfinder:distance_MZ:exponent $adv_opts.param_algorithm_pairfinder_distance_MZ_exponent
#end if
    #if $adv_opts.param_algorithm_pairfinder_distance_MZ_weight:
  -algorithm:pairfinder:distance_MZ:weight $adv_opts.param_algorithm_pairfinder_distance_MZ_weight
#end if
    #if $adv_opts.param_algorithm_pairfinder_distance_intensity_exponent:
  -algorithm:pairfinder:distance_intensity:exponent $adv_opts.param_algorithm_pairfinder_distance_intensity_exponent
#end if
    #if $adv_opts.param_algorithm_pairfinder_distance_intensity_weight:
  -algorithm:pairfinder:distance_intensity:weight $adv_opts.param_algorithm_pairfinder_distance_intensity_weight
#end if
    #if $adv_opts.param_algorithm_pairfinder_distance_intensity_log_transform:
  -algorithm:pairfinder:distance_intensity:log_transform
  #if " " in str($adv_opts.param_algorithm_pairfinder_distance_intensity_log_transform):
    "$adv_opts.param_algorithm_pairfinder_distance_intensity_log_transform"
  #else
    $adv_opts.param_algorithm_pairfinder_distance_intensity_log_transform
  #end if
#end if
#end if
 ]]>
</command>
  <inputs>
    <param name="param_in" type="data" format="mzML,featureXML" multiple="true" label="Input files to align (all must have the same file type)" help="(-in) "/>
    <param name="param_reference_file" type="data" format="mzML,featureXML" optional="True" label="File to use as reference (same file format as input files required)" help="(-file) "/>
    <param name="param_reference_index" type="integer" min="0" optional="True" value="0" label="Use one of the input files as reference ('1' for the first file, etc.)" help="(-index) &lt;br&gt;If '0', no explicit reference is set - the algorithm will select a reference"/>
    <param name="param_algorithm_max_num_peaks_considered" type="integer" min="-1" optional="True" value="1000" label="The maximal number of peaks/features to be considered per map" help="(-max_num_peaks_considered) To use all, set to '-1'"/>
    <param name="param_algorithm_superimposer_mz_pair_max_distance" type="float" min="0.0" optional="True" value="0.5" label="Maximum of m/z deviation of corresponding elements in different maps" help="(-mz_pair_max_distance)  This condition applies to the pairs considered in hashing"/>
    <param name="param_algorithm_superimposer_num_used_points" type="integer" min="-1" optional="True" value="2000" label="Maximum number of elements considered in each map (selected by intensity)" help="(-num_used_points)  Use this to reduce the running time and to disregard weak signals during alignment.  For using all points, set this to -1"/>
    <param name="param_algorithm_superimposer_scaling_bucket_size" type="float" min="0.0" optional="True" value="0.005" label="The scaling of the retention time interval is being hashed into buckets of this size during pose clustering" help="(-scaling_bucket_size)  A good choice for this would be a bit smaller than the error you would expect from repeated runs"/>
    <param name="param_algorithm_superimposer_shift_bucket_size" type="float" min="0.0" optional="True" value="3.0" label="The shift at the lower (respectively, higher) end of the retention time interval is being hashed into buckets of this size during pose clustering" help="(-shift_bucket_size)  A good choice for this would be about the time between consecutive MS scans"/>
    <param name="param_algorithm_pairfinder_second_nearest_gap" type="float" min="1.0" optional="True" value="2.0" label="Only link features whose distance to the second nearest neighbors (for both sides) is larger by 'second_nearest_gap' than the distance between the matched pair itself" help="(-second_nearest_gap) "/>
    <param name="param_algorithm_pairfinder_use_identifications" display="radio" type="boolean" truevalue="-algorithm:pairfinder:use_identifications" falsevalue="" checked="false" optional="True" label="Never link features that are annotated with different peptides (features without ID's always match; only the best hit per peptide identification is considered)" help="(-use_identifications) "/>
    <param name="param_algorithm_pairfinder_ignore_charge" display="radio" type="boolean" truevalue="-algorithm:pairfinder:ignore_charge" falsevalue="" checked="false" optional="True" label="false [default]: pairing requires equal charge state (or at least one unknown charge '0'); true: Pairing irrespective of charge state" help="(-ignore_charge) "/>
    <param name="param_algorithm_pairfinder_distance_RT_max_difference" type="float" min="0.0" optional="True" value="100.0" label="Never pair features with a larger RT distance (in seconds)" help="(-max_difference) "/>
    <param name="param_algorithm_pairfinder_distance_MZ_max_difference" type="float" min="0.0" optional="True" value="0.3" label="Never pair features with larger m/z distance (unit defined by 'unit')" help="(-max_difference) "/>
    <param name="param_algorithm_pairfinder_distance_MZ_unit" display="radio" type="select" optional="False" value="Da" label="Unit of the 'max_difference' paramete" help="(-unit) ">
      <option value="Da" selected="true">Da</option>
      <option value="ppm">ppm</option>
    </param>
    <expand macro="advanced_options">
      <param name="param_force" display="radio" type="boolean" truevalue="-force" falsevalue="" checked="false" optional="True" label="Overwrite tool specific checks" help="(-force) "/>
      <param name="param_algorithm_superimposer_rt_pair_distance_fraction" type="float" min="0.0" max="1.0" optional="True" value="0.1" label="Within each of the two maps, the pairs considered for pose clustering must be separated by at least this fraction of the total elution time interval (i.e., max - min)" help="(-rt_pair_distance_fraction)  "/>
      <param name="param_algorithm_superimposer_max_shift" type="float" min="0.0" optional="True" value="1000.0" label="Maximal shift which is considered during histogramming (in seconds)" help="(-max_shift)  This applies for both directions"/>
      <param name="param_algorithm_superimposer_max_scaling" type="float" min="1.0" optional="True" value="2.0" label="Maximal scaling which is considered during histogramming" help="(-max_scaling)  The minimal scaling is the reciprocal of this"/>
      <param name="param_algorithm_superimposer_dump_buckets" type="text" size="30" label="[DEBUG] If non-empty, base filename where hash table buckets will be dumped to" help="(-dump_buckets)  A serial number for each invocation will be appended automatically">
        <sanitizer>
          <valid initial="string.printable">
            <remove value="'"/>
            <remove value="&quot;"/>
          </valid>
        </sanitizer>
      </param>
      <param name="param_algorithm_superimposer_dump_pairs" type="text" size="30" label="[DEBUG] If non-empty, base filename where the individual hashed pairs will be dumped to (large!)" help="(-dump_pairs)  A serial number for each invocation will be appended automatically">
        <sanitizer>
          <valid initial="string.printable">
            <remove value="'"/>
            <remove value="&quot;"/>
          </valid>
        </sanitizer>
      </param>
      <param name="param_algorithm_pairfinder_distance_RT_exponent" type="float" min="0.0" optional="True" value="1.0" label="Normalized RT differences ([0-1], relative to 'max_difference') are raised to this power (using 1 or 2 will be fast, everything else is REALLY slow)" help="(-exponent) "/>
      <param name="param_algorithm_pairfinder_distance_RT_weight" type="float" min="0.0" optional="True" value="1.0" label="Final RT distances are weighted by this facto" help="(-weight) "/>
      <param name="param_algorithm_pairfinder_distance_MZ_exponent" type="float" min="0.0" optional="True" value="2.0" label="Normalized ([0-1], relative to 'max_difference') m/z differences are raised to this power (using 1 or 2 will be fast, everything else is REALLY slow)" help="(-exponent) "/>
      <param name="param_algorithm_pairfinder_distance_MZ_weight" type="float" min="0.0" optional="True" value="1.0" label="Final m/z distances are weighted by this facto" help="(-weight) "/>
      <param name="param_algorithm_pairfinder_distance_intensity_exponent" type="float" min="0.0" optional="True" value="1.0" label="Differences in relative intensity ([0-1]) are raised to this power (using 1 or 2 will be fast, everything else is REALLY slow)" help="(-exponent) "/>
      <param name="param_algorithm_pairfinder_distance_intensity_weight" type="float" min="0.0" optional="True" value="0.0" label="Final intensity distances are weighted by this facto" help="(-weight) "/>
      <param name="param_algorithm_pairfinder_distance_intensity_log_transform" display="radio" type="select" optional="False" value="disabled" label="Log-transform intensities?" help="(-log_transform) If disabled, d = |int_f2 - int_f1| / int_max. If enabled, d = |log(int_f2 + 1) - log(int_f1 + 1)| / log(int_max + 1))">
        <option value="enabled">enabled</option>
        <option value="disabled" selected="true">disabled</option>
      </param>
    </expand>
    </inputs>
    <outputs>
        <collection name="out" type="list">
            <discover_datasets pattern="__designation_and_ext__" directory="results_out"/>
        </collection>

        <collection name="trafo_out" type="list">
            <discover_datasets pattern="__designation_and_ext__" directory="results_trafoxml"/>
        </collection>
    </outputs>
    <help>Corrects retention time distortions between maps using a pose clustering approach.

For more information, visit http://ftp.mi.fu-berlin.de/OpenMS/release-documentation/html/TOPP_MapAlignerPoseClustering.html</help>
</tool>