<?xml version="1.0" encoding="UTF-8"?>
<tool ctdVersion="1.7" version="2.1.0" name="OpenSwathRTNormalizer" docurl="http://ftp.mi.fu-berlin.de/OpenMS/release-documentation/html/TOPP_OpenSwathRTNormalizer.html" category="Targeted Experiments" >
<description><![CDATA[This tool will take a description of RT peptides and their normalized retention time to write out a transformation file on how to transform the RT space into the normalized space.]]></description>
<manual><![CDATA[This tool will take a description of RT peptides and their normalized retention time to write out a transformation file on how to transform the RT space into the normalized space.]]></manual>
<PARAMETERS version="1.6.2" xsi:noNamespaceSchemaLocation="http://open-ms.sourceforge.net/schemas/Param_1_6_2.xsd" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance">
  <NODE name="OpenSwathRTNormalizer" description="This tool will take a description of RT peptides and their normalized retention time to write out a transformation file on how to transform the RT space into the normalized space.">
    <ITEM name="version" value="2.1.0" type="string" description="Version of the tool that generated this parameters file." required="false" advanced="true" />
    <NODE name="1" description="Instance &apos;1&apos; section for &apos;OpenSwathRTNormalizer&apos;">
      <ITEMLIST name="in" type="input-file" description="Input files separated by blank" required="true" advanced="false" supported_formats="*.mzML">
      </ITEMLIST>
      <ITEM name="tr" value="" type="input-file" description="transition file with the RT peptides (&apos;TraML&apos; or &apos;csv&apos;)" required="true" advanced="false" supported_formats="*.csv,*.traML" />
      <ITEM name="out" value="" type="output-file" description="output file" required="true" advanced="false" supported_formats="*.trafoXML" />
      <ITEM name="rt_norm" value="" type="input-file" description="RT normalization file (how to map the RTs of this run to the ones stored in the library)" required="false" advanced="false" supported_formats="*.trafoXML" />
      <ITEM name="min_rsq" value="0.95" type="double" description="Minimum r-squared of RT peptides regression" required="false" advanced="false" />
      <ITEM name="min_coverage" value="0.6" type="double" description="Minimum relative amount of RT peptides to keep" required="false" advanced="false" />
      <ITEM name="estimateBestPeptides" value="false" type="string" description="Whether the algorithms should try to choose the best peptides based on their peak shape for normalization. Use this option you do not expect all your peptides to be detected in a sample and too many &apos;bad&apos; peptides enter the outlier removal step (e.g. due to them being endogenous peptides or using a less curated list of peptides)." required="false" advanced="false" restrictions="true,false" />
      <ITEM name="log" value="" type="string" description="Name of log file (created only when specified)" required="false" advanced="true" />
      <ITEM name="debug" value="0" type="int" description="Sets the debug level" required="false" advanced="true" />
      <ITEM name="threads" value="1" type="int" description="Sets the number of threads allowed to be used by the TOPP tool" required="false" advanced="false" />
      <ITEM name="no_progress" value="false" type="string" description="Disables progress logging to command line" required="false" advanced="true" restrictions="true,false" />
      <ITEM name="force" value="false" type="string" description="Overwrite tool specific checks." required="false" advanced="true" restrictions="true,false" />
      <ITEM name="test" value="false" type="string" description="Enables the test mode (needed for internal use only)" required="false" advanced="true" restrictions="true,false" />
      <NODE name="algorithm" description="Algorithm parameters section">
        <ITEM name="stop_report_after_feature" value="-1" type="int" description="Stop reporting after feature (ordered by quality; -1 means do not stop)." required="false" advanced="false" />
        <ITEM name="rt_extraction_window" value="-1" type="double" description="Only extract RT around this value (-1 means extract over the whole range, a value of 500 means to extract around +/- 500 s of the expected elution). For this to work, the TraML input file needs to contain normalized RT values." required="false" advanced="false" />
        <ITEM name="rt_normalization_factor" value="1" type="double" description="The normalized RT is expected to be between 0 and 1. If your normalized RT has a different range, pass this here (e.g. it goes from 0 to 100, set this value to 100)" required="false" advanced="false" />
        <ITEM name="quantification_cutoff" value="0" type="double" description="Cutoff in m/z below which peaks should not be used for quantification any more" required="false" advanced="true" restrictions="0:" />
        <ITEM name="write_convex_hull" value="false" type="string" description="Whether to write out all points of all features into the featureXML" required="false" advanced="true" restrictions="true,false" />
        <ITEM name="add_up_spectra" value="1" type="int" description="Add up spectra around the peak apex (needs to be a non-even integer)" required="false" advanced="true" restrictions="1:" />
        <ITEM name="spacing_for_spectra_resampling" value="0.005" type="double" description="If spectra are to be added, use this spacing to add them up" required="false" advanced="true" restrictions="0:" />
        <ITEM name="uis_threshold_sn" value="-1" type="int" description="S/N threshold to consider identification transition (set to -1 to consider all)" required="false" advanced="false" />
        <ITEM name="uis_threshold_peak_area" value="0" type="int" description="Peak area threshold to consider identification transition (set to -1 to consider all)" required="false" advanced="false" />
        <NODE name="TransitionGroupPicker" description="">
          <ITEM name="stop_after_feature" value="-1" type="int" description="Stop finding after feature (ordered by intensity; -1 means do not stop)." required="false" advanced="false" />
          <ITEM name="stop_after_intensity_ratio" value="0.0001" type="double" description="Stop after reaching intensity ratio" required="false" advanced="false" />
          <ITEM name="min_peak_width" value="-1" type="double" description="Minimal peak width (s), discard all peaks below this value (-1 means no action)." required="false" advanced="true" />
          <ITEM name="background_subtraction" value="none" type="string" description="Try to apply a background subtraction to the peak (experimental). The background is estimated at the peak boundaries, either the smoothed or the raw chromatogram data can be used for that." required="false" advanced="true" restrictions="none,smoothed,original" />
          <ITEM name="recalculate_peaks" value="false" type="string" description="Tries to get better peak picking by looking at peak consistency of all picked peaks. Tries to use the consensus (median) peak border if theof variation within the picked peaks is too large." required="false" advanced="true" />
          <ITEM name="recalculate_peaks_max_z" value="1" type="double" description="Determines the maximal Z-Score (difference measured in standard deviations) that is considered too large for peak boundaries. If the Z-Score is above this value, the median is used for peak boundaries (default value 1.0)." required="false" advanced="true" />
          <ITEM name="minimal_quality" value="-10000" type="double" description="Only if compute_peak_quality is set, this parameter will not consider peaks below this quality threshold" required="false" advanced="true" />
          <ITEM name="compute_peak_quality" value="false" type="string" description="Tries to compute a quality value for each peakgroup and detect outlier transitions. The resulting score is centered around zero and values above 0 are generally good and below -1 or -2 are usually bad." required="false" advanced="true" />
          <NODE name="PeakPickerMRM" description="">
            <ITEM name="sgolay_frame_length" value="15" type="int" description="The number of subsequent data points used for smoothing.#br#This number has to be uneven. If it is not, 1 will be added." required="false" advanced="false" />
            <ITEM name="sgolay_polynomial_order" value="3" type="int" description="Order of the polynomial that is fitted." required="false" advanced="false" />
            <ITEM name="gauss_width" value="50" type="double" description="Gaussian width in seconds, estimated peak size." required="false" advanced="false" />
            <ITEM name="use_gauss" value="true" type="string" description="Use Gaussian filter for smoothing (alternative is Savitzky-Golay filter)" required="false" advanced="false" restrictions="false,true" />
            <ITEM name="peak_width" value="40" type="double" description="Force a certain minimal peak_width on the data (e.g. extend the peak at least by this amount on both sides) in seconds. -1 turns this feature off." required="false" advanced="false" />
            <ITEM name="signal_to_noise" value="1" type="double" description="Signal-to-noise threshold at which a peak will not be extended any more. Note that setting this too high (e.g. 1.0) can lead to peaks whose flanks are not fully captured." required="false" advanced="false" restrictions="0:" />
            <ITEM name="sn_win_len" value="1000" type="double" description="Signal to noise window length." required="false" advanced="false" />
            <ITEM name="sn_bin_count" value="30" type="int" description="Signal to noise bin count." required="false" advanced="false" />
            <ITEM name="write_sn_log_messages" value="true" type="string" description="Write out log messages of the signal-to-noise estimator in case of sparse windows or median in rightmost histogram bin" required="false" advanced="false" restrictions="true,false" />
            <ITEM name="remove_overlapping_peaks" value="false" type="string" description="Try to remove overlapping peaks during peak picking" required="false" advanced="false" restrictions="false,true" />
            <ITEM name="method" value="legacy" type="string" description="Which method to choose for chromatographic peak-picking (OpenSWATH legacy, corrected picking or Crawdad)." required="false" advanced="false" restrictions="legacy,corrected,crawdad" />
          </NODE>
        </NODE>
        <NODE name="DIAScoring" description="">
          <ITEM name="dia_extraction_window" value="0.05" type="double" description="DIA extraction window in Th." required="false" advanced="false" restrictions="0:" />
          <ITEM name="dia_centroided" value="false" type="string" description="Use centroded DIA data." required="false" advanced="false" restrictions="true,false" />
          <ITEM name="dia_byseries_intensity_min" value="300" type="double" description="DIA b/y series minimum intensity to consider." required="false" advanced="false" restrictions="0:" />
          <ITEM name="dia_byseries_ppm_diff" value="10" type="double" description="DIA b/y series minimal difference in ppm to consider." required="false" advanced="false" restrictions="0:" />
          <ITEM name="dia_nr_isotopes" value="4" type="int" description="DIA nr of isotopes to consider." required="false" advanced="false" restrictions="0:" />
          <ITEM name="dia_nr_charges" value="4" type="int" description="DIA nr of charges to consider." required="false" advanced="false" restrictions="0:" />
          <ITEM name="peak_before_mono_max_ppm_diff" value="20" type="double" description="DIA maximal difference in ppm to count a peak at lower m/z when searching for evidence that a peak might not be monoisotopic." required="false" advanced="false" restrictions="0:" />
        </NODE>
        <NODE name="EMGScoring" description="">
          <ITEM name="interpolation_step" value="0.2" type="double" description="Sampling rate for the interpolation of the model function." required="false" advanced="true" />
          <ITEM name="tolerance_stdev_bounding_box" value="3" type="double" description="Bounding box has range [minimim of data, maximum of data] enlarged by tolerance_stdev_bounding_box times the standard deviation of the data." required="false" advanced="true" />
          <ITEM name="max_iteration" value="500" type="int" description="Maximum number of iterations using by Levenberg-Marquardt algorithm." required="false" advanced="true" />
          <NODE name="statistics" description="">
            <ITEM name="mean" value="1" type="double" description="Centroid position of the model." required="false" advanced="true" />
            <ITEM name="variance" value="1" type="double" description="Variance of the model." required="false" advanced="true" />
          </NODE>
        </NODE>
        <NODE name="Scores" description="">
          <ITEM name="use_shape_score" value="true" type="string" description="Use the shape score (this score measures the similarity in shape of the transitions using a cross-correlation)" required="false" advanced="true" restrictions="true,false" />
          <ITEM name="use_coelution_score" value="true" type="string" description="Use the coelution score (this score measures the similarity in coelution of the transitions using a cross-correlation)" required="false" advanced="true" restrictions="true,false" />
          <ITEM name="use_rt_score" value="true" type="string" description="Use the retention time score (this score measure the difference in retention time)" required="false" advanced="true" restrictions="true,false" />
          <ITEM name="use_library_score" value="true" type="string" description="Use the library score" required="false" advanced="true" restrictions="true,false" />
          <ITEM name="use_elution_model_score" value="true" type="string" description="Use the elution model (EMG) score (this score fits a gaussian model to the peak and checks the fit)" required="false" advanced="true" restrictions="true,false" />
          <ITEM name="use_intensity_score" value="true" type="string" description="Use the intensity score" required="false" advanced="true" restrictions="true,false" />
          <ITEM name="use_nr_peaks_score" value="true" type="string" description="Use the number of peaks score" required="false" advanced="true" restrictions="true,false" />
          <ITEM name="use_total_xic_score" value="true" type="string" description="Use the total XIC score" required="false" advanced="true" restrictions="true,false" />
          <ITEM name="use_sn_score" value="true" type="string" description="Use the SN (signal to noise) score" required="false" advanced="true" restrictions="true,false" />
          <ITEM name="use_dia_scores" value="true" type="string" description="Use the DIA (SWATH) scores" required="false" advanced="true" restrictions="true,false" />
          <ITEM name="use_ms1_correlation" value="false" type="string" description="Use the correlation scores with the MS1 elution profiles" required="false" advanced="true" restrictions="true,false" />
          <ITEM name="use_ms1_fullscan" value="false" type="string" description="Use the full MS1 scan at the peak apex for scoring (ppm accuracy of precursor and isotopic pattern)" required="false" advanced="true" restrictions="true,false" />
          <ITEM name="use_uis_scores" value="false" type="string" description="Use UIS scores for peptidoform identification " required="false" advanced="true" restrictions="true,false" />
        </NODE>
      </NODE>
      <NODE name="outlierDetection" description="Parameters for the outlierDetection. Outlier detection can be done iteratively (by default) which removes one outlier per iteration or using the RANSAC algorithm.">
        <ITEM name="outlierMethod" value="iter_residual" type="string" description="Which outlier detection method to use (valid: &apos;iter_residual&apos;, &apos;iter_jackknife&apos;, &apos;ransac&apos;, &apos;none&apos;). Iterative methods remove one outlier at a time. Jackknife approach optimizes for maximum r-squared improvement while &apos;iter_residual&apos; removes the datapoint with the largest residual error (removal by residual is computationally cheaper, use this with lots of peptides)." required="false" advanced="false" restrictions="iter_residual,iter_jackknife,ransac,none" />
        <ITEM name="useIterativeChauvenet" value="false" type="string" description="Whether to use Chauvenet&apos;s criterion when using iterative methods. This should be used if the algorithm removes too many datapoints but it may lead to true outliers being retained." required="false" advanced="false" restrictions="true,false" />
        <ITEM name="RANSACMaxIterations" value="1000" type="int" description="Maximum iterations for the RANSAC outlier detection algorithm." required="false" advanced="false" />
        <ITEM name="RANSACMaxPercentRTThreshold" value="3" type="int" description="Maximum threshold in RT dimension for the RANSAC outlier detection algorithm (in percent of the total gradient). Default is set to 3% which is around +/- 4 minutes on a 120 gradient." required="false" advanced="false" />
        <ITEM name="RANSACSamplingSize" value="10" type="int" description="Sampling size of data points per iteration for the RANSAC outlier detection algorithm." required="false" advanced="false" />
      </NODE>
      <NODE name="peptideEstimation" description="Parameters for the peptide estimation (use -estimateBestPeptides to enable).">
        <ITEM name="InitialQualityCutoff" value="0.5" type="double" description="The initial overall quality cutoff for a peak to be scored (range ca. -2 to 2)" required="false" advanced="false" />
        <ITEM name="OverallQualityCutoff" value="5.5" type="double" description="The overall quality cutoff for a peak to go into the retention time estimation (range ca. 0 to 10)" required="false" advanced="false" />
        <ITEM name="NrRTBins" value="10" type="int" description="Number of RT bins to use to compute coverage. This option should be used to ensure that there is a complete coverage of the RT space (this should detect cases where only a part of the RT gradient is actually covered by normalization peptides)" required="false" advanced="false" />
        <ITEM name="MinPeptidesPerBin" value="1" type="int" description="Minimal number of peptides that are required for a bin to counted as &apos;covered&apos;" required="false" advanced="false" />
        <ITEM name="MinBinsFilled" value="8" type="int" description="Minimal number of bins required to be covered" required="false" advanced="false" />
      </NODE>
    </NODE>
  </NODE>
</PARAMETERS>
</tool>
