<?xml version="1.0" encoding="UTF-8"?>
<tool ctdVersion="1.7" version="2.1.0" name="MapAlignerSpectrum" docurl="http://ftp.mi.fu-berlin.de/OpenMS/release-documentation/html/TOPP_MapAlignerSpectrum.html" category="Map Alignment" >
<description><![CDATA[Corrects retention time distortions between maps by spectrum alignment.]]></description>
<manual><![CDATA[Corrects retention time distortions between maps by spectrum alignment.]]></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="MapAlignerSpectrum" description="Corrects retention time distortions between maps by spectrum alignment.">
    <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;MapAlignerSpectrum&apos;">
      <ITEMLIST name="in" type="input-file" description="Input files to align (all must have the same file type)" required="true" advanced="false" supported_formats="*.mzML">
      </ITEMLIST>
      <ITEMLIST name="out" type="output-file" description="Output files (same file type as &apos;in&apos;). Either this option or &apos;trafo_out&apos; has to be provided; they can be used together." required="false" advanced="false" supported_formats="*.mzML">
      </ITEMLIST>
      <ITEMLIST name="trafo_out" type="output-file" description="Transformation output files. Either this option or &apos;out&apos; has to be provided; they can be used together." required="false" advanced="false" supported_formats="*.trafoXML">
      </ITEMLIST>
      <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="gapcost" value="1" type="double" description="This Parameter stands for the cost of opining a gap in the Alignment. A gap means that one spectrum can not be aligned directly to another spectrum in the Map. This happens, when the similarity of both spectra a too low or even not present. Imagine it as a insert or delete of the spectrum in the map (similar to sequence alignment). The gap is necessary for aligning, if we open a gap there is a possibility that an another spectrum can be correct aligned with a higher score as before without gap. But to open a gap is a negative event and needs to carry a punishment, so a gap should only be opened if the benefits outweigh the downsides. The Parameter is to giving as a positive number, the implementation convert it to a negative number." required="false" advanced="false" restrictions="0:" />
        <ITEM name="affinegapcost" value="0.5" type="double" description="This Parameter controls the cost of extension a already open gap. The idea behind the affine gapcost lies under the assumption, that it is better to get a long distance of connected gaps than to have a structure of gaps interspersed with matches (gap match gap match etc.).  Therefor the punishment for the extension of a gap generally should be lower than the normal gapcost. If the result of the alignment shows high compression, it is a good idea to lower either the affine gapcost or gap opening cost." required="false" advanced="false" restrictions="0:" />
        <ITEM name="cutoff_score" value="0.7" type="double" description="The Parameter defines the threshold which filtered spectra, these spectra are high potential candidate for deciding the interval of a sub-alignment.  Only those pair of spectra are selected, which has a score higher or same of the threshold." required="false" advanced="true" restrictions="0:1" />
        <ITEM name="bucketsize" value="100" type="int" description="Defines the numbers of buckets. It is a quantize of the interval of those points, which defines the main alignment (match points). These points have to filtered, to reduce the amount of points for the calculating a smoother spline curve." required="false" advanced="true" restrictions="1:" />
        <ITEM name="anchorpoints" value="100" type="int" description="Defines the percent of numbers of match points which a selected from one bucket. The high score pairs are previously selected. The reduction of match points helps to get a smoother spline curve." required="false" advanced="true" restrictions="1:100" />
        <ITEM name="debug" value="false" type="string" description="Activate the debug mode, there a files written starting with debug prefix." required="false" advanced="true" restrictions="true,false" />
        <ITEM name="mismatchscore" value="-5" type="double" description="Defines the score of two spectra if they have no similarity to each other. " required="false" advanced="true" restrictions=":0" />
        <ITEM name="scorefunction" value="SteinScottImproveScore" type="string" description="The score function is the core of an alignment. The success of an alignment depends mostly of the elected score function. The score function return the similarity of two spectra. The score influence defines later the way of possible traceback. There are multiple spectra similarity scores available.." required="false" advanced="false" restrictions="SteinScottImproveScore,ZhangSimilarityScore" />
      </NODE>
      <NODE name="model" description="Options to control the modeling of retention time transformations from data">
        <ITEM name="type" value="interpolated" type="string" description="Type of model" required="false" advanced="false" restrictions="linear,b_spline,lowess,interpolated" />
        <NODE name="linear" description="Parameters for &apos;linear&apos; model">
          <ITEM name="symmetric_regression" value="false" type="string" description="Perform linear regression on &apos;y - x&apos; vs. &apos;y + x&apos;, instead of on &apos;y&apos; vs. &apos;x&apos;." required="false" advanced="false" restrictions="true,false" />
        </NODE>
        <NODE name="b_spline" description="Parameters for &apos;b_spline&apos; model">
          <ITEM name="wavelength" value="0" type="double" description="Determines the amount of smoothing by setting the number of nodes for the B-spline. 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. &apos;0&apos; sets the number of nodes to twice the number of input points." required="false" advanced="false" restrictions="0:" />
          <ITEM name="num_nodes" value="5" type="int" description="Number of nodes for B-spline fitting. Overrides &apos;wavelength&apos; if set (to two or greater). A lower value means more smoothing." required="false" advanced="false" restrictions="0:" />
          <ITEM name="extrapolate" value="linear" type="string" description="Method to use for extrapolation beyond the original data range. &apos;linear&apos;: Linear extrapolation using the slope of the B-spline at the corresponding endpoint. &apos;b_spline&apos;: Use the B-spline (as for interpolation). &apos;constant&apos;: Use the constant value of the B-spline at the corresponding endpoint. &apos;global_linear&apos;: Use a linear fit through the data (which will most probably introduce discontinuities at the ends of the data range)." required="false" advanced="false" restrictions="linear,b_spline,constant,global_linear" />
          <ITEM name="boundary_condition" value="2" type="int" description="Boundary condition at B-spline endpoints: 0 (value zero), 1 (first derivative zero) or 2 (second derivative zero)" required="false" advanced="false" restrictions="0:2" />
        </NODE>
        <NODE name="lowess" description="Parameters for &apos;lowess&apos; model">
          <ITEM name="span" value="0.666666666666667" type="double" description="Fraction of datapoints (f) to use for each local regression (determines the amount of smoothing). Choosing this parameter in the range .2 to .8 usually results in a good fit." required="false" advanced="false" restrictions="0:1" />
          <ITEM name="num_iterations" value="3" type="int" description="Number of robustifying iterations for lowess fitting." required="false" advanced="false" restrictions="0:" />
          <ITEM name="delta" value="-1" type="double" description="Nonnegative parameter which may be used to save computations (recommended value is 0.01 of the range of the input, 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." required="false" advanced="false" />
          <ITEM name="interpolation_type" value="cspline" type="string" description="Method to use for interpolation between datapoints computed by lowess. &apos;linear&apos;: Linear interpolation. &apos;cspline&apos;: Use the cubic spline for interpolation. &apos;akima&apos;: Use an akima spline for interpolation" required="false" advanced="false" restrictions="linear,cspline,akima" />
          <ITEM name="extrapolation_type" value="four-point-linear" type="string" description="Method to use for extrapolation outside the data range. &apos;two-point-linear&apos;: Uses a line through the first and last point to extrapolate. &apos;four-point-linear&apos;: 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. &apos;global-linear&apos;: Uses a linear regression to fit a line through all data points and use it for interpolation." required="false" advanced="false" restrictions="two-point-linear,four-point-linear,global-linear" />
        </NODE>
        <NODE name="interpolated" description="Parameters for &apos;interpolated&apos; model">
          <ITEM name="interpolation_type" value="cspline" type="string" description="Type of interpolation to apply." required="false" advanced="false" restrictions="linear,cspline,akima" />
          <ITEM name="extrapolation_type" value="two-point-linear" type="string" description="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. Note that global-linear may not be continuous at the border." required="false" advanced="false" restrictions="two-point-linear,four-point-linear,global-linear" />
        </NODE>
      </NODE>
    </NODE>
  </NODE>
</PARAMETERS>
</tool>
