view PTModel.xml @ 1:17e8c91b70d5 draft

Uploaded

<?xml version='1.0' encoding='UTF-8'?>
<tool id="PTModel" name="PTModel" version="1.12.0">
  <description>Trains a model for the prediction of proteotypic peptides from a training set.</description>
  <macros>
    <token name="@EXECUTABLE@">PTModel</token>
    <import>macros.xml</import>
  </macros>
  <expand macro="stdio"/>
  <expand macro="requirements"/>
  <command>PTModel

-in_positive ${param_in_positive}
-in_negative ${param_in_negative}
-out ${param_out}
-c ${param_c}
-svm_type ${param_svm_type}
-nu ${param_nu}
-kernel_type ${param_kernel_type}
-degree ${param_degree}
-border_length ${param_border_length}
-k_mer_length ${param_k_mer_length}
-sigma ${param_sigma}
-max_positive_count ${param_max_positive_count}
-max_negative_count ${param_max_negative_count}
${param_redundant}
${param_additive_cv}
-threads \${GALAXY_SLOTS:-24} 
${param_skip_cv}
-cv:number_of_runs ${param_number_of_runs}
-cv:number_of_partitions ${param_number_of_partitions}
-cv:degree_start ${param_degree_start}
-cv:degree_step_size ${param_degree_step_size}
-cv:degree_stop ${param_degree_stop}
-cv:c_start ${param_c_start}
-cv:c_step_size ${param_c_step_size}
-cv:c_stop ${param_c_stop}
-cv:nu_start ${param_nu_start}
-cv:nu_step_size ${param_nu_step_size}
-cv:nu_stop ${param_nu_stop}
-cv:sigma_start ${param_sigma_start}
-cv:sigma_step_size ${param_sigma_step_size}
-cv:sigma_stop ${param_sigma_stop}
</command>
  <inputs>
    <param name="param_in_positive" type="data" format="idXML" optional="False" label="input file with positive examples" help="(-in_positive)"/>
    <param name="param_in_negative" type="data" format="idXML" optional="False" label="input file with negative examples" help="(-in_negative)"/>
    <param name="param_c" type="float" value="1.0" label="the penalty parameter of the svm" help="(-c)"/>
    <param name="param_svm_type" type="select" optional="True" value="C_SVC" label="the type of the svm (NU_SVC or C_SVC)" help="(-svm_type)">
      <option value="NU_SVC">NU_SVC</option>
      <option value="C_SVC">C_SVC</option>
    </param>
    <param name="param_nu" type="float" min="0.0" max="1.0" optional="True" value="0.5" label="the nu parameter [0..1] of the svm (for nu-SVR)" help="(-nu)"/>
    <param name="param_kernel_type" type="select" optional="True" value="OLIGO" label="the kernel type of the svm" help="(-kernel_type)">
      <option value="LINEAR">LINEAR</option>
      <option value="RBF">RBF</option>
      <option value="POLY">POLY</option>
      <option value="OLIGO">OLIGO</option>
    </param>
    <param name="param_degree" type="integer" min="1" optional="True" value="1" label="the degree parameter of the kernel function of the svm (POLY kernel)" help="(-degree)"/>
    <param name="param_border_length" type="integer" min="1" optional="True" value="22" label="length of the POBK" help="(-border_length)"/>
    <param name="param_k_mer_length" type="integer" min="1" optional="True" value="1" label="k_mer length of the POBK" help="(-k_mer_length)"/>
    <param name="param_sigma" type="float" value="5.0" label="sigma of the POBK" help="(-sigma)"/>
    <param name="param_max_positive_count" type="integer" min="1" optional="True" value="1000" label="quantity of positive samples for training (randomly chosen if smaller than available quantity)" help="(-max_positive_count)"/>
    <param name="param_max_negative_count" type="integer" min="1" optional="True" value="1000" label="quantity of positive samples for training (randomly chosen if smaller than available quantity)" help="(-max_negative_count)"/>
    <param name="param_redundant" type="boolean" truevalue="-redundant true" falsevalue="-redundant false" checked="false" optional="True" label="if the input sets are redundant and the redundant peptides should occur more than once in the training set, this flag has to be set" help="(-redundant)"/>
    <param name="param_additive_cv" type="boolean" truevalue="-additive_cv true" falsevalue="-additive_cv false" checked="false" optional="True" label="if the step sizes should be interpreted additively (otherwise the actual value is multiplied with the step size to get the new value" help="(-additive_cv)"/>
    <param name="param_skip_cv" type="boolean" truevalue="-cv:skip_cv true" falsevalue="-cv:skip_cv false" checked="false" optional="True" label="Has to be set if the cv should be skipped and the model should just be trained with the specified parameters." help="(-skip_cv)"/>
    <param name="param_number_of_runs" type="integer" min="1" optional="True" value="10" label="number of runs for the CV" help="(-number_of_runs)"/>
    <param name="param_number_of_partitions" type="integer" min="2" optional="True" value="10" label="number of CV partitions" help="(-number_of_partitions)"/>
    <param name="param_degree_start" type="integer" min="1" optional="True" value="1" label="starting point of degree" help="(-degree_start)"/>
    <param name="param_degree_step_size" type="integer" value="2" label="step size point of degree" help="(-degree_step_size)"/>
    <param name="param_degree_stop" type="integer" value="4" label="stopping point of degree" help="(-degree_stop)"/>
    <param name="param_c_start" type="float" value="1.0" label="starting point of c" help="(-c_start)"/>
    <param name="param_c_step_size" type="float" value="100.0" label="step size of c" help="(-c_step_size)"/>
    <param name="param_c_stop" type="float" value="1000.0" label="stopping point of c" help="(-c_stop)"/>
    <param name="param_nu_start" type="float" min="0.0" max="1.0" optional="True" value="0.1" label="starting point of nu" help="(-nu_start)"/>
    <param name="param_nu_step_size" type="float" value="1.3" label="step size of nu" help="(-nu_step_size)"/>
    <param name="param_nu_stop" type="float" min="0.0" max="1.0" optional="True" value="0.9" label="stopping point of nu" help="(-nu_stop)"/>
    <param name="param_sigma_start" type="float" value="1.0" label="starting point of sigma" help="(-sigma_start)"/>
    <param name="param_sigma_step_size" type="float" value="1.3" label="step size of sigma" help="(-sigma_step_size)"/>
    <param name="param_sigma_stop" type="float" value="15.0" label="stopping point of sigma" help="(-sigma_stop)"/>
  </inputs>
  <outputs>
    <data name="param_out" label="output file: the model in libsvm format" format="txt"/>
  </outputs>
  <help>**What it does**

Trains a model for the prediction of proteotypic peptides from a training set.


For more information, visit http://ftp.mi.fu-berlin.de/OpenMS/release-documentation/html/TOPP_PTModel.html

@REFERENCES@
</help>
</tool>