annotate main_macros.xml @ 23:4ed102b922cb draft default tip

planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/tools/sklearn commit 8850f42c2c3763e614f7454c9c006f3d2ff572c0

<macros>
    <token name="@VERSION@">1.0.8.3</token>

    <xml name="python_requirements">
        <requirements>
            <requirement type="package" version="0.8.3">Galaxy-ML</requirement>
            <yield />
        </requirements>
    </xml>

    <xml name="macro_stdio">
        <stdio>
            <exit_code range="1:" level="fatal" description="Error occurred. Please check Tool Standard Error" />
        </stdio>
    </xml>


    <!--Generic interface-->

    <xml name="sl_Conditional" token_train="tabular" token_data="tabular" token_model="txt">
        <conditional name="selected_tasks">
            <param name="selected_task" type="select" label="Select a Classification Task">
                <option value="train" selected="true">Train a model</option>
                <option value="load">Load a model and predict</option>
            </param>
            <when value="load">
                <param name="infile_model" type="data" format="@MODEL@" label="Models" help="Select a model file." />
                <param name="infile_data" type="data" format="@DATA@" label="Data (tabular)" help="Select the dataset you want to classify." />
                <param name="header" type="boolean" optional="True" truevalue="booltrue" falsevalue="boolfalse" checked="False" label="Does the dataset contain header:" />
                <conditional name="prediction_options">
                    <param name="prediction_option" type="select" label="Select the type of prediction">
                        <option value="predict">Predict class labels</option>
                        <option value="advanced">Include advanced options</option>
                    </param>
                    <when value="predict">
                    </when>
                    <when value="advanced">
                    </when>
                </conditional>
            </when>
            <when value="train">
                <conditional name="selected_algorithms">
                    <yield />
                </conditional>
            </when>
        </conditional>
    </xml>

    <xml name="advanced_section">
        <section name="options" title="Advanced Options" expanded="False">
            <yield />
        </section>
    </xml>


    <!--Generalized Linear Models-->
    <xml name="loss" token_help=" " token_select="false">
        <param argument="loss" type="select" label="Loss function" help="@HELP@">
            <option value="squared_loss" selected="@SELECT@">squared loss</option>
            <option value="huber">huber</option>
            <option value="epsilon_insensitive">epsilon insensitive</option>
            <option value="squared_epsilon_insensitive">squared epsilon insensitive</option>
            <yield />
        </param>
    </xml>

    <xml name="penalty" token_help=" ">
        <param argument="penalty" type="select" label="Penalty (regularization term)" help="@HELP@">
            <option value="l2" selected="true">l2</option>
            <option value="l1">l1</option>
            <option value="elasticnet">elastic net</option>
            <option value="none">none</option>
            <yield />
        </param>
    </xml>

    <xml name="l1_ratio" token_default_value="0.15" token_help=" ">
        <param argument="l1_ratio" type="float" value="@DEFAULT_VALUE@" label="Elastic Net mixing parameter" help="@HELP@" />
    </xml>

    <xml name="epsilon" token_default_value="0.1" token_help="Used if loss is ‘huber’, ‘epsilon_insensitive’, or ‘squared_epsilon_insensitive’. ">
        <param argument="epsilon" type="float" value="@DEFAULT_VALUE@" label="Epsilon (epsilon-sensitive loss functions only)" help="@HELP@" />
    </xml>

    <xml name="learning_rate_s" token_help=" " token_selected1="false" token_selected2="false">
        <param argument="learning_rate" type="select" optional="true" label="Learning rate schedule" help="@HELP@">
            <option value="optimal" selected="@SELECTED1@">optimal</option>
            <option value="constant">constant</option>
            <option value="invscaling" selected="@SELECTED2@">inverse scaling</option>
            <yield />
        </param>
    </xml>

    <xml name="eta0" token_default_value="0.0" token_help="Used with ‘constant’ or ‘invscaling’ schedules. ">
        <param argument="eta0" type="float" value="@DEFAULT_VALUE@" label="Initial learning rate" help="@HELP@" />
    </xml>

    <xml name="power_t" token_default_value="0.5" token_help=" ">
        <param argument="power_t" type="float" value="@DEFAULT_VALUE@" label="Exponent for inverse scaling learning rate" help="@HELP@" />
    </xml>

    <xml name="normalize" token_checked="false" token_help=" ">
        <param argument="normalize" type="boolean" optional="true" truevalue="booltrue" falsevalue="boolfalse" checked="@CHECKED@" label="Normalize samples before training" help=" " />
    </xml>

    <xml name="copy_X" token_checked="true" token_help=" ">
        <param argument="copy_X" type="boolean" optional="true" truevalue="booltrue" falsevalue="boolfalse" checked="@CHECKED@" label="Use a copy of samples" help="If false, samples would be overwritten. " />
    </xml>

    <xml name="ridge_params">
        <expand macro="normalize" />
        <expand macro="alpha" default_value="1.0" />
        <expand macro="fit_intercept" />
        <expand macro="max_iter" default_value="" />
        <expand macro="tol" default_value="0.001" help_text="Precision of the solution. " />
        <!--class_weight-->
        <expand macro="copy_X" />
        <param argument="solver" type="select" value="" label="Solver to use in the computational routines" help=" ">
            <option value="auto" selected="true">auto</option>
            <option value="svd">svd</option>
            <option value="cholesky">cholesky</option>
            <option value="lsqr">lsqr</option>
            <option value="sparse_cg">sparse_cg</option>
            <option value="sag">sag</option>
        </param>
        <expand macro="random_state" />
    </xml>

    <!--Ensemble methods-->
    <xml name="n_estimators" token_default_value="10" token_help=" ">
        <param argument="n_estimators" type="integer" optional="true" value="@DEFAULT_VALUE@" label="Number of trees in the forest" help="@HELP@" />
    </xml>

    <xml name="max_depth" token_default_value="" token_help=" ">
        <param argument="max_depth" type="integer" optional="true" value="@DEFAULT_VALUE@" label="Maximum depth of the tree" help="@HELP@" />
    </xml>

    <xml name="min_samples_split" token_type="integer" token_default_value="2" token_help=" ">
        <param argument="min_samples_split" type="@TYPE@" optional="true" value="@DEFAULT_VALUE@" label="Minimum number of samples required to split an internal node" help="@HELP@" />
    </xml>

    <xml name="min_samples_leaf" token_type="integer" token_default_value="1" token_label="Minimum number of samples in newly created leaves" token_help=" ">
        <param argument="min_samples_leaf" type="@TYPE@" optional="true" value="@DEFAULT_VALUE@" label="@LABEL@" help="@HELP@" />
    </xml>

    <xml name="min_weight_fraction_leaf" token_default_value="0.0" token_help=" ">
        <param argument="min_weight_fraction_leaf" type="float" optional="true" value="@DEFAULT_VALUE@" label="Minimum weighted fraction of the input samples required to be at a leaf node" help="@HELP@" />
    </xml>

    <xml name="max_leaf_nodes" token_default_value="" token_help=" ">
        <param argument="max_leaf_nodes" type="integer" optional="true" value="@DEFAULT_VALUE@" label="Maximum number of leaf nodes in best-first method" help="@HELP@" />
    </xml>

    <xml name="min_impurity_decrease" token_default_value="0" token_help=" ">
        <param argument="min_impurity_decrease" type="float" value="@DEFAULT_VALUE@" optional="true" label="The threshold value of impurity for stopping node splitting" help="@HELP@" />
    </xml>

    <xml name="bootstrap" token_checked="true" token_help=" ">
        <param argument="bootstrap" type="boolean" optional="true" truevalue="booltrue" falsevalue="boolflase" checked="@CHECKED@" label="Use bootstrap samples for building trees." help="@HELP@" />
    </xml>

    <xml name="criterion" token_help=" ">
        <param argument="criterion" type="select" label="Function to measure the quality of a split" help=" ">
            <option value="gini" selected="true">Gini impurity</option>
            <option value="entropy">Information gain</option>
            <yield />
        </param>
    </xml>

    <xml name="criterion2" token_help="">
        <param argument="criterion" type="select" label="Function to measure the quality of a split">
            <option value="mse">mse - mean squared error</option>
            <option value="mae">mae - mean absolute error</option>
            <yield />
        </param>
    </xml>

    <xml name="oob_score" token_checked="false" token_help=" ">
        <param argument="oob_score" type="boolean" optional="true" truevalue="booltrue" falsevalue="boolfalse" checked="@CHECKED@" label="Use out-of-bag samples to estimate the generalization error" help="@HELP@" />
    </xml>

    <xml name="max_features">
        <conditional name="select_max_features">
            <param argument="max_features" type="select" label="max_features">
                <option value="auto" selected="true">auto - max_features=n_features</option>
                <option value="sqrt">sqrt - max_features=sqrt(n_features)</option>
                <option value="log2">log2 - max_features=log2(n_features)</option>
                <option value="number_input">I want to type the number in or input None type</option>
            </param>
            <when value="auto">
            </when>
            <when value="sqrt">
            </when>
            <when value="log2">
            </when>
            <when value="number_input">
                <param name="num_max_features" type="float" value="" optional="true" label="Input max_features number:" help="If int, consider the number of features at each split; If float, then max_features is a percentage and int(max_features * n_features) features are considered at each split." />
            </when>
        </conditional>
    </xml>

    <xml name="verbose" token_default_value="0" token_help="If 1 then it prints progress and performance once in a while. If greater than 1 then it prints progress and performance for every tree.">
        <param argument="verbose" type="integer" value="@DEFAULT_VALUE@" optional="true" label="Enable verbose output" help="@HELP@" />
    </xml>

    <xml name="learning_rate" token_default_value="1.0" token_help=" ">
        <param argument="learning_rate" type="float" optional="true" value="@DEFAULT_VALUE@" label="Learning rate" help="@HELP@" />
    </xml>

    <xml name="subsample" token_help=" ">
        <param argument="subsample" type="float" value="1.0" optional="true" label="The fraction of samples to be used for fitting the individual base learners" help="@HELP@" />
    </xml>

    <xml name="presort">
        <param argument="presort" type="select" label="Whether to presort the data to speed up the finding of best splits in fitting">
            <option value="auto" selected="true">auto</option>
            <option value="true">true</option>
            <option value="false">false</option>
        </param>
    </xml>

    <!-- LightGBM -->
    <xml name="feature_fraction" token_help="LightGBM will randomly select part of the features for each iteration (tree) if feature_fraction is smaller than 1.0. For example, if you set it to 0.8, LightGBM will select 80% of features before training each tree.">
        <param argument="feature_fraction" type="float" value="1.0" label="Proportion of features to train each tree" help="@HELP@" />
    </xml>

    <xml name="lambda_l1" token_help=" ">
        <param argument="lambda_l1" type="float" value="0.0" label="L1 regularization" help="@HELP@" />
    </xml>

    <xml name="lambda_l2" token_help=" ">
        <param argument="lambda_l2" type="float" value="0.0" label="L1 regularization" help="@HELP@" />
    </xml>

    <xml name="min_gain_to_split" token_help=" ">
        <param argument="min_gain_to_split" type="float" value="0.0" label="Minimal gain to perform split" help="@HELP@" />
    </xml>

    <xml name="min_child_weight" token_help="Minimal sum hessian in one leaf. It can be used to deal with over-fitting.">
        <param argument="min_child_weight" type="float" value="0.0" label="Minimal sum hessian in one leaf" help="@HELP@" />
    </xml>


    <!--Parameters-->
    <xml name="tol" token_default_value="0.0" token_help_text="Early stopping heuristics based on the relative center changes. Set to default (0.0) to disable this convergence detection.">
        <param argument="tol" type="float" optional="true" value="@DEFAULT_VALUE@" label="Tolerance" help="@HELP_TEXT@" />
    </xml>

    <xml name="n_clusters" token_default_value="8">
        <param argument="n_clusters" type="integer" optional="true" value="@DEFAULT_VALUE@" label="Number of clusters" help=" " />
    </xml>

    <xml name="fit_intercept" token_checked="true">
        <param argument="fit_intercept" type="boolean" optional="true" truevalue="booltrue" falsevalue="boolfalse" checked="@CHECKED@" label="Estimate the intercept" help="If false, the data is assumed to be already centered." />
    </xml>

    <xml name="n_iter_no_change" token_default_value="5" token_help_text="Number of iterations with no improvement to wait before early stopping. ">
        <param argument="n_iter_no_change" type="integer" optional="true" value="@DEFAULT_VALUE@" label="Number of iterations" help="@HELP_TEXT@" />
    </xml>

    <xml name="shuffle" token_checked="true" token_help_text=" " token_label="Shuffle data after each iteration">
        <param argument="shuffle" type="boolean" optional="true" truevalue="booltrue" falsevalue="boolfalse" checked="@CHECKED@" label="@LABEL@" help="@HELP_TEXT@" />
    </xml>

    <xml name="random_state" token_default_value="" token_help_text="Integer number. The seed of the pseudo random number generator to use when shuffling the data. A fixed seed allows reproducible results. default=None.">
        <param argument="random_state" type="integer" optional="true" value="@DEFAULT_VALUE@" label="Random seed number" help="@HELP_TEXT@" />
    </xml>

    <xml name="warm_start" token_checked="true" token_help_text="When set to True, reuse the solution of the previous call to fit as initialization,otherwise, just erase the previous solution.">
        <param argument="warm_start" type="boolean" optional="true" truevalue="booltrue" falsevalue="boolfalse" checked="@CHECKED@" label="Perform warm start" help="@HELP_TEXT@" />
    </xml>

    <xml name="C" token_default_value="1.0" token_help_text="Penalty parameter C of the error term.">
        <param argument="C" type="float" optional="true" value="@DEFAULT_VALUE@" label="Penalty parameter" help="@HELP_TEXT@" />
    </xml>

    <!--xml name="class_weight" token_default_value="" token_help_text="">
    <param argument="class_weight" type="" optional="true" value="@DEFAULT_VALUE@" label="" help="@HELP_TEXT@"/>
  </xml-->

    <xml name="alpha" token_default_value="0.0001" token_help_text="Constant that multiplies the regularization term if regularization is used. ">
        <param argument="alpha" type="float" optional="true" value="@DEFAULT_VALUE@" label="Regularization coefficient" help="@HELP_TEXT@" />
    </xml>

    <xml name="n_samples" token_default_value="100" token_help_text="The total number of points equally divided among clusters.">
        <param argument="n_samples" type="integer" optional="true" value="@DEFAULT_VALUE@" label="Number of samples" help="@HELP_TEXT@" />
    </xml>

    <xml name="n_features" token_default_value="2" token_help_text="Number of different numerical properties produced for each sample.">
        <param argument="n_features" type="integer" optional="true" value="@DEFAULT_VALUE@" label="Number of features" help="@HELP_TEXT@" />
    </xml>

    <xml name="noise" token_default_value="0.0" token_help_text="Floating point number. ">
        <param argument="noise" type="float" optional="true" value="@DEFAULT_VALUE@" label="Standard deviation of the Gaussian noise added to the data" help="@HELP_TEXT@" />
    </xml>

    <xml name="C" token_default_value="1.0" token_help_text="Penalty parameter C of the error term. ">
        <param argument="C" type="float" optional="true" value="@DEFAULT_VALUE@" label="Penalty parameter" help="@HELP_TEXT@" />
    </xml>

    <xml name="max_iter" token_default_value="300" token_label="Maximum number of iterations per single run" token_help_text=" ">
        <param argument="max_iter" type="integer" optional="true" value="@DEFAULT_VALUE@" label="@LABEL@" help="@HELP_TEXT@" />
    </xml>

    <xml name="n_init" token_default_value="10">
        <param argument="n_init" type="integer" optional="true" value="@DEFAULT_VALUE@" label="Number of runs with different centroid seeds" help=" " />
    </xml>

    <xml name="init">
        <param argument="init" type="select" label="Centroid initialization method" help="''k-means++'' selects initial cluster centers that speed up convergence. ''random'' chooses k observations (rows) at random from data as initial centroids.">
            <option value="k-means++">k-means++</option>
            <option value="random">random</option>
        </param>
    </xml>

    <xml name="gamma" token_default_value="1.0" token_label="Scaling parameter" token_help_text=" ">
        <param argument="gamma" type="float" optional="true" value="@DEFAULT_VALUE@" label="@LABEL@" help="@HELP_TEXT@" />
    </xml>

    <xml name="degree" token_default_value="3" token_label="Degree of the polynomial" token_help_text=" ">
        <param argument="degree" type="integer" optional="true" value="@DEFAULT_VALUE@" label="@LABEL@" help="@HELP_TEXT@" />
    </xml>

    <xml name="coef0" token_default_value="1" token_label="Zero coefficient" token_help_text=" ">
        <param argument="coef0" type="integer" optional="true" value="@DEFAULT_VALUE@" label="@LABEL@" help="@HELP_TEXT@" />
    </xml>

    <xml name="pos_label" token_default_value="">
        <param argument="pos_label" type="integer" optional="true" value="@DEFAULT_VALUE@" label="Label of the positive class" help=" " />
    </xml>

    <xml name="average">
        <param argument="average" type="select" optional="true" label="Averaging type" help=" ">
            <option value="micro">Calculate metrics globally by counting the total true positives, false negatives and false positives. (micro)</option>
            <option value="samples">Calculate metrics for each instance, and find their average. Only meaningful for multilabel. (samples)</option>
            <option value="macro">Calculate metrics for each label, and find their unweighted mean. This does not take label imbalance into account. (macro)</option>
            <option value="weighted">Calculate metrics for each label, and find their average, weighted by support (the number of true instances for each label). This alters ‘macro’ to account for label imbalance; it can result in an F-score that is not between precision and recall. (weighted)</option>
            <option value="None">None</option>
            <yield />
        </param>
    </xml>

    <xml name="beta">
        <param argument="beta" type="float" value="1.0" label="The strength of recall versus precision in the F-score" help=" " />
    </xml>


    <!--Data interface-->

    <xml name="samples_tabular" token_label1="Training samples dataset:" token_multiple1="false" token_multiple2="false">
        <param name="infile1" type="data" format="tabular" label="@LABEL1@" />
        <param name="header1" type="boolean" optional="true" truevalue="booltrue" falsevalue="boolfalse" checked="False" label="Does the dataset contain header:" />
        <conditional name="column_selector_options_1">
            <expand macro="samples_column_selector_options" multiple="@MULTIPLE1@" />
        </conditional>
        <param name="infile2" type="data" format="tabular" label="Dataset containing class labels or target values:" />
        <param name="header2" type="boolean" optional="true" truevalue="booltrue" falsevalue="boolfalse" checked="False" label="Does the dataset contain header:" />
        <conditional name="column_selector_options_2">
            <expand macro="samples_column_selector_options" column_option="selected_column_selector_option2" col_name="col2" multiple="@MULTIPLE2@" infile="infile2" />
        </conditional>
        <yield />
    </xml>

    <xml name="samples_column_selector_options" token_column_option="selected_column_selector_option" token_col_name="col1" token_multiple="False" token_infile="infile1">
        <param name="@COLUMN_OPTION@" type="select" label="Choose how to select data by column:">
            <option value="by_index_number" selected="true">Select columns by column index number(s)</option>
            <option value="all_but_by_index_number">All columns EXCLUDING some by column index number(s)</option>
            <option value="by_header_name">Select columns by column header name(s)</option>
            <option value="all_but_by_header_name">All columns EXCLUDING some by column header name(s)</option>
            <option value="all_columns">All columns</option>
        </param>
        <when value="by_index_number">
            <param name="@COL_NAME@" multiple="@MULTIPLE@" type="data_column" use_header_names="true" data_ref="@INFILE@" label="Select target column(s):" />
        </when>
        <when value="all_but_by_index_number">
            <param name="@COL_NAME@" multiple="@MULTIPLE@" type="data_column" use_header_names="true" data_ref="@INFILE@" label="Select target column(s):" />
        </when>
        <when value="by_header_name">
            <param name="@COL_NAME@" type="text" value="" label="Type header name(s):" help="Comma-separated string. For example: target1,target2" />
        </when>
        <when value="all_but_by_header_name">
            <param name="@COL_NAME@" type="text" value="" label="Type header name(s):" help="Comma-separated string. For example: target1,target2" />
        </when>
        <when value="all_columns">
        </when>
    </xml>

    <xml name="clf_inputs_extended" token_label1=" " token_label2=" " token_multiple="False">
        <conditional name="true_columns">
            <param name="selected_input1" type="select" label="Select the input type of true labels dataset:">
                <option value="tabular" selected="true">Tabular</option>
                <option value="sparse">Sparse</option>
            </param>
            <when value="tabular">
                <param name="infile1" type="data" label="@LABEL1@" />
                <param name="col1" type="data_column" data_ref="infile1" label="Select the target column:" />
            </when>
            <when value="sparse">
                <param name="infile1" type="data" format="txt" label="@LABEL1@" />
            </when>
        </conditional>
        <conditional name="predicted_columns">
            <param name="selected_input2" type="select" label="Select the input type of predicted labels dataset:">
                <option value="tabular" selected="true">Tabular</option>
                <option value="sparse">Sparse</option>
            </param>
            <when value="tabular">
                <param name="infile2" type="data" label="@LABEL2@" />
                <param name="col2" multiple="@MULTIPLE@" type="data_column" data_ref="infile2" label="Select target column(s):" />
            </when>
            <when value="sparse">
                <param name="infile2" type="data" format="txt" label="@LABEL1@" />
            </when>
        </conditional>
    </xml>

    <xml name="clf_inputs" token_label1="Dataset containing true labels (tabular):" token_label2="Dataset containing predicted values (tabular):" token_multiple1="False" token_multiple="False">
        <param name="infile1" type="data" format="tabular" label="@LABEL1@" />
        <param name="header1" type="boolean" optional="True" truevalue="booltrue" falsevalue="boolfalse" checked="False" label="Does the dataset contain header:" />
        <conditional name="column_selector_options_1">
            <expand macro="samples_column_selector_options" multiple="@MULTIPLE1@" />
        </conditional>
        <param name="infile2" type="data" format="tabular" label="@LABEL2@" />
        <param name="header2" type="boolean" optional="True" truevalue="booltrue" falsevalue="boolfalse" checked="False" label="Does the dataset contain header:" />
        <conditional name="column_selector_options_2">
            <expand macro="samples_column_selector_options" column_option="selected_column_selector_option2" col_name="col2" multiple="@MULTIPLE@" infile="infile2" />
        </conditional>
    </xml>

    <xml name="multiple_input" token_name="input_files" token_max_num="10" token_format="txt" token_label="Sparse matrix file (.mtx, .txt)" token_help_text="Specify a sparse matrix file in .txt format.">
        <repeat name="@NAME@" min="1" max="@MAX_NUM@" title="Select input file(s):">
            <param name="input" type="data" format="@FORMAT@" label="@LABEL@" help="@HELP_TEXT@" />
        </repeat>
    </xml>

    <xml name="sparse_target" token_label1="Select a sparse matrix:" token_label2="Select the tabular containing true labels:" token_multiple="False" token_format1="txt" token_format2="tabular" token_help1="" token_help2="">
        <param name="infile1" type="data" format="@FORMAT1@" label="@LABEL1@" help="@HELP1@" />
        <expand macro="input_tabular_target" />
    </xml>

    <xml name="sl_mixed_input">
        <conditional name="input_options">
            <expand macro="data_input_options" />
            <expand macro="data_input_whens" />
        </conditional>
    </xml>

    <xml name="sl_mixed_input_plus_sequence">
        <conditional name="input_options">
            <expand macro="data_input_options">
                <option value="seq_fasta">sequnences in a fasta file</option>
                <option value="refseq_and_interval">reference genome and intervals</option>
            </expand>
            <expand macro="data_input_whens">
                <when value="seq_fasta">
                    <expand macro="inputs_seq_fasta" />
                </when>
                <when value="refseq_and_interval">
                    <expand macro="inputs_refseq_and_interval" />
                </when>
            </expand>
        </conditional>
    </xml>

    <xml name="data_input_options">
        <param name="selected_input" type="select" label="Select input type:">
            <option value="tabular" selected="true">tabular data</option>
            <option value="sparse">sparse matrix</option>
            <yield />
        </param>
    </xml>

    <xml name="data_input_whens">
        <when value="tabular">
            <expand macro="samples_tabular" multiple1="true" multiple2="false" />
        </when>
        <when value="sparse">
            <expand macro="sparse_target" />
        </when>
        <yield />
    </xml>

    <xml name="input_tabular_target">
        <param name="infile2" type="data" format="tabular" label="Dataset containing class labels or target values:" />
        <param name="header2" type="boolean" optional="true" truevalue="booltrue" falsevalue="boolfalse" checked="false" label="Does the dataset contain header:" />
        <conditional name="column_selector_options_2">
            <expand macro="samples_column_selector_options" column_option="selected_column_selector_option2" col_name="col2" multiple="false" infile="infile2" />
        </conditional>
    </xml>

    <xml name="inputs_seq_fasta">
        <param name="fasta_path" type="data" format="fasta" label="Dataset containing fasta genomic/protein sequences" help="Sequences will be one-hot encoded to arrays." />
        <expand macro="input_tabular_target" />
    </xml>

    <xml name="inputs_refseq_and_interval">
        <param name="ref_genome_file" type="data" format="fasta" label="Dataset containing reference genomic sequence" />
        <param name="interval_file" type="data" format="interval" label="Dataset containing sequence intervals for training" help="interval. Sequences will be retrieved from the reference genome and one-hot encoded to training arrays." />
        <param name="target_file" type="data" format="bed" label="Dataset containing positions and features for target values." help="bed. The file will be compressed with `bgzip` and then indexed using `tabix`." />
        <param name="infile2" type="data" format="tabular" label="Dataset containing the feature list for prediction" />
        <param name="header2" type="boolean" optional="true" truevalue="booltrue" falsevalue="boolfalse" checked="false" label="Does the dataset contain header:" />
        <conditional name="column_selector_options_2">
            <expand macro="samples_column_selector_options" column_option="selected_column_selector_option2" col_name="col2" multiple="true" infile="infile2" />
        </conditional>
    </xml>

    <!--Advanced options-->
    <xml name="nn_advanced_options">
        <section name="options" title="Advanced Options" expanded="False">
            <yield />
            <param argument="weights" type="select" label="Weight function" help="Used in prediction.">
                <option value="uniform" selected="true">Uniform weights. All points in each neighborhood are weighted equally. (Uniform)</option>
                <option value="distance">Weight points by the inverse of their distance. (Distance)</option>
            </param>
            <param argument="algorithm" type="select" label="Neighbor selection algorithm" help=" ">
                <option value="auto" selected="true">Auto</option>
                <option value="ball_tree">BallTree</option>
                <option value="kd_tree">KDTree</option>
                <option value="brute">Brute-force</option>
            </param>
            <param argument="leaf_size" type="integer" value="30" label="Leaf size" help="Used with BallTree and KDTree. Affects the time and memory usage of the constructed tree." />
            <!--param name="metric"-->
            <!--param name="p"-->
            <!--param name="metric_params"-->
        </section>
    </xml>

    <xml name="svc_advanced_options">
        <section name="options" title="Advanced Options" expanded="False">
            <yield />
            <param argument="kernel" type="select" optional="true" label="Kernel type" help="Kernel type to be used in the algorithm. If none is given, ‘rbf’ will be used.">
                <option value="rbf" selected="true">rbf</option>
                <option value="linear">linear</option>
                <option value="poly">poly</option>
                <option value="sigmoid">sigmoid</option>
                <option value="precomputed">precomputed</option>
            </param>
            <param argument="degree" type="integer" optional="true" value="3" label="Degree of the polynomial (polynomial kernel only)" help="Ignored by other kernels. dafault : 3 " />
            <!--TODO: param argument="gamma" float, optional (default=’auto’) -->
            <param argument="coef0" type="float" optional="true" value="0.0" label="Zero coefficient (polynomial and sigmoid kernels only)" help="Independent term in kernel function. dafault: 0.0 " />
            <param argument="shrinking" type="boolean" optional="true" truevalue="booltrue" falsevalue="boolfalse" checked="true" label="Use the shrinking heuristic" help=" " />
            <param argument="probability" type="boolean" optional="true" truevalue="booltrue" falsevalue="boolfalse" checked="false" label="Enable probability estimates. " help="This must be enabled prior to calling fit, and will slow down that method." />
            <!-- param argument="cache_size"-->
            <!--expand macro="class_weight"/-->
            <expand macro="tol" default_value="0.001" help_text="Tolerance for stopping criterion. " />
            <expand macro="max_iter" default_value="-1" label="Solver maximum number of iterations" help_text="Hard limit on iterations within solver, or -1 for no limit." />
            <!--param argument="decision_function_shape"-->
            <expand macro="random_state" help_text="Integer number. The seed of the pseudo random number generator to use when shuffling the data for probability estimation. A fixed seed allows reproducible results." />
        </section>
    </xml>

    <xml name="spectral_clustering_advanced_options">
        <section name="options" title="Advanced Options" expanded="False">
            <expand macro="n_clusters" />
            <param argument="eigen_solver" type="select" value="" label="Eigen solver" help="The eigenvalue decomposition strategy to use.">
                <option value="arpack" selected="true">arpack</option>
                <option value="lobpcg">lobpcg</option>
                <option value="amg">amg</option>
                <!--None-->
            </param>
            <expand macro="random_state" />
            <expand macro="n_init" />
            <param argument="gamma" type="float" optional="true" value="1.0" label="Kernel scaling factor" help="Scaling factor of RBF, polynomial, exponential chi^2 and sigmoid affinity kernel. Ignored for affinity=''nearest_neighbors''." />
            <param argument="affinity" type="select" label="Affinity" help="Affinity kernel to use. ">
                <option value="rbf" selected="true">RBF</option>
                <option value="precomputed">precomputed</option>
                <option value="nearest_neighbors">Nearset neighbors</option>
            </param>
            <param argument="n_neighbors" type="integer" optional="true" value="10" label="Number of neighbors" help="Number of neighbors to use when constructing the affinity matrix using the nearest neighbors method. Ignored for affinity=''rbf''" />
            <!--param argument="eigen_tol"-->
            <param argument="assign_labels" type="select" label="Assign labels" help="The strategy to use to assign labels in the embedding space.">
                <option value="kmeans" selected="true">kmeans</option>
                <option value="discretize">discretize</option>
            </param>
            <param argument="degree" type="integer" optional="true" value="3" label="Degree of the polynomial (polynomial kernel only)" help="Ignored by other kernels. dafault : 3 " />
            <param argument="coef0" type="integer" optional="true" value="1" label="Zero coefficient (polynomial and sigmoid kernels only)" help="Ignored by other kernels. dafault : 1 " />
            <!--param argument="kernel_params"-->
        </section>
    </xml>

    <xml name="minibatch_kmeans_advanced_options">
        <section name="options" title="Advanced Options" expanded="False">
            <expand macro="n_clusters" />
            <expand macro="init" />
            <expand macro="n_init" default_value="3" />
            <expand macro="max_iter" default_value="100" />
            <expand macro="tol" help_text="Early stopping heuristics based on normalized center change. To disable set to 0.0 ." />
            <expand macro="random_state" />
            <param argument="batch_size" type="integer" optional="true" value="100" label="Batch size" help="Size of the mini batches." />
            <!--param argument="compute_labels"-->
            <param argument="max_no_improvement" type="integer" optional="true" value="10" label="Maximum number of improvement attempts" help="
        Convergence detection based on inertia (the consecutive number of mini batches that doe not yield an improvement on the smoothed inertia).
        To disable, set max_no_improvement to None. " />
            <param argument="init_size" type="integer" optional="true" value="" label="Number of random initialization samples" help="Number of samples to randomly sample for speeding up the initialization . ( default: 3 * batch_size )" />
            <param argument="reassignment_ratio" type="float" optional="true" value="0.01" label="Re-assignment ratio" help="Controls the fraction of the maximum number of counts for a center to be reassigned. Higher values yield better clustering results." />
        </section>
    </xml>

    <xml name="kmeans_advanced_options">
        <section name="options" title="Advanced Options" expanded="False">
            <expand macro="n_clusters" />
            <expand macro="init" />
            <expand macro="n_init" />
            <expand macro="max_iter" />
            <expand macro="tol" default_value="0.0001" help_text="Relative tolerance with regards to inertia to declare convergence." />
            <!--param argument="precompute_distances"/-->
            <expand macro="random_state" />
            <param argument="copy_x" type="boolean" optional="true" truevalue="booltrue" falsevalue="boolfalse" checked="true" label="Use a copy of data for precomputing distances" help="Mofifying the original data introduces small numerical differences caused by subtracting and then adding the data mean." />
            <expand macro="kmeans_algorithm" />
        </section>
    </xml>

    <xml name="kmeans_algorithm">
        <param argument="algorithm" type="select" label="K-means algorithm to use:">
            <option value="auto" selected="true">auto</option>
            <option value="full">full</option>
            <option value="elkan">elkan</option>
        </param>
    </xml>

    <xml name="birch_advanced_options">
        <section name="options" title="Advanced Options" expanded="False">
            <param argument="threshold" type="float" optional="true" value="0.5" label="Subcluster radius threshold" help="The radius of the subcluster obtained by merging a new sample; the closest subcluster should be less than the threshold to avoid a new subcluster." />
            <param argument="branching_factor" type="integer" optional="true" value="50" label="Maximum number of subclusters per branch" help="Maximum number of CF subclusters in each node." />
            <expand macro="n_clusters" default_value="3" />
            <!--param argument="compute_labels"/-->
        </section>
    </xml>

    <xml name="dbscan_advanced_options">
        <section name="options" title="Advanced Options" expanded="False">
            <param argument="eps" type="float" optional="true" value="0.5" label="Maximum neighborhood distance" help="The maximum distance between two samples for them to be considered as in the same neighborhood." />
            <param argument="min_samples" type="integer" optional="true" value="5" label="Minimal core point density" help="The number of samples (or total weight) in a neighborhood for a point (including the point itself) to be considered as a core point." />
            <param argument="metric" type="text" optional="true" value="euclidean" label="Metric" help="The metric to use when calculating distance between instances in a feature array." />
            <param argument="algorithm" type="select" label="Pointwise distance computation algorithm" help="The algorithm to be used by the NearestNeighbors module to compute pointwise distances and find nearest neighbors.">
                <option value="auto" selected="true">auto</option>
                <option value="ball_tree">ball_tree</option>
                <option value="kd_tree">kd_tree</option>
                <option value="brute">brute</option>
            </param>
            <param argument="leaf_size" type="integer" optional="true" value="30" label="Leaf size" help="Leaf size passed to BallTree or cKDTree. Memory and time efficieny factor in tree constrution and querying." />
        </section>
    </xml>

    <xml name="clustering_algorithms_options">
        <conditional name="algorithm_options">
            <param name="selected_algorithm" type="select" label="Clustering Algorithm">
                <option value="KMeans" selected="true">KMeans</option>
                <option value="SpectralClustering">Spectral Clustering</option>
                <option value="MiniBatchKMeans">Mini Batch KMeans</option>
                <option value="DBSCAN">DBSCAN</option>
                <option value="Birch">Birch</option>
            </param>
            <when value="KMeans">
                <expand macro="kmeans_advanced_options" />
            </when>
            <when value="DBSCAN">
                <expand macro="dbscan_advanced_options" />
            </when>
            <when value="Birch">
                <expand macro="birch_advanced_options" />
            </when>
            <when value="SpectralClustering">
                <expand macro="spectral_clustering_advanced_options" />
            </when>
            <when value="MiniBatchKMeans">
                <expand macro="minibatch_kmeans_advanced_options" />
            </when>
        </conditional>
    </xml>

    <xml name="distance_metrics">
        <param argument="metric" type="select" label="Distance metric" help=" ">
            <option value="euclidean" selected="true">euclidean</option>
            <option value="cityblock">cityblock</option>
            <option value="cosine">cosine</option>
            <option value="l1">l1</option>
            <option value="l2">l2</option>
            <option value="manhattan">manhattan</option>
            <yield />
        </param>
    </xml>

    <xml name="distance_nonsparse_metrics">
        <option value="braycurtis">braycurtis</option>
        <option value="canberra">canberra</option>
        <option value="chebyshev">chebyshev</option>
        <option value="correlation">correlation</option>
        <option value="dice">dice</option>
        <option value="hamming">hamming</option>
        <option value="jaccard">jaccard</option>
        <option value="kulsinski">kulsinski</option>
        <option value="mahalanobis">mahalanobis</option>
        <option value="matching">matching</option>
        <option value="minkowski">minkowski</option>
        <option value="rogerstanimoto">rogerstanimoto</option>
        <option value="russellrao">russellrao</option>
        <option value="seuclidean">seuclidean</option>
        <option value="sokalmichener">sokalmichener</option>
        <option value="sokalsneath">sokalsneath</option>
        <option value="sqeuclidean">sqeuclidean</option>
        <option value="yule">yule</option>
    </xml>

    <xml name="pairwise_kernel_metrics">
        <param argument="metric" type="select" label="Pirwise Kernel metric" help=" ">
            <option value="rbf" selected="true">rbf</option>
            <option value="sigmoid">sigmoid</option>
            <option value="polynomial">polynomial</option>
            <option value="linear" selected="true">linear</option>
            <option value="chi2">chi2</option>
            <option value="additive_chi2">additive_chi2</option>
        </param>
    </xml>

    <xml name="sparse_pairwise_metric_functions">
        <param name="selected_metric_function" type="select" label="Select the pairwise metric you want to compute:">
            <option value="euclidean_distances" selected="true">Euclidean distance matrix</option>
            <option value="pairwise_distances">Distance matrix</option>
            <option value="pairwise_distances_argmin">Minimum distances between one point and a set of points</option>
            <yield />
        </param>
    </xml>

    <xml name="pairwise_metric_functions">
        <option value="additive_chi2_kernel">Additive chi-squared kernel</option>
        <option value="chi2_kernel">Exponential chi-squared kernel</option>
        <option value="linear_kernel">Linear kernel</option>
        <option value="manhattan_distances">L1 distances</option>
        <option value="pairwise_kernels">Kernel</option>
        <option value="polynomial_kernel">Polynomial kernel</option>
        <option value="rbf_kernel">Gaussian (rbf) kernel</option>
        <option value="laplacian_kernel">Laplacian kernel</option>
    </xml>

    <xml name="sparse_pairwise_condition">
        <when value="pairwise_distances">
            <section name="options" title="Advanced Options" expanded="False">
                <expand macro="distance_metrics">
                    <yield />
                </expand>
            </section>
        </when>
        <when value="euclidean_distances">
            <section name="options" title="Advanced Options" expanded="False">
                <param argument="squared" type="boolean" optional="true" truevalue="booltrue" falsevalue="boolfalse" checked="false" label="Return squared Euclidean distances" help=" " />
            </section>
        </when>
    </xml>

    <xml name="argmin_distance_condition">
        <when value="pairwise_distances_argmin">
            <section name="options" title="Advanced Options" expanded="False">
                <param argument="axis" type="integer" optional="true" value="1" label="Axis" help="Axis along which the argmin and distances are to be computed." />
                <expand macro="distance_metrics">
                    <yield />
                </expand>
                <param argument="batch_size" type="integer" optional="true" value="500" label="Batch size" help="Number of rows to be processed in each batch run." />
            </section>
        </when>
    </xml>

    <xml name="sparse_preprocessors">
        <param name="selected_pre_processor" type="select" label="Select a preprocessor:">
            <option value="StandardScaler" selected="true">Standard Scaler (Standardizes features by removing the mean and scaling to unit variance)</option>
            <option value="Binarizer">Binarizer (Binarizes data)</option>
            <option value="MaxAbsScaler">Max Abs Scaler (Scales features by their maximum absolute value)</option>
            <option value="Normalizer">Normalizer (Normalizes samples individually to unit norm)</option>
            <yield />
        </param>
    </xml>

    <xml name="sparse_preprocessors_ext">
        <expand macro="sparse_preprocessors">
            <option value="KernelCenterer">Kernel Centerer (Centers a kernel matrix)</option>
            <option value="MinMaxScaler">Minmax Scaler (Scales features to a range)</option>
            <option value="PolynomialFeatures">Polynomial Features (Generates polynomial and interaction features)</option>
            <option value="RobustScaler">Robust Scaler (Scales features using outlier-invariance statistics)</option>
            <option value="QuantileTransformer">QuantileTransformer (Transform features using quantiles information)</option>
            <option value="PowerTransformer">PowerTransformer (Apply a power transform featurewise to make data more Gaussian-like)</option>
            <option value="KBinsDiscretizer">KBinsDiscretizer (Bin continuous data into intervals.)</option>
        </expand>
    </xml>

    <xml name="sparse_preprocessor_options">
        <when value="Binarizer">
            <section name="options" title="Advanced Options" expanded="False">
                <param argument="copy" type="boolean" optional="true" truevalue="booltrue" falsevalue="boolfalse" checked="true" label="Use a copy of data for precomputing binarization" help=" " />
                <param argument="threshold" type="float" optional="true" value="0.0" label="Threshold" help="Feature values below or equal to this are replaced by 0, above it by 1. Threshold may not be less than 0 for operations on sparse matrices. " />
            </section>
        </when>
        <when value="StandardScaler">
            <section name="options" title="Advanced Options" expanded="False">
                <param argument="copy" type="boolean" optional="true" truevalue="booltrue" falsevalue="boolfalse" checked="true" label="Use a copy of data for performing inplace scaling" help=" " />
                <param argument="with_mean" type="boolean" optional="true" truevalue="booltrue" falsevalue="boolfalse" checked="true" label="Center the data before scaling" help=" " />
                <param argument="with_std" type="boolean" optional="true" truevalue="booltrue" falsevalue="boolfalse" checked="true" label="Scale the data to unit variance (or unit standard deviation)" help=" " />
            </section>
        </when>
        <when value="MaxAbsScaler">
            <section name="options" title="Advanced Options" expanded="False">
                <param argument="copy" type="boolean" optional="true" truevalue="booltrue" falsevalue="boolfalse" checked="true" label="Use a copy of data for precomputing scaling" help=" " />
            </section>
        </when>
        <when value="Normalizer">
            <section name="options" title="Advanced Options" expanded="False">
                <param argument="norm" type="select" optional="true" label="The norm to use to normalize non zero samples" help=" ">
                    <option value="l1" selected="true">l1</option>
                    <option value="l2">l2</option>
                    <option value="max">max</option>
                </param>
                <param argument="copy" type="boolean" optional="true" truevalue="booltrue" falsevalue="boolfalse" checked="true" label="Use a copy of data for precomputing row normalization" help=" " />
            </section>
        </when>
        <yield />
    </xml>

    <xml name="sparse_preprocessor_options_ext">
        <expand macro="sparse_preprocessor_options">
            <when value="KernelCenterer">
                <section name="options" title="Advanced Options" expanded="False">
                </section>
            </when>
            <when value="MinMaxScaler">
                <section name="options" title="Advanced Options" expanded="False">
                    <param argument="feature_range" type="text" value="(0, 1)" optional="true" help="Desired range of transformed data. None or tuple (min, max). None equals to (0, 1)" />
                    <param argument="copy" type="boolean" optional="true" truevalue="booltrue" falsevalue="boolflase" checked="true" label="Use a copy of data for precomputing normalization" help=" " />
                </section>
            </when>
            <when value="PolynomialFeatures">
                <section name="options" title="Advanced Options" expanded="False">
                    <param argument="degree" type="integer" optional="true" value="2" label="The degree of the polynomial features " help="" />
                    <param argument="interaction_only" type="boolean" optional="true" truevalue="booltrue" falsevalue="boolflase" checked="false" label="Produce interaction features only" help="(Features that are products of at most degree distinct input features) " />
                    <param argument="include_bias" type="boolean" optional="true" truevalue="booltrue" falsevalue="boolflase" checked="true" label="Include a bias column" help="Feature in which all polynomial powers are zero " />
                </section>
            </when>
            <when value="RobustScaler">
                <section name="options" title="Advanced Options" expanded="False">
                    <!--=True, =True, copy=True-->
                    <param argument="with_centering" type="boolean" optional="true" truevalue="booltrue" falsevalue="boolflase" checked="true" label="Center the data before scaling" help=" " />
                    <param argument="with_scaling" type="boolean" optional="true" truevalue="booltrue" falsevalue="boolflase" checked="true" label="Scale the data to interquartile range" help=" " />
                    <param argument="copy" type="boolean" optional="true" truevalue="booltrue" falsevalue="boolflase" checked="true" label="Use a copy of data for inplace scaling" help=" " />
                </section>
            </when>
            <when value="QuantileTransformer">
                <section name="options" title="Advanced Options" expanded="False">
                    <param name="n_quantiles" type="integer" value="1000" min="0" label="Number of quantiles to be computed" />
                    <param name="output_distribution" type="select" label="Marginal distribution for the transformed data">
                        <option value="uniform" selected="true">uniform</option>
                        <option value="normal">normal</option>
                    </param>
                    <param name="ignore_implicit_zeros" type="boolean" truevalue="booltrue" falsevalue="boolfalse" checked="false" label="Whether to discard sparse entries" help="Only applies to sparse matrices. If False, sparse entries are treated as zeros" />
                    <param name="subsample" type="integer" value="100000" label="Maximum number of samples used to estimate the quantiles for computational efficiency" help="Note that the subsampling procedure may differ for value-identical sparse and dense matrices." />
                    <expand macro="random_state" help_text="This is used by subsampling and smoothing noise" />
                </section>
            </when>
            <when value="PowerTransformer">
                <section name="options" title="Advanced Options" expanded="False">
                    <param name="method" type="select" label="The power transform method">
                        <option value="yeo-johnson" selected="true">yeo-johnson (works with positive and negative values)</option>
                        <option value="box-cox">box-cox (might perform better, but only works with strictly positive values)</option>
                    </param>
                    <param name="standardize" type="boolean" truevalue="booltrue" falsevalue="boolfalse" checked="true" label="Whether to apply zero-mean, unit-variance normalization to the transformed output." />
                </section>
            </when>
            <when value="KBinsDiscretizer">
                <section name="options" title="Advanced Options" expanded="False">
                    <param name="n_bins" type="integer" value="5" min="2" label="The number of bins to produce" />
                    <param name="encode" type="select" label="Method used to encode the transformed result">
                        <option value="onehot" selected="true">onehot (encode the transformed result with one-hot encoding and return a sparse matrix)</option>
                        <option value="onehot-dense">onehot-dense (encode the transformed result with one-hot encoding and return a dense array)</option>
                        <option value="ordinal">ordinal (return the bin identifier encoded as an integer value)</option>
                    </param>
                    <param name="strategy" type="select" label="Strategy used to define the widths of the bins">
                        <option value="uniform">uniform (all bins in each feature have identical widths)</option>
                        <option value="quantile" selected="true">quantile (all bins in each feature have the same number of points)</option>
                        <option value="kmeans">kmeans (values in each bin have the same nearest center of a 1D k-means cluster)</option>
                    </param>
                </section>
            </when>
        </expand>
    </xml>

    <xml name="cv_splitter">
        <option value="default" selected="true">default splitter</option>
        <option value="KFold">KFold</option>
        <option value="StratifiedKFold">StratifiedKFold</option>
        <option value="LeaveOneOut">LeaveOneOut</option>
        <option value="LeavePOut">LeavePOut</option>
        <option value="RepeatedKFold">RepeatedKFold</option>
        <option value="RepeatedStratifiedKFold">RepeatedStratifiedKFold</option>
        <option value="ShuffleSplit">ShuffleSplit</option>
        <option value="StratifiedShuffleSplit">StratifiedShuffleSplit</option>
        <option value="TimeSeriesSplit">TimeSeriesSplit</option>
        <option value="PredefinedSplit">PredefinedSplit</option>
        <option value="OrderedKFold">OrderedKFold</option>
        <option value="RepeatedOrderedKFold">RepeatedOrderedKFold</option>
        <yield />
    </xml>

    <xml name="cv_splitter_options">
        <when value="default">
            <expand macro="cv_n_splits" />
        </when>
        <when value="KFold">
            <expand macro="cv_n_splits" />
            <expand macro="cv_shuffle" />
            <expand macro="random_state" />
        </when>
        <when value="StratifiedKFold">
            <expand macro="cv_n_splits" />
            <expand macro="cv_shuffle" />
            <expand macro="random_state" />
        </when>
        <when value="LeaveOneOut">
        </when>
        <when value="LeavePOut">
            <param argument="p" type="integer" value="" label="p" help="Integer. Size of the test sets." />
        </when>
        <when value="RepeatedKFold">
            <expand macro="cv_n_splits" value="5" />
            <param argument="n_repeats" type="integer" value="10" label="n_repeats" help="Number of times cross-validator needs to be repeated." />
            <expand macro="random_state" />
        </when>
        <when value="RepeatedStratifiedKFold">
            <expand macro="cv_n_splits" value="5" />
            <param argument="n_repeats" type="integer" value="10" label="n_repeats" help="Number of times cross-validator needs to be repeated." />
            <expand macro="random_state" />
        </when>
        <when value="ShuffleSplit">
            <expand macro="cv_n_splits" value="10" help="Number of re-shuffling and splitting iterations." />
            <expand macro="cv_test_size" value="0.1" />
            <expand macro="random_state" />
        </when>
        <when value="StratifiedShuffleSplit">
            <expand macro="cv_n_splits" value="10" help="Number of re-shuffling and splitting iterations." />
            <expand macro="cv_test_size" value="0.1" />
            <expand macro="random_state" />
        </when>
        <when value="TimeSeriesSplit">
            <expand macro="cv_n_splits" />
            <param argument="max_train_size" type="integer" value="" optional="true" label="Maximum size of the training set" help="Maximum size for a single training set." />
        </when>
        <when value="PredefinedSplit">
            <param argument="test_fold" type="text" value="" area="true" label="test_fold" help="List, e.g., [0, 1, -1, 1], represents two test sets, [X[0]] and [X[1], X[3]], X[2] is excluded from any test set due to '-1'." />
        </when>
        <when value="OrderedKFold">
            <expand macro="cv_n_splits" />
            <expand macro="cv_shuffle" />
            <expand macro="random_state" />
        </when>
        <when value="RepeatedOrderedKFold">
            <expand macro="cv_n_splits" />
            <param argument="n_repeats" type="integer" value="5" />
            <expand macro="random_state" />
        </when>
        <yield />
    </xml>

    <xml name="cv">
        <conditional name="cv_selector">
            <param name="selected_cv" type="select" label="Select the cv splitter:">
                <expand macro="cv_splitter">
                    <option value="GroupKFold">GroupKFold</option>
                    <option value="GroupShuffleSplit">GroupShuffleSplit</option>
                    <option value="LeaveOneGroupOut">LeaveOneGroupOut</option>
                    <option value="LeavePGroupsOut">LeavePGroupsOut</option>
                </expand>
            </param>
            <expand macro="cv_splitter_options">
                <when value="GroupKFold">
                    <expand macro="cv_n_splits" />
                    <expand macro="cv_groups" />
                </when>
                <when value="GroupShuffleSplit">
                    <expand macro="cv_n_splits" value="5" />
                    <expand macro="cv_test_size" />
                    <expand macro="random_state" />
                    <expand macro="cv_groups" />
                </when>
                <when value="LeaveOneGroupOut">
                    <expand macro="cv_groups" />
                </when>
                <when value="LeavePGroupsOut">
                    <param argument="n_groups" type="integer" value="" label="n_groups" help="Number of groups (p) to leave out in the test split." />
                    <expand macro="cv_groups" />
                </when>
            </expand>
        </conditional>
    </xml>

    <xml name="cv_reduced" token_label="Select the cv splitter">
        <conditional name="cv_selector">
            <param name="selected_cv" type="select" label="@LABEL@">
                <expand macro="cv_splitter" />
            </param>
            <expand macro="cv_splitter_options" />
        </conditional>
    </xml>

    <xml name="cv_n_splits" token_value="3" token_help="Number of folds. Must be at least 2.">
        <param argument="n_splits" type="integer" value="@VALUE@" min="1" label="n_splits" help="@HELP@" />
    </xml>

    <xml name="cv_shuffle">
        <param argument="shuffle" type="boolean" optional="true" truevalue="booltrue" falsevalue="boolfalse" checked="false" label="Whether to shuffle data before splitting" />
    </xml>

    <xml name="cv_test_size" token_value="0.2">
        <param argument="test_size" type="float" value="@VALUE@" min="0.0" label="Portion or number of the test set" help="0.0-1.0, proportion of the dataset to include in the test split; >1, integer only, the absolute number of test samples " />
    </xml>

    <xml name="cv_groups">
        <section name="groups_selector" title="Groups column selector" expanded="true">
            <param name="infile_g" type="data" format="tabular" label="Choose dataset containing groups info:" />
            <param name="header_g" type="boolean" optional="true" truevalue="booltrue" falsevalue="boolfalse" checked="False" label="Does the dataset contain header:" />
            <conditional name="column_selector_options_g">
                <expand macro="samples_column_selector_options" column_option="selected_column_selector_option_g" col_name="col_g" multiple="False" infile="infile_g" />
            </conditional>
        </section>
    </xml>

    <xml name="train_test_split_params">
        <conditional name="split_algos">
            <param name="shuffle" type="select" label="Select the splitting method">
                <option value="None">No shuffle</option>
                <option value="simple" selected="true">ShuffleSplit</option>
                <option value="stratified">StratifiedShuffleSplit -- target values serve as class labels</option>
                <option value="group">GroupShuffleSplit or split by group names</option>
            </param>
            <when value="None">
                <expand macro="train_test_split_test_size" />
            </when>
            <when value="simple">
                <expand macro="train_test_split_test_size" />
                <expand macro="random_state" />
            </when>
            <when value="stratified">
                <expand macro="train_test_split_test_size" />
                <expand macro="random_state" />
            </when>
            <when value="group">
                <expand macro="train_test_split_test_size" optional="true" />
                <expand macro="random_state" />
                <param argument="group_names" type="text" value="" optional="true" label="Type in group names instead" help="For example: chr6, chr7. This parameter is optional. If used, it will override the holdout size and random seed." />
                <yield />
            </when>
        </conditional>
        <!--param argument="train_size" type="float" optional="True" value="" label="Train size:"/>-->
    </xml>

    <xml name="train_test_split_test_size" token_optional="false">
        <param name="test_size" type="float" value="0.2" optional="@OPTIONAL@" label="Holdout size" help="Leass than 1, for preportion; greater than 1 (integer), for number of samples." />
    </xml>

    <xml name="feature_selection_algorithms">
        <option value="SelectKBest" selected="true">SelectKBest - Select features according to the k highest scores</option>
        <option value="GenericUnivariateSelect">GenericUnivariateSelect - Univariate feature selector with configurable strategy</option>
        <option value="SelectPercentile">SelectPercentile - Select features according to a percentile of the highest scores</option>
        <option value="SelectFpr">SelectFpr - Filter: Select the p-values below alpha based on a FPR test</option>
        <option value="SelectFdr">SelectFdr - Filter: Select the p-values for an estimated false discovery rate</option>
        <option value="SelectFwe">SelectFwe - Filter: Select the p-values corresponding to Family-wise error rate</option>
        <option value="VarianceThreshold">VarianceThreshold - Feature selector that removes all low-variance features</option>
        <option value="SelectFromModel">SelectFromModel - Meta-transformer for selecting features based on importance weights</option>
        <option value="RFE">RFE - Feature ranking with recursive feature elimination</option>
        <option value="RFECV">RFECV - Feature ranking with recursive feature elimination and cross-validated selection of the best number of features</option>
        <yield />
    </xml>

    <xml name="feature_selection_algorithm_details">
        <when value="GenericUnivariateSelect">
            <expand macro="feature_selection_score_function" />
            <section name="options" title="Advanced Options" expanded="False">
                <param argument="mode" type="select" label="Feature selection mode">
                    <option value="percentile">percentile</option>
                    <option value="k_best">k_best</option>
                    <option value="fpr">fpr</option>
                    <option value="fdr">fdr</option>
                    <option value="fwe">fwe</option>
                </param>
                <param argument="param" type="float" value="" optional="true" label="Parameter of the corresponding mode" help="float or int depending on the feature selection mode" />
            </section>
        </when>
        <when value="SelectPercentile">
            <expand macro="feature_selection_score_function" />
            <section name="options" title="Advanced Options" expanded="False">
                <param argument="percentile" type="integer" value="10" optional="True" label="Percent of features to keep" />
            </section>
        </when>
        <when value="SelectKBest">
            <expand macro="feature_selection_score_function" />
            <section name="options" title="Advanced Options" expanded="False">
                <param argument="k" type="integer" value="10" optional="True" label="Number of top features to select" help="No 'all' option is supported." />
            </section>
        </when>
        <when value="SelectFpr">
            <expand macro="feature_selection_score_function" />
            <section name="options" title="Advanced Options" expanded="False">
                <param argument="alpha" type="float" value="" optional="True" label="Alpha" help="The highest p-value for features to be kept." />
            </section>
        </when>
        <when value="SelectFdr">
            <expand macro="feature_selection_score_function" />
            <section name="options" title="Advanced Options" expanded="False">
                <param argument="alpha" type="float" value="" optional="True" label="Alpha" help="The highest uncorrected p-value for features to keep." />
            </section>
        </when>
        <when value="SelectFwe">
            <expand macro="feature_selection_score_function" />
            <section name="options" title="Advanced Options" expanded="False">
                <param argument="alpha" type="float" value="" optional="True" label="Alpha" help="The highest uncorrected p-value for features to keep." />
            </section>
        </when>
        <when value="VarianceThreshold">
            <section name="options" title="Options" expanded="False">
                <param argument="threshold" type="float" value="0.0" optional="True" label="Threshold" help="Features with a training-set variance lower than this threshold will be removed." />
            </section>
        </when>
    </xml>

    <xml name="feature_selection_SelectFromModel">
        <when value="SelectFromModel">
            <conditional name="model_inputter">
                <param name="input_mode" type="select" label="Construct a new estimator from a selection list?">
                    <option value="new" selected="true">Yes</option>
                    <option value="prefitted">No. Load a prefitted estimator</option>
                </param>
                <when value="new">
                    <expand macro="estimator_selector_fs" />
                </when>
                <when value="prefitted">
                    <param name="fitted_estimator" type="data" format='zip' label="Load a prefitted estimator" />
                </when>
            </conditional>
            <expand macro="feature_selection_SelectFromModel_options" />
        </when>
    </xml>

    <xml name="feature_selection_SelectFromModel_no_prefitted">
        <when value="SelectFromModel">
            <conditional name="model_inputter">
                <param name="input_mode" type="select" label="Construct a new estimator from a selection list?">
                    <option value="new" selected="true">Yes</option>
                </param>
                <when value="new">
                    <expand macro="estimator_selector_all" />
                </when>
            </conditional>
            <expand macro="feature_selection_SelectFromModel_options" />
        </when>
    </xml>

    <xml name="feature_selection_SelectFromModel_options">
        <section name="options" title="Advanced Options" expanded="False">
            <param argument="threshold" type="text" value="" optional="true" label="threshold" help="The threshold value to use for feature selection. e.g. 'mean', 'median', '1.25*mean'." />
            <param argument="norm_order" type="integer" value="1" label="norm_order" help="Order of the norm used to filter the vectors of coefficients below threshold in the case where the coef_ attribute of the estimator is of dimension 2. " />