annotate macros.xml @ 0:bd808d1c4e0c draft default tip

planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/flexynesis commit b6763da7273957b7362787b7fdc6af5572161adb

<macros>
    <token name="@TOOL_VERSION@">0.2.10</token>
    <token name="@VERSION_SUFFIX@">0</token>
    <token name="@PROFILE@">24.1</token>
    <xml name="requirements">
        <requirements>
            <requirement type="package" version="@TOOL_VERSION@">flexynesis</requirement>
            <yield/>
        </requirements>
    </xml>
    <xml name="edam">
        <edam_topics>
            <edam_topic>topic_0622</edam_topic>
            <edam_topic>topic_3474</edam_topic>
            <edam_topic>topic_2640</edam_topic>
        </edam_topics>
        <edam_operations>
            <edam_operation>operation_3197</edam_operation>
            <edam_operation>operation_2403</edam_operation>
            <edam_operation>operation_2426</edam_operation>
        </edam_operations>
    </xml>
    <token name="@CHECK_NON_COMMERCIAL_USE@"><![CDATA[
        #if not $non_commercial_use
            >&2 echo "this tool is only available for non commercial use";
            exit 1;
        #end if
    ]]></token>
    <xml name="main_inputs">
        <param name="train_clin" type="data" format="csv" label="Training clinical data"/>
        <param name="test_clin" type="data" format="csv" label="Test clinical data"/>
        <param name="train_omics_main" type="data" format="csv" label="Training omics data"/>
        <param name="test_omics_main" type="data" format="csv" label="Test omics data"/>
        <param name="assay_main" type="text" optional="true" label="What type of assay is your input?" help="This would be used as output name.">
            <sanitizer invalid_char=" ">
                <valid initial="string.letters">
                    <add value="_" />
                </valid> 
            </sanitizer>
        </param>
    </xml>
    <xml name="extra_inputs">
        <param name="train_omics" type="data" optional="true" format="csv" label="Training omics data"/>
        <param name="test_omics" type="data" optional="true" format="csv" label="Test omics data"/>
        <param name="assay" type="text" optional="true" label="What type of assay is your input?" help="This would be used as output name." >
            <sanitizer invalid_char=" ">
                <valid initial="string.letters">
                    <add value="_" /> 
                </valid>
            </sanitizer>
        </param>
    </xml>
    <xml name="advanced">
        <section name="advanced" title="Advanced Options">
            <param argument="--fusion_type" type="select" label="Fusion method" help="How to fuse the omics layers?">
                <option value="intermediate">intermediate</option>
                <option value="early">early</option>
            </param>
            <param argument="--finetuning_samples" type="integer" min="0" value="0" label="Number of samples from the test dataset to use for fine-tuning the model." help="Set to 0 to disable fine-tuning." />
            <param argument="--variance_threshold" type="float" min="0" max="100" value="1" label="Variance threshold (as percentile) to drop low variance features." help="Set to 0 for no variance filtering." />
            <param argument="--correlation_threshold" type="float" min="0" max="1" value="0.8" label="Correlation threshold to drop highly redundant features." help="Set to 1 for no redundancy filtering." />
            <param argument="--subsample" type="integer" min="0" value="0" label="Downsample training set to randomly drawn N samples for training." />
            <param argument="--features_min" type="integer" min="0" value="500" label="Minimum number of features to retain after feature selection." />
            <param argument="--features_top_percentile" type="float" min="0" max="100" value="20" label="Top percentile features (among the features remaining after variance filtering and data cleanup) to retain after feature selection." />
            <param argument="--log_transform" type="boolean" truevalue="--log_transform True" falsevalue="" checked="false" label="Whether to apply log-transformation to input data matrices" />
            <param argument="--early_stop_patience" type="integer" min="-1" value="10" label="How many epochs to wait when no improvements in validation loss are observed." help="Set to -1 to disable early stopping." />
            <param argument="--hpo_iter" type="integer" min="1" value="100" label="Number of iterations for hyperparameter optimisation." />
            <param argument="--hpo_patience" type="integer" min="0" value="10" label="How many hyperparameter optimisation iterations to wait for when no improvements are observed." help="Set to 0 to disable early stopping." />
            <param argument="--use_cv" type="boolean" truevalue="--use_cv" falsevalue="" checked="false" label="Cross validation" help="If set, a 5-fold cross-validation training will be done. Otherwise, a single training on 80 percent of the dataset is done. " />
            <param argument="--use_loss_weighting" type="boolean" truevalue="--use_loss_weighting True" falsevalue="" checked="true" label="Whether to apply loss-balancing using uncertainty weights method." />
            <param argument="--evaluate_baseline_performance" type="boolean" truevalue="--evaluate_baseline_performance" falsevalue="" checked="false" label="Enable modeling also with Random Forest + SVMs to see the performance of off-the-shelf tools on the same dataset." />
            <param argument="--disable_marker_finding" type="boolean" truevalue="--disable_marker_finding" falsevalue="" checked="false" label="Disable marker discovery after model training." />
        </section>
    </xml>
    <xml name="citations">
        <citations>
            <citation type="doi">10.1101/2024.07.16.603606</citation>
        </citations>
    </xml>
</macros>