diff multimodal_learner.xml @ 0:375c36923da1 draft default tip

planemo upload for repository https://github.com/goeckslab/gleam.git commit 1c6c1ad7a1b2bd3645aa0eafa2167784820b52e0

--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/multimodal_learner.xml	Tue Dec 09 23:49:47 2025 +0000
@@ -0,0 +1,316 @@
+<tool id="multimodal_learner" name="Multimodal Learner" version="0.1.0" profile="22.01">
+  <description>Train and evaluate an AutoGluon Multimodal model (tabular + image + text)</description>
+
+  <requirements>
+    <container type='docker'>quay.io/goeckslab/multimodal-learner:1.4.0</container>
+  </requirements>
+
+  <required_files>
+    <include path="multimodal_learner.py"/>
+    <include path="utils.py"/>
+    <include path="split_logic.py"/>
+    <include path="training_pipeline.py"/>
+    <include path="test_pipeline.py"/>
+    <include path="metrics_logic.py"/>
+    <include path="plot_logic.py"/>
+    <include path="report_utils.py"/>
+    <include path="feature_help_modal.py"/>
+  </required_files>
+
+  <stdio>
+    <exit_code range="137" level="fatal_oom" description="Out of Memory"/>
+    <exit_code range="1:" level="fatal" description="Tool failed — see Tool Standard Error"/>
+  </stdio>
+
+  <command detect_errors="exit_code"><![CDATA[
+#import re
+
+#set $image_zip_paths = []
+#if $use_images_conditional.use_images == "yes"
+  #for $zip_file in $use_images_conditional.images_zip_repeat
+    #set $image_zip_paths = $image_zip_paths + [$zip_file.images_zip]
+  #end for
+#end if
+#if len($image_zip_paths) > 0
+  #set $images_zip_cli = " ".join(["'%s'" % z for z in $image_zip_paths])
+#else
+  #set $images_zip_cli = None
+#end if
+
+set -e;
+ln -sf '$input_csv' 'train_input.csv';
+#if $test_dataset_conditional.has_test_dataset == "yes"
+ln -sf '$test_dataset_conditional.input_test' 'test_input.csv';
+#end if
+
+python '$__tool_directory__/multimodal_learner.py'
+  --input_csv_train 'train_input.csv'
+  #if $test_dataset_conditional.has_test_dataset == "yes"
+  --input_csv_test 'test_input.csv'
+  #end if
+  --target_column '$target_column'
+
+  #if $use_images_conditional.use_images == "yes"
+    #if $images_zip_cli
+    --images_zip $images_zip_cli
+    #end if
+    --missing_image_strategy '$use_images_conditional.missing_image_strategy'
+    #if $use_images_conditional.backbone_image
+    --backbone_image '$use_images_conditional.backbone_image'
+    #end if
+  #end if
+
+  #if $backbone_text not in ("", None)
+  --backbone_text '$backbone_text'
+  #end if
+
+  --preset '$preset'
+  --eval_metric '$eval_metric'
+
+  --random_seed '$random_seed'
+  #if $time_limit
+  --time_limit $time_limit
+  #end if
+  #if $deterministic == "true"
+  --deterministic
+  #end if
+
+  #if $customize_defaults_conditional.customize_defaults == "yes"
+    #if $customize_defaults_conditional.validation_size not in ("", None)
+      --validation_size $customize_defaults_conditional.validation_size
+    #end if
+    #if $customize_defaults_conditional.split_probabilities and str($customize_defaults_conditional.split_probabilities).strip()
+      --split_probabilities #echo " ".join([str(float(x)) for x in str($customize_defaults_conditional.split_probabilities).replace(",", " ").split() if x.strip()]) #
+    #end if
+    #if $customize_defaults_conditional.cross_validation == "true"
+      --cross_validation true
+      --num_folds $customize_defaults_conditional.num_folds
+    #end if
+    #if $customize_defaults_conditional.epochs
+      --epochs $customize_defaults_conditional.epochs
+    #end if
+    #if $customize_defaults_conditional.learning_rate
+      --learning_rate $customize_defaults_conditional.learning_rate
+    #end if
+    #if $customize_defaults_conditional.batch_size
+      --batch_size $customize_defaults_conditional.batch_size
+    #end if
+    #if $customize_defaults_conditional.threshold
+      --threshold $customize_defaults_conditional.threshold
+    #end if
+    #if $customize_defaults_conditional.hyperparameters
+      --hyperparameters '$customize_defaults_conditional.hyperparameters'
+    #end if
+  #end if
+
+  --output_json '$output_json'
+  --output_html '$output_html'
+  --output_config '$output_config'
+]]></command>
+
+  <inputs>
+    <param name="input_csv" type="data" format="csv,tsv" label="Training dataset (CSV/TSV)" help="Must contain the target column and optional image paths"/>
+    <param name="target_column" type="data_column" data_ref="input_csv" numerical="false" use_header_names="true" label="Target / Label column"/>
+
+    <conditional name="test_dataset_conditional">
+      <param name="has_test_dataset" type="boolean" truevalue="yes" falsevalue="no" checked="false" label="Provide separate test dataset?"/>
+      <when value="yes">
+        <param name="input_test" type="data" format="csv,tsv" optional="true" label="Test dataset (CSV/TSV)"/>
+      </when>
+      <when value="no"/>
+    </conditional>
+
+    <param name="backbone_text" type="select" label="Text backbone" optional="true">
+      <option value="microsoft/deberta-v3-base" selected="true">microsoft/deberta-v3-base</option>
+      <option value="microsoft/deberta-v3-small">microsoft/deberta-v3-small</option>
+      <option value="google/electra-base-discriminator">google/electra-base-discriminator</option>
+      <option value="google/electra-small-discriminator">google/electra-small-discriminator</option>
+      <option value="roberta-base">roberta-base</option>
+      <option value="bert-base-uncased">bert-base-uncased</option>
+      <option value="distilroberta-base">distilroberta-base</option>
+      <option value="albert-base-v2">albert-base-v2</option>
+    </param>
+
+    <conditional name="use_images_conditional">
+      <param name="use_images" type="boolean" truevalue="yes" falsevalue="no" checked="false" label="Use image modality?"/>
+      <when value="yes">
+        <repeat name="images_zip_repeat" title="Image archive(s)" min="1">
+          <param name="images_zip" type="data" format="zip" label="ZIP file containing images"/>
+        </repeat>
+        <param name="backbone_image" type="select" label="Image backbone" optional="true">
+          <option value='swin_base_patch4_window7_224' selected='true'>swin_base_patch4_window7_224</option>
+          <option value='swin_large_patch4_window12_384.in22k_ft_in1k'>swin_large_patch4_window12_384.in22k_ft_in1k</option>
+          <option value='swin_small_patch4_window7_224'>swin_small_patch4_window7_224</option>
+          <option value='swin_tiny_patch4_window7_224'>swin_tiny_patch4_window7_224</option>
+          <option value='caformer_b36.in21k_ft_in1k'>caformer_b36.in21k_ft_in1k</option>
+          <option value='caformer_m36.in21k_ft_in1k'>caformer_m36.in21k_ft_in1k</option>
+          <option value='caformer_s36.in21k_ft_in1k'>caformer_s36.in21k_ft_in1k</option>
+          <option value='caformer_s18.in1k'>caformer_s18.in1k</option>
+          <option value='caformer_b36.sail_in22k_ft_in1k'>caformer_b36.sail_in22k_ft_in1k</option>
+          <option value='caformer_m36.sail_in22k_ft_in1k'>caformer_m36.sail_in22k_ft_in1k</option>
+          <option value='caformer_s36.sail_in22k_ft_in1k'>caformer_s36.sail_in22k_ft_in1k</option>
+          <option value='vit_base_patch16_224'>vit_base_patch16_224</option>
+          <option value='vit_large_patch14_224'>vit_large_patch14_224</option>
+          <option value='convnext_base'>convnext_base</option>
+          <option value='eva02_base_patch14_448.mim_in22k_ft_in22k_in1k'>eva02_base_patch14_448.mim_in22k_ft_in22k_in1k</option>
+          <option value='resnet50'>resnet50</option>
+        </param>
+        <param name="missing_image_strategy" type="boolean" truevalue="true" falsevalue="false" checked="false"
+               label="Drop rows with missing images?" help="True = drop, False = replace with placeholder (default)"/>
+      </when>
+      <when value="no"/>
+    </conditional>
+
+    <param name="preset" type="select" label="Quality preset">
+      <option value="medium_quality" selected="true">Medium quality (fast)</option>
+      <option value="high_quality">High quality</option>
+      <option value="best_quality">Best quality (slowest)</option>
+    </param>
+
+    <param name="eval_metric" type="select" label="Primary evaluation metric">
+      <option value="auto" selected="true">Auto (let AutoGluon choose)</option>
+      <option value="roc_auc">ROC AUC</option>
+      <option value="accuracy">Accuracy</option>
+      <option value="balanced_accuracy">Balanced Accuracy</option>
+      <option value="f1">F1</option>
+      <option value="f1_macro">F1 Macro</option>
+      <option value="f1_micro">F1 Micro</option>
+      <option value="f1_weighted">F1 Weighted</option>
+      <option value="precision">Precision</option>
+      <option value="precision_macro">Precision Macro</option>
+      <option value="precision_micro">Precision Micro</option>
+      <option value="precision_weighted">Precision Weighted</option>
+      <option value="recall">Recall</option>
+      <option value="recall_macro">Recall Macro</option>
+      <option value="recall_micro">Recall Micro</option>
+      <option value="recall_weighted">Recall Weighted</option>
+      <option value="average_precision">Average Precision</option>
+      <option value="roc_auc_ovo_macro">ROC AUC OVO Macro</option>
+      <option value="roc_auc_ovo_weighted">ROC AUC OVO Weighted</option>
+      <option value="roc_auc_ovr_macro">ROC AUC OVR Macro</option>
+      <option value="roc_auc_ovr_weighted">ROC AUC OVR Weighted</option>
+      <option value="log_loss">Log Loss</option>
+      <option value="mse">MSE</option>
+      <option value="rmse">RMSE</option>
+      <option value="mae">MAE</option>
+      <option value="msle">MSLE</option>
+      <option value="r2">R2</option>
+    </param>
+
+    <param name="random_seed" type="integer" value="42" label="Random seed"/>
+
+    <param name="time_limit" type="integer" optional="true" min="60" label="Time limit (seconds)" help="Total training time budget. Recommended: 3600+ for real runs"/>
+    <param name="deterministic" type="boolean" truevalue="true" falsevalue="false" checked="false"
+           label="Enable deterministic mode" help="Use deterministic algorithms and CuDNN settings to reduce run-to-run variance (may slow training)"/>
+
+    <conditional name="customize_defaults_conditional">
+      <param name="customize_defaults" type="boolean" truevalue="yes" falsevalue="no" checked="false" label="Advanced: customize training settings?"/>
+      <when value="yes">
+        <param name="validation_size" type="float" value="0.2" label="Validation fraction (when test set provided)"/>
+        <param name="split_probabilities" type="text" value="0.7 0.1 0.2" label="Train / Val / Test split (space-separated) when no test set"/>
+        <param name="cross_validation" type="boolean" truevalue="true" falsevalue="false" checked="false" label="Enable k-fold cross-validation"/>
+        <param name="num_folds" type="integer" value="5" label="Number of CV folds"/>
+        <param name="epochs" type="integer" optional="true" label="Max epochs"/>
+        <param name="learning_rate" type="float" optional="true" label="Learning rate"/>
+        <param name="batch_size" type="integer" optional="true" label="Batch size"/>
+        <param name="threshold" type="float" optional="true" min="0" max="1" label="Binary classification threshold"/>
+        <param name="hyperparameters" type="text" optional="true" label="Extra AutoGluon hyperparameters (JSON or YAML string)"/>
+      </when>
+      <when value="no"/>
+    </conditional>
+  </inputs>
+
+  <outputs>
+    <data name="output_html" format="html" label="Multimodal Learner analysis report on data ${input_csv.name}"/>
+    <data name="output_config" format="yaml" label="Multimodal Learner training config on data ${input_csv.name}"/>
+    <data name="output_json" format="json" label="Multimodal Learner metric results on data ${input_csv.name}"/>
+  </outputs>
+
+  <tests>
+    <!-- Basic run with images + external test set -->
+    <test expect_num_outputs="3">
+      <param name="input_csv" value="train.csv"/>
+      <param name="target_column" value="7"/>
+      <param name="test_dataset_conditional|has_test_dataset" value="yes"/>
+      <param name="test_dataset_conditional|input_test" value="test.csv"/>
+      <param name="use_images_conditional|use_images" value="yes"/>
+      <param name="use_images_conditional|images_zip_repeat_0|images_zip" value="images.zip"/>
+      <param name="use_images_conditional|backbone_image" value="resnet50"/>
+      <param name="backbone_text" value="google/electra-base-discriminator"/>
+      <output name="output_html">
+        <assert_contents>
+          <has_text text="Model Performance Summary"/>
+        </assert_contents>
+      </output>
+    </test>
+
+    <!-- Custom threshold -->
+    <test expect_num_outputs="3">
+      <param name="input_csv" value="train.csv"/>
+      <param name="target_column" value="7"/>
+      <param name="test_dataset_conditional|has_test_dataset" value="yes"/>
+      <param name="test_dataset_conditional|input_test" value="test.csv"/>
+      <param name="use_images_conditional|use_images" value="yes"/>
+      <param name="use_images_conditional|images_zip_repeat_0|images_zip" value="images.zip"/>
+      <param name="customize_defaults_conditional|customize_defaults" value="yes"/>
+      <param name="customize_defaults_conditional|threshold" value="0.4"/>
+      <output name="output_json">
+        <assert_contents>
+          <has_text text="&quot;threshold&quot;: 0.4"/>
+        </assert_contents>
+      </output>
+    </test>
+
+    <!-- No external test set; internal split -->
+    <test expect_num_outputs="3">
+      <param name="input_csv" value="train.csv"/>
+      <param name="target_column" value="7"/>
+      <param name="test_dataset_conditional|has_test_dataset" value="no"/>
+      <param name="use_images_conditional|use_images" value="yes"/>
+      <param name="use_images_conditional|images_zip_repeat_0|images_zip" value="images.zip"/>
+      <output name="output_json">
+        <assert_contents>
+          <has_text text="&quot;val&quot;"/>
+        </assert_contents>
+      </output>
+    </test>
+
+    <!-- Text/tabular only (ignore images) -->
+    <test expect_num_outputs="3">
+      <param name="input_csv" value="train.csv"/>
+      <param name="target_column" value="7"/>
+      <param name="test_dataset_conditional|has_test_dataset" value="yes"/>
+      <param name="test_dataset_conditional|input_test" value="test.csv"/>
+      <param name="use_images_conditional|use_images" value="no"/>
+      <output name="output_html">
+        <assert_contents>
+          <has_text text="Train and Validation Performance Summary"/>
+        </assert_contents>
+      </output>
+    </test>
+  </tests>
+
+  <help><![CDATA[
+**AutoGluon Multimodal Learner**
+
+Trains a powerful multimodal model combining tabular features, images, and text using AutoGluon-Multimodal.
+
+- Handles missing images intelligently
+- Supports cross-validation
+- Produces detailed HTML reports and transparent metrics
+- Fully reproducible
+
+Ideal for medical imaging + clinical data, product images + descriptions, etc.
+]]></help>
+
+  <citations>
+    <citation type="bibtex">
+@article{AutoGluon2023,
+  author = {Erickson, Nick and Mueller, Jonas and Wang, Yizhou and others},
+  title = {AutoGluon-Tabular: Robust and Accurate AutoML for Structured Data},
+  journal = {arXiv preprint arXiv:2003.06505},
+  year = {2023}
+}
+    </citation>
+  </citations>
+</tool>