Galaxy Machine Learning

Welcome to the Galaxy for research in AI, statistics and prediction hub

The Galaxy for research in AI, statistics and prediction is a hub of tools, workflows and training materials for dedicated machine learning tasks such as data preprocessing, classification, regression, clustering, fine-tuning biological foundation models and visualisation to achieve end-to-end varied machine learning analyses. The complete set of resources are available on the Galaxy platform, which guarantees simple access, easy extension, flexible adaptation to personal needs, accelerated model training, and sophisticated and reproducible machine learning analyses independent of command-line knowledge.

The hub provides you with a Swiss Army knife of Scikit-learn, Keras (a deep learning library based on TensorFlow), PyTorch and various other tools to transform, learn and predict and plot your data.

The hub is mainly developed by the Goecks Lab and the European Galaxy project. The German Network for Bioinformatics Infrastructure (de.NBI), which runs the German ELIXIR Node, provides the necessary compute clusters with CPUs and GPU resources.

This project is a community effort, so feel free to jump in, ask questions, and contribute to the development of new tools, workflows, training materials, and research. Learn, share ideas, and grow with the community along the way!

Get started

Are you new to Galaxy, or returning after a long time, and looking for help to get started? Take a guided tour through Galaxy’s user interface.

Training

We are passionate about training. So we are working in close collaboration with the Galaxy Training Network (GTN) to develop training materials of data analyses based on Galaxy (Batut et al. 2017). These materials hosted on the GTN GitHub repository are available online at https://training.galaxyproject.org.

Want to learn more about machine learning? Take one of our guided tours or check out the following hands-on tutorials, developed together with the GTN “Statistics and machine learning” community.

Lesson	Slides	Hands-on	Input dataset	Workflows
Introduction to machine learning
Classification
Multi-omics classification (Flexynesis)
Regression
Clustering
Deep Learning (Part 1) - Feedforward neural networks (FNN)
Deep Learning (Part 2) - Recurrent neural networks (RNN)
Deep Learning (Part 3) - Convolutional neural networks (CNN)
GLEAM Image Learner - Validating Skin Lesion Classification
Fine-tune biological foundation model (protein language models)

Available tools

In this section we list the most important tools that have been integrated into the machine learning hub. There are many more tools available so please have a more detailed look at the tool panel. For better readability, we have divided them into categories.

Classification

Identifying which category an object belongs to.

Tool	Description	Reference
flexynesis	Flexynesis: deep learning tool for multi-omics data	Uyar et al. 2025
tabpfn	Tabular data classification using TabPFN	Hollmann et al. 2025
sklearn_svm_classifier	Support vector machines (SVMs) for classification	Pedregosa et al. 2011
sklearn_nn_classifier	Nearest Neighbors Classification	Pedregosa et al. 2011
sklearn_ensemble	Ensemble methods for classification and regression	Pedregosa et al. 2011
sklearn_discriminant_classifier	Linear and Quadratic Discriminant Analysis	Pedregosa et al. 2011
sklearn_generalized_linear	Generalized linear models for classification and regression	Pedregosa et al. 2011
sklearn_clf_metrics	Calculate metrics for classification performance	Pedregosa et al. 2011

Regression

Predicting a continuous-valued attribute associated with an object.

Tool	Description	Reference
tabpfn	Tabular data regression using TabPFN	Hollmann et al. 2025
sklearn_ensemble	Ensemble methods for classification and regression	Pedregosa et al. 2011
sklearn_generalized_linear	Generalized linear models for classification and regression	Pedregosa et al. 2011
sklearn_regression_metrics	Calculate metrics for regression performance	Pedregosa et al. 2011

Unsupervised/Clustering

Automatic grouping of similar objects into sets.

Tool	Description	Reference
flexynesis	Flexynesis: deep learning tool for multi-omics data	Uyar et al. 2025
sklearn_numeric_clustering	Different numerical clustering algorithms	Pedregosa et al. 2011

Model building

Building general machine learning models.

Tool	Description	Reference
sklearn_estimator_attributes	Estimator attributes to get all attributes from an estimator or scikit object	Pedregosa et al. 2011
sklearn_stacking_ensemble_models	Stacking Ensembles to build stacking, voting ensemble models with numerous base options	Pedregosa et al. 2011
sklearn_searchcv	Hyperparameter Search performs hyperparameter optimization using various SearchCVs	Pedregosa et al. 2011
sklearn_build_pipeline	Pipeline Builder as an all-in-one platform to build pipeline, single estimator, preprocessor and custom wrappers	Pedregosa et al. 2011

Model evaluation

Evaluation, validating and choosing parameters and models.

Tool	Description	Reference
sklearn_model_validation	Model Validation includes cross_validate, cross_val_predict, learning_curve, and more	Pedregosa et al. 2011
sklearn_pairwise_metrics	Evaluate pairwise distances or compute affinity or kernel for sets of samples	Pedregosa et al. 2011
sklearn_train_test_eval	Train, Test and Evaluation to fit a model using part of dataset and evaluate using the rest	Pedregosa et al. 2011
model_prediction	Model Prediction predicts on new data using a pre-fitted model	Chollet et al. 2011
sklearn_fitted_model_eval	Evaluate a Fitted Model using a new batch of labeled data	Pedregosa et al. 2011
sklearn_model_fit	Fit a Pipeline, Ensemble or other models using a labeled dataset	Pedregosa et al. 2011

Preprocessing and feature selection

Feature selection and preprocessing.

Tool	Description	Reference
cleanlab	Detect and optionally clean data issues using Cleanlab	Northcutt et al. 2021
sklearn_data_preprocess	Preprocess raw feature vectors into standardized datasets	Pedregosa et al. 2011
sklearn_feature_selection	Feature Selection module, including univariate filter selection methods and recursive feature elimination algorithm	Pedregosa et al. 2011

Deep learning

Build and use deep neural networks.

Tool	Description	Reference
image_learner	Image Learner: image classification	Khai Van Dang et al. 2026
keras_batch_models	Build Deep learning Batch Training Models with online data generator for Genomic/Protein sequences and images	Chollet et al. 2011
keras_model_builder	Create deep learning model with an optimizer, loss function and fit parameters	Chollet et al. 2011
keras_model_config	Create a deep learning model architecture using Keras	Chollet et al. 2011
keras_train_and_eval	Deep learning training and evaluation either implicitly or explicitly	Chollet et al. 2011

Visualization

Plotting and visualization.

Tool	Description	Reference
plotly_regression_performance_plots	Plot actual vs predicted curves and residual plots of tabular data
plotly_ml_performance_plots	Plot confusion matrix, precision, recall and ROC and AUC curves of tabular data
ml_visualization_ex	Machine Learning Visualization Extension includes several types of plotting for machine learning	Chollet et al. 2011

Utilities

General data and table manipulation tools.

Tool	Description	Reference
table_compute	The power of the pandas data library for manipulating and computing expressions upon tabular data and matrices.
datamash_ops	Datamash operations on tabular data
datamash_transpose	Transpose rows/columns in a tabular file
sklearn_sample_generator	Generate random samples with controlled size and complexity	Pedregosa et al. 2011
sklearn_train_test_split	Split Dataset into training and test subsets	Pedregosa et al. 2011

Interactive Environments

You have done the heavy lifting and now want to use your coding skills inside Jupyter or RStudio? Work on data with the following:

Tool	Description	Reference
GPU-enabled JupyterLab	GPU-enabled JupyterLab
Jupyter	Jupyter lab
RStudio	RStudio

Contributors

Our Data Policy

Registered Users	Unregistered Users	FTP Data	GDPR Compliance
For all different storage options, for detailed explanations of data retention policies, and ways how to increase your quota please refer to our dedicated storage site.	Processed data will only be accessible during one browser session, using a cookie to identify your data. This cookie is not used for any other purposes (e.g. tracking or analytics). If UseGalaxy.eu service is not accessed for 90 days, those datasets will be permanently deleted.	Any user data uploaded to our FTP server should be imported into Galaxy as soon as possible. Data left in FTP folders for more than 3 months, will be deleted.	The Galaxy service complies with the EU General Data Protection Regulation (GDPR). You can read more about this on our Terms and Conditions.