Statistics and machine learning

🛠️ GLEAM Multimodal Learner - HANCOCK recurrence prediction

2026-03-25T09:45:47+00:00

Train and evaluate a HANCOCK recurrence model with Multimodal Learner

🖼️ Gleam Multimodal Learner - HNSCC Recurrence Prediction with HANCOCK

2026-03-25T09:45:47+00:00

Introduction to GLEAM Multimodal Learner

📚 Gleam Multimodal Learner - Head and Neck cancer Recurrence Prediction with HANCOCK

2026-03-25T09:45:47+00:00

In this tutorial, we use the HANCOCK head-and-neck cancer cohort (Dörrich et al. 2025) to build a recurrence prediction model with GLEAM Multimodal Learner.

🛠️ Image Learner - HAM10000

2026-01-28T12:35:24+00:00

🖼️ Gleam Image Learner - Validating Skin Lesion Classification on HAM10000

2026-01-28T12:35:24+00:00

Introduction to GLEAM Image Learner and Galaxy

📚 GLEAM Image Learner - Validating Skin Lesion Classification on HAM10000

2026-01-28T12:35:24+00:00

In this tutorial, we will use the HAM10000 (“Human Against Machine with 10,000 training images”) dataset to develop a deep learning classifier for dermoscopic skin lesion classification. The goal is to accurately classify seven types of pigmented skin lesions using the GLEAM Image Learner tool.

📅 Galaxy Training Academy 2026

Delphine Lariviere — 2026-01-21T17:14:51+00:00

The Galaxy Training Academy is a self-paced online training event for beginners and advanced learners who want to improve their data analysis skills in Galaxy and/or in popular fields in bioinformatics. Over the course of one week, we offer a diverse selection of learning tracks for you.

🛠️ Final - Survival Markers of Lower Grade

2025-08-13T15:40:49+00:00

This workflow shows Flexynesis usage for predicting survival markers from a multi-omics dataset

📚 Identifing Survival Markers of Brain tumor with Flexynesis

2025-08-13T15:40:49+00:00

Here, we use Flexynesis tool suite on a multi-omics dataset of 506 Brain Lower Grade Glioma (LGG) and 288 Glioblastoma Multiforme (GBM) samples with matching mutation and copy number alteration. This data were downloaded from the cBioPortal (cbioPortal community). The data was split into train (70% of the samples) and test (30% of the samples).

🛠️ Final - Modeling Breast Cancer Subtypes + TABPFN

2025-08-13T10:24:48+00:00

This WF applies Flexynesis on BRCA data from Metabric for a classification task

📚 Modeling Breast Cancer Subtypes with Flexynesis

2025-08-13T10:24:48+00:00

Flexynesis represents a state-of-the-art deep learning framework specifically designed for multi-modal data integration in biological research (Uyar et al. 2024). What sets Flexynesis apart is its comprehensive suite of deep learning architectures that can handle various data integration scenarios while providing robust feature selection and hyperparameter optimization.

🛠️ Final - Unsupervised Analysis of Bone Marrow Cells

2025-08-10T09:24:27+00:00

Unsupervised Classification of Bone marrow cells

📚 Unsupervised Analysis of Bone Marrow Cells with Flexynesis

2025-08-10T09:24:27+00:00

Traditional dimensionality reduction techniques, while useful, often fail to capture the complex non-linear relationships present in high-dimensional data. Deep learning approaches, particularly Variational Autoencoders (VAEs), have emerged as powerful tools for unsupervised analysis of single-cell transcriptomic data (Zhao et al. 2017). VAEs combine the representational power of neural networks with probabilistic modeling, enabling them to learn meaningful latent representations while accounting for the inherent uncertainty in biological data.

🛠️ Flexynesis - get data from Cbioportal

2025-08-10T09:16:32+00:00

Download data from cBioPortal and prepare it for Flexynesis

📚 Prepare Data from CbioPortal for Flexynesis Integration

2025-08-10T09:16:32+00:00

The cBioPortal is an open-access web platform that provides intuitive access to large-scale cancer genomics datasets Gao et al. 2013 cbioPortal community. Originally developed to make complex molecular profiling data more accessible to the broader research community, cBioPortal hosts data from thousands of cancer studies and tens of thousands of tumor samples.

🎥 Recording of Galaxy Tabular Learner - Building a Model using Chowell clinical data

2025-05-07T00:00:00+00:00

A 24M long recording is now available.

🖼️ Galaxy Tabular Learner: Building a Model using Chowell clinical data

2025-05-05T09:32:11+00:00

What you will do

📚 Pretraining a Large Language Model (LLM) from Scratch on DNA Sequences

2025-04-17T09:19:54+00:00

Generative Artificial Intelligence (AI) represents a cutting-edge domain within machine learning, focused on creating new, synthetic yet realistic data. This includes generating text, images, music, and even biological sequences. At the heart of many generative AI applications are Large Language Models (LLMs), which have revolutionized natural language processing and beyond.

📚 Generating Artificial Yeast DNA Sequences using a DNA LLM

2025-04-17T09:19:54+00:00

Generating synthetic DNA sequences using pre-trained language models bridges the fields of synthetic biology and artificial intelligence, enabling the creation of novel DNA sequences that closely mimic natural genomes. By leveraging the power of advanced language models, we can generate biologically relevant sequences that have the potential to revolutionize genetic engineering, drug discovery, and our understanding of genomic function.

📚 Fine-tuning a LLM for DNA Sequence Classification

2025-04-17T09:19:54+00:00

After preparing, training, and utilizing a language model for DNA sequences, we can now fine-tune a pre-trained Large Language Model (LLM) for specific DNA sequence classification tasks. Here, we will use a pre-trained model from Hugging Face, specifically the Mistral-DNA-v1-17M-hg38, and adapt it to classify DNA sequences based on their biological functions. Our objective is to classify sequences according to whether they bind to transcription factors.

📚 Predicting Mutation Impact with Zero-shot Learning using a pretrained DNA LLM

2025-04-17T09:19:54+00:00

Predicting the impact of mutations is a critical task in genomics, as it provides insights into how genetic variations influence biological functions and contribute to diseases. Traditional methods for assessing mutation impact often rely on extensive experimental data or computationally intensive simulations. However, with the advent of large language models (LLMs) and zero-shot learning, we can now predict mutation impacts more efficiently and effectively.

🎥 Recording of Introduction to Machine learning

2025-03-25T00:00:00+00:00

A 27M long recording is now available.

🎥 Recording of Fine tune large protein model (ProtTrans) using HuggingFace

2025-03-24T00:00:00+00:00

A 1H long recording is now available.

🎥 Recording of Classification in Machine Learning

2025-03-24T00:00:00+00:00

A 1H25M long recording is now available.

🖼️ Fine-tuning Protein Language Model

2025-03-21T13:40:33+00:00

Language Models (LM)

🖼️ Regression in Machine Learning

2025-03-21T13:40:33+00:00

Regression

🖼️ Classification in Machine Learning

2025-03-21T13:40:33+00:00

What is classification in machine learning?

🖼️ Introduction to Machine learning

2025-03-21T13:40:33+00:00

Contents

📚 Foundational Aspects of Machine Learning using Python

2025-03-11T17:21:16+00:00

Machine Learning is a subset of artificial intelligence that involves training algorithms to learn patterns from data and make predictions or decisions without being explicitly programmed. It has revolutionized various fields, from healthcare and finance to autonomous vehicles and natural language processing.

📚 Regulations/standards for AI using DOME

2025-03-11T17:21:16+00:00

With the significant drop in the cost of many high-throughput technologies, vast amounts of biological data are being generated and made available to researchers. Machine learning (ML) has emerged as a powerful tool for analyzing data related to cellular processes, genomics, proteomics, post-translational modifications, metabolism, and drug discovery, offering the potential for transformative medical advancements.

📅 Galaxy Training Academy 2025

Delphine Lariviere — 2025-02-10T19:40:45+00:00

The Galaxy Training Academy is a self-paced online training event for beginners and advanced learners who want to improve their Galaxy data analysis skills. Over the course of one week, we offer a diverse selection of learning track for you.

🛠️ Ludwig - Image recognition model - MNIST

2024-12-13T13:25:07+00:00

Generates LORIS LLR6 model

📚 Galaxy Tabular Learner - Building a Model using Chowell clinical data

2024-12-13T13:25:07+00:00

In this tutorial, we will build a new immunotherapy-response classifier with Galaxy Tabular Learner using a comprehensive dataset of patients treated with immune checkpoint blockade (ICB) and non-ICB-treated patients across 18 solid tumor types. The goal is to accurately predict patient responses to the treatment.

🛠️ Ludwig - Image recognition model - MNIST

2024-10-28T12:27:43+00:00

Deep Learning image classifier model

📚 Train and Test a Deep learning image classifier with Galaxy-Ludwig

2024-10-28T12:27:43+00:00

🎥 Recording of Deep Learning (Part 3) - Convolutional neural networks (CNN)

2024-10-05T00:00:00+00:00

A 45M long recording is now available.

🎥 Recording of Fine tune large protein model (ProtTrans) using HuggingFace

2024-08-29T00:00:00+00:00

A 35M long recording is now available.

🎥 Recording of Classification in Machine Learning

2024-08-29T00:00:00+00:00

A 1H7M long recording is now available.

📚 Fine tune large protein model (ProtTrans) using HuggingFace

2024-06-17T12:35:27+00:00

The advent of large language models has transformed the field of natural language processing, enabling machines to comprehend and generate human-like language with unprecedented accuracy. Pre-trained language models, such as BERT, RoBERTa, and their variants, have achieved state-of-the-art results on various tasks, from sentiment analysis and question answering to language translation and text classification. Moreover, the emergence of transformer-based models, such as Generative Pre-trained Transformer (GPT) and its variants, has enabled the creation of highly advanced language models to generate coherent and context-specific text. The latest iteration of these models, ChatGPT, has taken the concept of conversational AI to new heights, allowing users to engage in natural-sounding conversations with machines. However, despite their impressive capabilities, these models are imperfect, and their performance can be significantly improved through fine-tuning. Fine-tuning involves adapting the pre-trained model to a specific task or domain by adjusting its parameters to optimise its performance on a target dataset. This process allows the model to learn task-specific features and relationships that may not be captured by the pre-trained model alone, resulting in highly accurate and specialised language models that can be applied to a wide range of applications. In this tutorial, we will discuss and fine-tune large language model trained on protein sequences ProtT5, exploring the benefits and challenges of this approach, as well as the various techniques and strategies such as low ranking adaptations (LoRA) that can be employed to fit large language models with billions of parameters on regular GPUs. Protein large language models (LLMs) represent a significant advancement in Bioinformatics, leveraging the power of deep learning to understand and predict the behaviour of proteins at an unprecedented scale. These models, exemplified by the ProtTrans suite, are inspired by natural language processing (NLP) techniques, applying similar methodologies to biological sequences. ProtTrans models, including BERT and T5 adaptations, are trained on vast datasets of protein sequences from databases such as UniProt and BFD, storing millions of protein sequences and enabling them to capture the complex patterns and functions encoded within amino acid sequences. By interpreting these sequences much like languages, protein LLMs offer transformative potential in drug discovery, disease understanding, and synthetic biology, bridging the gap between computational predictions and experimental biology. In this tutorial, we will fine-tune the ProtT5 pre-trained model for dephosphorylation site prediction, a binary classification task.

📅 Galaxy Training Academy 2024

Teresa Müller — 2024-06-11T15:07:31+00:00

The Galaxy Academy is a self-paced online training event for beginners as well as learners who would like to improve their Galaxy data analysis skills. Over the course of one week, we will have a different topic and focus every day.

🛠️ ml_regression (imported from uploaded file)

2024-05-21T10:39:24+00:00

Regression in Machine Learning

🛠️ Intro_To_CNN_v1.0.11.0

2023-12-11T10:30:45+00:00

🛠️ Intro_To_RNN_v1_0_10_0

2023-10-17T08:58:40+00:00

🛠️ Intro_To_FNN_v1_0_10_0

2023-10-17T08:58:40+00:00

🛤️ From R to Machine Learning; an introductory course

2023-06-27T15:59:26+00:00

This learning path aims to teach you the basics of Machine Learning using R. Initially you will learn how to code in R within the Galaxy platform, gaining some familiarity into how to wrangle and analyze data. Then, you will be guided through the various types of Machine Learning techniques, developing some simple models using R.

📚 Supervised Learning with Hyperdimensional Computing

2023-04-28T20:05:26+00:00

chopin2 (Cumbo et al. 2020) implements a domain-agnostic supervised classification method based on the hyperdimensional (HD) computing paradigm. It is an open-source tool and its code is available on GitHub at https://github.com/cumbof/chopin2.

🛠️ gpu_jupytool

2023-01-18T08:59:15+00:00

📚 A Docker-based interactive Jupyterlab powered by GPU for artificial intelligence in Galaxy

2022-04-06T17:18:13+00:00

Jupyterlab is a popular integrated development environment (IDE) for a variety of tasks in data science such as prototyping analyses, creating meaningful plots, data manipulation and preprocessing. Python is one of the most used languages in such an environment. Given the usefulness of Jupyterlab, more importantly in online platforms, a robust Jupyterlab notebook application has been developed that is powered by GPU acceleration and contains numerous packages such as Pandas, Numpy, Scipy, Scikit-learn, Tensorflow, ONNX to support modern data science projects. It has been developed as an interactive Galaxy tool that runs on an isolated docker container. The docker container has been built using nvidia/cuda:11.8.0-cudnn8-runtime-ubuntu20.04 as the base container. Moreover, a Galaxy tool ( run_jupyter_job) can be executed using Bioblend which uses Galaxy’s remote job handling for long-running machine learning and deep learning training. The training happens remotely on a Galaxy cluster and the outcome datasets such as the trained models, tabular files and so on are saved in a Galaxy history for further use.

🎥 Recording of Image classification in Galaxy with fruit 360 dataset

2022-01-19T00:00:00+00:00

A 1H long recording is now available.

🛠️ fruit_360

2021-12-01T15:54:59+00:00

Image classification with fruit 360 dataset

🖼️ Image classification in Galaxy with fruit 360 dataset

2021-12-01T15:54:59+00:00

What is a convolutional neural network (CNN)?

📚 Image classification in Galaxy with fruit 360 dataset

2021-12-01T15:54:59+00:00

The classification of fruits and vegetables offers many useful applications such as

🖼️ Feedforward neural networks (FNN) Deep Learning - Part 1

2021-06-02T10:53:09+00:00

What is an artificial neural network?

🖼️ Recurrent neural networks (RNN) Deep Learning - Part 2

2021-05-31T15:17:18+00:00

What is a recurrent neural network (RNN)?

📚 Introduction to Machine Learning using R

2021-05-21T15:04:43+00:00

This is an Introduction to Machine Learning in R, in which you’ll learn the basics of unsupervised learning for pattern recognition and supervised learning for prediction. At the end of this workshop, we hope that you will:

🖼️ Convolutional neural networks (CNN) Deep Learning - Part 3

2021-05-19T07:55:00+00:00

What is a convolutional neural network (CNN)?

🛠️ papaa@0.1.9_PI3K_OG_model_tutorial

2021-05-06T10:06:35+00:00

PanCancer Aberrant Pathway Activity Analysis: PI3K example

📚 PAPAA PI3K_OG: PanCancer Aberrant Pathway Activity Analysis

2021-05-06T10:06:35+00:00

Signaling pathways are among the most commonly altered across different tumor types. Many tumors possess at least one driver alteration and nearly half of such alterations are potentially targeted by currently available drugs. A recent study in TCGA tumors has identified patterns of somatic variations and mechanisms in 10 canonical pathways

📚 Deep Learning (Part 1) - Feedforward neural networks (FNN)

2021-04-28T06:47:19+00:00

Artificial neural networks are a machine learning discipline roughly inspired by how neurons in a

📚 Deep Learning (Part 3) - Convolutional neural networks (CNN)

2021-04-19T17:54:38+00:00

Artificial neural networks are a machine learning discipline that have been successfully applied to problems

🛠️ Simtext training workflow

2021-04-05T18:58:54+00:00

In this workflow the similarity among set of search queries (e.g. genes) is analyzed based on the associated vocabulary in PubMed. The last tool is an interactive tool that enables the inspection of the data.

📚 Text-mining with the SimText toolset

2021-04-05T18:58:54+00:00

Literature exploration in PubMed on a large number of biomedical entities (e.g., genes, diseases, or experiments) can be time-consuming and challenging, especially when assessing associations between entities. Here, we use SimText, a toolset for literature research that allows you to collect text from PubMed for any given set of biomedical entities, extract associated terms, and analyze similarities among them and their key characteristics in an interactive tool.

📚 Deep Learning (Part 2) - Recurrent neural networks (RNN)

2021-02-23T08:46:07+00:00

Artificial neural networks are a machine learning discipline roughly inspired by how neurons in a

🎥 Recording of Introduction to Machine Learning using R

2021-02-15T00:00:00+00:00

A 1H30M long recording is now available.

🎥 Recording of Regression in Machine Learning

2021-02-15T00:00:00+00:00

A 1H29M long recording is now available.

🎥 Recording of Deep Learning (Part 1) - Feedforward neural networks (FNN)

2021-02-15T00:00:00+00:00

A 1H10M long recording is now available.

🎥 Recording of Deep Learning (Part 2) - Recurrent neural networks (RNN)

2021-02-15T00:00:00+00:00

A 50M long recording is now available.

🎥 Recording of Classification in Machine Learning

2021-02-15T00:00:00+00:00

A 1H50M long recording is now available.

🎥 Recording of Deep Learning (Part 3) - Convolutional neural networks (CNN)

2021-02-15T00:00:00+00:00

A 1H long recording is now available.

🛠️ Intro_To_Deep_Learning

2021-01-26T14:40:29+00:00

Introduction to Deep Learning

🛠️ Clustering in Machine Learning

2020-05-08T17:04:18+00:00

Clustering in Machine Learning

📚 Clustering in Machine Learning

2020-05-08T17:04:18+00:00

The goal of unsupervised learning is to discover hidden patterns in any unlabeled data. One of the approaches to unsupervised learning is clustering. In this tutorial, we will discuss clustering, its types and a few algorithms to find clusters in data. Clustering groups data points based on their similarities. Each group is called a cluster and contains data points with high similarity and low similarity with data points in other clusters. In short, data points of a cluster are more similar to each other than they are to the data points of other clusters. The goal of clustering is to divide a set of data points in such a way that similar items fall into the same cluster, whereas dissimilar data points fall in different clusters. Further in this tutorial, we will discuss ideas on how to choose different metrics of similarity between data points and use them in different clustering algorithms.

🛠️ ml_classification

2020-04-30T14:15:23+00:00

Classification in Machine Learning

📚 Classification in Machine Learning

2020-04-30T14:15:23+00:00

In this tutorial you will learn how to apply Galaxy tools to solve classification problems. First, we will introduce classification briefly, and then examine logistic regression, which is an example of a linear classifier. Next, we will discuss the nearest neighbor classifier, which is a simple but nonlinear classifier. Then advanced classifiers, such as support vector machines, random forest and ensemble classifiers will be introduced and applied. Furthermore, we will show how to visualize the results in each step.

📚 Introduction to deep learning

2020-03-26T12:17:27+00:00

Introduction

📚 Regression in Machine Learning

2020-01-25T09:55:53+00:00

In this tutorial you will learn how to use Galaxy tools to solve regression problems. First, we will introduce the concept of regression briefly, and then examine linear regression, which models the relationship between a target variable and some explanatory variables (also known as independent variables). Next, we will discuss gradient boosting regression, an more advanced regressor model which can model nonlinear relationships between variables. Then, we will show how to visualize the results in each step. Finally, we will discuss how to train our models by finding the values of their parameters that minimize a cost function. We will work through a real problem to learn how the models and learning algorithms work.

🛠️ Machine Learning

2019-11-21T07:14:20+00:00

Basics of machine learning

🛠️ Regression GradientBoosting

2019-06-25T12:59:12+00:00

Machine learning: classification and regression

🛠️ Classification LSVC

2019-06-25T12:59:12+00:00

Machine learning: classification and regression

📚 Machine learning: classification and regression

2019-03-07T13:04:32+00:00

Machine learning is a subset of artificial intelligence (AI) that provides machines with the ability to automatically learn from data without being explicitly programmed. It is a combined field of computer science, mathematics and statistics to create a predictive model by learning patterns in a dataset. The dataset may have an output field which makes the learning process supervised. The supervised learning methods in machine learning have outputs (also called as targets or classes or categories) defined in the datasets in a column. These targets can either be integers or real (continuous) numbers. When the targets are integers, the learning task is known as classification. Each row in the dataset is a sample and the classification is assigning a class label/target to each sample. The algorithm which is used for this learning task is called a classifier. When the targets are real numbers, the learning task is called regression and the algorithm which is used for this task is called a regressor. We will go through classification first and look at regression later in this tutorial.

🛠️ Age Prediction RNA-Seq

2019-01-25T11:10:10+00:00

Age prediction using machine learning

🛠️ Age Prediction DNA Methylation

2019-01-25T11:10:10+00:00

Age prediction using machine learning

📚 Age prediction using machine learning

2019-01-25T11:10:10+00:00

Machine Learning is used to create predictive models by learning features from datasets. In the studies performed by Jason G. Fleischer et al. 2018 and Jana Naue et al. 2017, biomarkers are examined to predict the chronological age of humans by analysing the RNA-seq gene expression levels and DNA methylation pattern respectively. Different machine learning algorithms are used in these studies to select specific biomarkers to make age prediction. The RNA-seq gene expression (FPKM) dataset is generated using fibroblast cell lines of humans. The skin fibroblasts cells keep damage that happens with age. Epigenomic and phenotypic changes which are age-dependent are also contained in these cells. Within each individual, DNA methylation changes with age. This knowledge is used to select useful biomarkers from DNA methylation dataset. The CpGs sites with the highest correlation to age are selected as the biomarkers/features. In both these studies, specific biomarkers are analysed by machine learning algorithms to create an age prediction model.

📚 Basics of machine learning

2018-11-05T18:03:45+00:00

Machine learning uses techniques from statistics, mathematics and computer science to make computer programs learn from data. It is one of the most popular fields of computer science and finds applications in multiple streams of data analysis such as classification, regression, clustering, dimensionality reduction, density estimation and many more. Some real-life applications are spam filtering, medical diagnosis, autonomous driving, recommendation systems, facial recognition, stock prices prediction and many more. The following image shows a basic flow of any machine learning task. Data is provided by a user to a machine learning algorithm for analysis.

🛠️ Workflow Constructed From History 'IWTomics Workflow'

2018-06-14T09:51:52+00:00

Interval-Wise Testing for omics data

📚 Interval-Wise Testing for omics data

2018-06-14T09:51:52+00:00

IWTomics (Cremona et al. 2018) implements the Interval-Wise Testing (IWT; Pini and Vantini 2017) for omics data. This