Applied AlphaFold Training

Want to learn about UMass Chan's AlphaFold offerings? Want to learn how to run AlphaFold on the UMass Chan High Performance Compute cluster?

Join us for an in-depth, hands-on Applied AlphaFold Training Workshop, designed for researchers, trainees, and staff at UMass Chan Medical School who want to leverage state-of-the-art protein structure prediction tools in their work. This session will introduce participants to AlphaFold, demonstrate how to run it efficiently on UMass Chan’s high-performance computing (HPC) infrastructure, and guide you through next steps for interpreting and applying your results in real-world biomedical research.

During this workshop, attendees will:

Explore UMass Chan’s Computing Capabilities

Learn about the HPC environment, available GPU resources, storage options, and support services that enable efficient large-scale AlphaFold jobs. We’ll walk you through system access, job submission workflows, and best practices for optimizing performance.

Get Hands-On Training Running AlphaFold

We’ll demonstrate how to prepare inputs, configure runs, and execute AlphaFold on the cluster—whether using command-line workflows, Singularity/Apptainer containers, or workflow tools. Participants will see a full end-to-end example job on the UMass Chan systems.

Learn What to Do After Your Predictions Finish

Once AlphaFold generates its predictions, what comes next? We’ll discuss how to analyze output files, evaluate model quality metrics, visualize structures, integrate results into downstream pipelines, and consider appropriate biological interpretations and limitations.

Who Should Attend

This training is ideal for researchers in structural biology, computational biology, bioinformatics, biochemistry, AI-driven science, or any field where protein structure prediction can accelerate discovery.

Why Attend

By the end of the workshop, you’ll understand how to use UMass Chan’s computational resources to run AlphaFold efficiently and confidently—and how to turn predictions into meaningful scientific insights.