ACES: AlphaFold Protein Structure Prediction
Overview
Instructor(s): Dr. Michael Dickens
Time: February 2026
Location: Online using Zoom
Prerequisite(s): Current ACCESS ID, basic Linux/Unix skills
This short course covers how to run AlphaFold on the ACES cluster, utilizing the NVIDIA H100 GPUs.
A Registration button will appear here when registration has been opened.
Note: In order to run AlphaFold3 on the HPRC ACES cluster, you will need to request the access model parameters file by agreeing to the Google terms of service
Course Materials
Participation
During the training, attendees are expected to use their own computer and complete the instructor-led application and allocation processes.
Learning Objectives and Agenda
In this class, participants will:
- Learn about AlphaFold resources and Limitations
- Learn about shared database files
- Learn how to run ParaFold to reduce GPU idle time
- Submit an example ParaFold/AlphaFold2 job script
- Submit an example AlphaFold3 job script
- Visualize the AlphaFold job results
This course focuses, among others, on the following topics:
- AlphaFold History
- Running AlphaFold2 on ACES
- ParaFold AlphaFold2 workflow
- ParaFold with reduced_dbs
- AlphaFold2 confidence metrics
- Running AlphaFold3 on ACES
- HPRC Cluster Utilities
- Visualization of Results
- view predictions in Jmol
- Job Resource Monitoring