Overview

Instructor(s): Dr. Dinesh Devarajan

Time: April 2026

Location: Blocker 220

Prerequisite(s): Active HPRC Account, Linux/Unix skills

This short course provides hands-on introduction to diffusion-based generative models for protein design, with a focus on RFdiffusion. Participants will learn how to run RFdiffusion inference workflows on HPRC clusters. The session will introduce the computational workflow, strategies for generative design runs on HPC infrastructure.

A Registration button will appear here when registration has been opened.

Course Materials

Participation

During the training, attendees are expected to log in to an HPRC cluster using their own computer and complete the instructor-led examples and exercises.

Learning Objectives and Agenda

In this course, participants will

• Understand how diffusion models such as RFdiffusion enable de novo protein design
• Learn how RFdiffusion inference workflows are executed on HPC systems
• Set up and run RFdiffusion inference through guided, hands-on exercises
• Modify RFdiffusion input parameters (motifs, length, symmetry, structural constraints) to guide protein backbone generation
• Interpret and visualize RFdiffusion outputs