Backbone Generation with RFdiffusion All-Atom

This video covers backbone generation with RFdiffusion All-Atom, based on an expanded version of RoseTTAFold that has the capability to input and model protein interactions with nucleic acids, small molecules, ions, covalently modified residues (RoseTTAFold All Atom). The video covers an overview of the model, inputs and outputs, architecture, and use cases, and limitations. Video from the Rosetta Commons ML Bootcamp (October 2024) Video Instructor: Nick Randolph (UNC Chapel Hill) Credits: Course Instructor: Nick Randolph Course Teaching Assistants: Fatima Hitawala, Amrita Nallathambi, Ben Orr RC Leadership and NSF Sponsored Grant PIs: Julia Koehler Leman & Jeffrey Gray RC Education Director: Ashley Vater Videographer: Ryan Caster Rosetta Bootcamp Trainee Participants. Funding: Rosetta Commons and National Science Foundation 00:00 - Intro 00:10 - RFDiffusion-AA 04:51 - Inputs and Outputs 06:55 - RFDiffusion-AA overview 08:24 - RoseTTAFold-AA and RFdiffusion-AA Losses 11:56 - Limitations