Sequence Design with LigandMPNN

This video covers LigandMPNN, the successor of ProteinMPNN, for sequence design with additional molecular context. This context could include a small molecule, nucleic acid, and/or metals, enabling improving sequence design for these complex interactions. Nick shares an overview, expands on sidechain packing, inputs and outputs, 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 - LigandMPNN
00:24 - Inputs and Outputs
00:43 - Additional atomic context improves local sequence recovery
02:13 - LigandMPNN Overview
11:09 - LigandMPNN Loss
11:30 - Sidechain packing network
15:35 - Limitations

Видео Sequence Design with LigandMPNN канала RosettaCommons