New immunotherapy platform could increase potential to target cancer cells Possu Huang Lab news.stanford.edu/stories/2024/1… 🔬Read about related technology available for licensing: 23-287 “Using de novo protein design to target MHC-1 and MR-1 antigens” - techfinder.stanford.edu/technology/usi…

Our piece celebrating the Possu Huang Lab's clever approach to designing high-affinity, specific binders to peptide–MHC complexes 👏

Possu Huang Lab nature.com/articles/s4158…

Thanks Michael Birnbaum and lab for the great perspective on TRACeR papers!

A method for designing high-affinity, specific binders to peptide–MHC complexes may improve the next generation of antigen-specific T cell-based therapeutics #NBTNV go.nature.com/3ZFVH0O rdcu.be/d3ZBW

TRACeR platforms more accurately recognize a wide variety of surface proteins expressed by cancer cells, which makes them easier to target with the body’s own immune system. stanford.io/4h0WzUx Possu Huang Lab #immunotherapy

Assessing Generative Model Coverage of Protein Structures with SHAPES biorxiv.org/cgi/content/sh… #biorxiv_bioeng

Assessing Generative Model Coverage of Protein Structures with SHAPES 1. This paper introduces SHAPES, a comprehensive framework to evaluate generative protein structure models by assessing their coverage of the protein structure space, highlighting regions often undersampled or

I'm organizing a Keystone symposium, along with Liz Kellogg ❄️🔬 and Possu Huang Lab, on machine learning and macromolecules. Mar 23-26 in Keystone, Colorado. We have a great lineup and deadlines are coming up soon! keystonesymposia.org/conferences/co…

A framework for evaluating how well generative models of protein structure match the distribution of natural structures. Possu Huang Lab

Full-atom MPNN (FAMPNN) - a sequence design method that explicitly models both sequence identity and sidechain conformation. biorxiv.org/content/10.110… code: github.com/richardshuai/f…

Excited to share our joint work with Richard Shuai, Full-Atom MPNN (FAMPNN), a protein sequence design method that explicitly models both sequence and side-chain structure! 🧵 1/N

In new work led by Talal Widatalla and Richard Shuai, we make exciting progress toward functional molecular design by augmenting structure-conditioned protein sequence models with side chain information!

Sidechain conditioning and modeling for full-atom protein sequence design with FAMPNN 1. This paper introduces FAMPNN (Full-Atom MPNN), a novel method for protein sequence design that explicitly models both sequence identity and sidechain conformation, addressing a significant

All-atom fixed backbone protein sequence design with FAMPNN Richard Shuai Talal Widatalla Possu Huang Lab Brian Hie