Discover and read the best of Twitter Threads about #ProteinML
Most recents (2)
Excited to announce PoET, our (@timt1630, @tbepler1) retrieval-augmented generative protein language model that achieves state-of-the-art unsupervised variant function prediction performance on #ProteinGym. #MachineLearning #ProteinML 1/9
arxiv.org/abs/2306.06156
arxiv.org/abs/2306.06156
Inspired by evolution, PoET conditions on observed protein sequences to infer fitness constraints and extrapolate a generative distribution of protein sequences. This allows PoET to be focused on any level of homology, from superfamilies to families to subfamilies and beyond. 2/9
The key idea in the design of PoET was to create a transformer that could condition on homologous sequences but did not require aligned inputs. Our solution was to model the generative process of whole protein families as a sequence-of-sequences generative modeling problem. 3/9
Here, we used #MachineLearning to design high diversity antibody variants with orders of magnitude greater potency than could be found with conventional directed mutagenesis. #ProteinML #AntibodyEngineering
doi.org/10.1038/s41467… @NatureComms 1/4
doi.org/10.1038/s41467… @NatureComms 1/4
Our method uses protein embeddings and Bayesian ML to design optimized antibody variant libraries, and we compare directly with other methods in a head-to-head prospective design study. 2/4
It was wonderful to collaborate with Lin Li, Rajmonda Caceres, Matt Walsh, and the rest of the @MITLL, @MIT, and @AAlphaBio teams on this project! 3/4
