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 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

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 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