CMCB Life Sciences Seminar: Prof. Anne-Florence Bitbol, EPFL, Instiute of Bioengineering, Switzerland

Host: James Sáenz

Title: "Predicting interaction partners and generating new protein sequences using protein language models"

Abstract: Protein language models trained on multiple sequence alignments of homologous proteins successfully capture coevolution between amino acids in structural contact: this is one of the ingredients of the success of AlphaFold. We have used such models, especially MSA Transformer, to generate new protein sequences from given protein families, and to predict which proteins interact among the members of two protein families. Despite their successes, a drawback of models based on multiple sequence alignments is that sequence alignment can be imperfect. Thus, we are developing ProtMamba, a homology-aware but alignment-free protein language model. ProtMamba starts from concatenated homologous sequences, is based on the Mamba state-space model architecture, has promising generative properties, and is able to predict fitness.