Conformational Rank Conditioned Committees for Machine Learning-Assisted Directed Evolution
This addresses a bottleneck in therapeutic antibody discovery by providing a scalable method to model conformational uncertainty, though it appears incremental as an enhancement to existing MLDE pipelines.
The paper tackles the problem of separating conformational uncertainty from epistemic uncertainty in machine learning-assisted directed evolution for antibody design by introducing a rank-conditioned committee framework that assigns neural network committees per conformational rank. The approach demonstrates significant improvements over baseline strategies on SARS-CoV-2 antibody docking.
Machine Learning-assisted directed evolution (MLDE) is a powerful tool for efficiently navigating antibody fitness landscapes. Many structure-aware MLDE pipelines rely on a single conformation or a single committee across all conformations, limiting their ability to separate conformational uncertainty from epistemic uncertainty. Here, we introduce a rank -conditioned committee (RCC) framework that leverages ranked conformations to assign a deep neural network committee per rank. This design enables a principled separation between epistemic uncertainty and conformational uncertainty. We validate our approach on SARS-CoV-2 antibody docking, demonstrating significant improvements over baseline strategies. Our results offer a scalable route for therapeutic antibody discovery while directly addressing the challenge of modeling conformational uncertainty.