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 RCC-MLDE 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.
@article{arxiv.2510.24974,
title = {Conformational Rank Conditioned Committees for Machine Learning-Assisted Directed Evolution},
author = {Mia Adler and Carrie Liang and Brian Peng and Oleg Presnyakov and Justin M. Baker and Jannelle Lauffer and Himani Sharma and Barry Merriman},
journal= {arXiv preprint arXiv:2510.24974},
year = {2025}
}