Conformational Rank Conditioned Committees for Machine Learning-Assisted Directed Evolution

TL;DR

This paper introduces a rank-conditioned committee framework for machine learning-assisted directed evolution, enabling better separation of uncertainties and improving antibody discovery by leveraging conformational rankings.

Contribution

The paper proposes a novel rank-conditioned committee approach that explicitly models conformational uncertainty in MLDE, enhancing its effectiveness in antibody evolution tasks.

Findings

Significant improvements in SARS-CoV-2 antibody docking performance

Effective separation of conformational and epistemic uncertainties

Scalable approach for therapeutic antibody discovery

Abstract

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.