Conformational Rank Conditioned Committees for Machine Learning-Assisted Directed Evolution

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Adler, Mia, Liang, Carrie, Peng, Brian, Presnyakov, Oleg, Baker, Justin M., Lauffer, Jannelle, Sharma, Himani, Merriman, Barry
Natura: Preprint
Pubblicazione: 2025
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866911297526824960
author Adler, Mia
Liang, Carrie
Peng, Brian
Presnyakov, Oleg
Baker, Justin M.
Lauffer, Jannelle
Sharma, Himani
Merriman, Barry
author_facet Adler, Mia
Liang, Carrie
Peng, Brian
Presnyakov, Oleg
Baker, Justin M.
Lauffer, Jannelle
Sharma, Himani
Merriman, Barry
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2510_24974
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Conformational Rank Conditioned Committees for Machine Learning-Assisted Directed Evolution
Adler, Mia
Liang, Carrie
Peng, Brian
Presnyakov, Oleg
Baker, Justin M.
Lauffer, Jannelle
Sharma, Himani
Merriman, Barry
Machine Learning
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.
title Conformational Rank Conditioned Committees for Machine Learning-Assisted Directed Evolution
topic Machine Learning
url https://arxiv.org/abs/2510.24974