A Dynamics-Informed Machine Learning Framework for Inhibitor Optimization Against Quickly Evolving Targets to Avoid Resistance
- 1UMass Chan Medical School
Abstract
Drug resistance often emerges through mutations that reshape protein conformational ensembles, allowing inhibitor potency to be altered without directly disrupting protein-ligand contacts. Consequently, the molecular mechanisms underlying these effects remain difficult to identify, hindering the design of inhibitors with durable potency against rapidly evolving drug targets. To address this challenge, we developed ROBUST, a physics-informed machine learning framework that integrates experimental measurements, molecular dynamics simulations, and interpretable statistical modeling to identify energetic determinants of inhibitor potency. Using HIV-1 protease as a stringent model system for drug resistance, we determined 157 new inhibition constants and integrated them with prior measurements to establish a comprehensive experimental dataset of 364 protease-inhibitor pairs. Analysis of the corresponding molecular dynamics simulations revealed a compact network of energetic interactions that quantitatively explains how resistance mutations and inhibitor modifications jointly reshape molecular recognition and inhibitor potency across the multidimensional resistance landscape. Models constructed from these energetic signatures predicted binding free energies with high accuracy (RMSE < 1 kcal mol-1) and successfully generalized to unseen darunavir analogs. Importantly, ROBUST accurately prioritized unseen analogs based on their potency across the variant set, demonstrating its utility for identifying compounds with improved resistance profiles. Together, these results uncover the energetic principles through which resistance mutations and inhibitor modifications alter potency and establish ROBUST as a mechanistically interpretable framework for translating these insights into resistance-aware inhibitor optimization against rapidly evolving drug targets.
Related
- SbWRKY62 Coordinates With SbERF096 to Activate Pterostilbene Biosynthesis and Targets a Xylanase Inhibitor Protein for Anthracnose Resistance in Sorghum
- DNA Repair Pathways as Determinants of PARP Inhibitor Resistance and Therapeutic Targets in Cancer
- Mutation-resolved ABL1 inhibitor resistance prediction under mutation-disjoint and temporal cross-study validation
- Accelerated discovery and optimization of a potent andselective MMP12 inhibitor with the machine learningplatform CAMOLE-1
- Oncogenic RAS as an adaptive signaling ecosystem: context-dependent vulnerabilities and resistance-informed therapeutic design
BibTeX
@misc{intravaia2026dynamicsinformed,
title = {{A Dynamics-Informed Machine Learning Framework for Inhibitor Optimization Against Quickly Evolving Targets to Avoid Resistance}},
author = {L. E. Intravaia and J. Kaur and A. M. Shaqra and M. Henes and K. Kosovrasti and V. Schroeder and E. A. Nalivaika and A. Ali and N. Kurt Yilmaz and C. A. Schiffer},
howpublished = {bioRxiv},
year = {2026},
month = sep,
doi = {10.64898/2026.09.25.754496},
url = {https://www.biorxiv.org/content/10.64898/2026.09.25.754496v1},
note = {CC BY-NC-ND},
}
RIS
TY - UNPB
TI - A Dynamics-Informed Machine Learning Framework for Inhibitor Optimization Against Quickly Evolving Targets to Avoid Resistance
AU - L. E. Intravaia
AU - J. Kaur
AU - A. M. Shaqra
AU - M. Henes
AU - K. Kosovrasti
AU - V. Schroeder
AU - E. A. Nalivaika
AU - A. Ali
AU - N. Kurt Yilmaz
AU - C. A. Schiffer
PY - 2026
DA - 2026/09/25
PB - bioRxiv
DO - 10.64898/2026.09.25.754496
UR - https://www.biorxiv.org/content/10.64898/2026.09.25.754496v1
AB - Drug resistance often emerges through mutations that reshape protein conformational ensembles, allowing inhibitor potency to be altered without directly disrupting protein-ligand contacts. Consequently, the molecular mechanisms underlying these effects remain difficult to identify, hindering the design of inhibitors with durable potency against rapidly evolving drug targets. To address this challenge, we developed ROBUST, a physics-informed machine learning framework that integrates experimental measurements, molecular dynamics simulations, and interpretable statistical modeling to identify energetic determinants of inhibitor potency. Using HIV-1 protease as a stringent model system for drug resistance, we determined 157 new inhibition constants and integrated them with prior measurements to establish a comprehensive experimental dataset of 364 protease-inhibitor pairs. Analysis of the corresponding molecular dynamics simulations revealed a compact network of energetic interactions that quantitatively explains how resistance mutations and inhibitor modifications jointly reshape molecular recognition and inhibitor potency across the multidimensional resistance landscape. Models constructed from these energetic signatures predicted binding free energies with high accuracy (RMSE < 1 kcal mol-1) and successfully generalized to unseen darunavir analogs. Importantly, ROBUST accurately prioritized unseen analogs based on their potency across the variant set, demonstrating its utility for identifying compounds with improved resistance profiles. Together, these results uncover the energetic principles through which resistance mutations and inhibitor modifications alter potency and establish ROBUST as a mechanistically interpretable framework for translating these insights into resistance-aware inhibitor optimization against rapidly evolving drug targets.
ER -