Topological regression as an interpretable and efficient tool for quantitative structureactivity relationship modeling

Authors

Ruibo Zhang, Texas Tech University
Daniel Nolte, Texas Tech University
Cesar Sanchez-Villalobos, Texas Tech University
Souparno Ghosh, University of Nebraska-LincolnFollow
Ranadip Pal, Texas Tech University

Document Type

Article

Date of this Version

6-4-2024

Citation

Nature Communications | ( 2024) 15:5072. https://doi.org/10.1038/s41467-024-49372-0

Comments

Open access.

Abstract

Quantitative structure-activity relationship (QSAR)modeling is a powerful tool for drug discovery, yet the lack of interpretability of commonly used QSAR models hinders their application inmolecular design.We propose a similaritybased regression framework, topological regression (TR), that offers a statistically grounded, computationally fast, and interpretable technique to predict drug responses. We compare the predictive performance of TR on 530 ChEMBL human target activity datasets against the predictive performance of deep-learning-based QSAR models. Our results suggest that our sparse TR model can achieve equal, if not better, performance than the deep learningbased QSAR models and provide better intuitive interpretation by extracting an approximate isometry between the chemical space of the drugs and their activity space.