GPCR Ligand Bioactivity Prediction with Physics-Informed Dual-State Query Learning
Abstract
Predicting the bioactivity profiles of small molecules against G protein-coupled receptors (GPCRs) is a challenge in drug discovery. Although deep learning has accelerated the prediction of binding affinities, existing approaches often struggle to distinguish between functional efficacies because they neglect dynamic conformational equilibria. Furthermore, structure-based methods are frequently limited by the scarcity of high-resolution active-state crystal structures and the indistinguishability of conformational states in static representations. To bridge the gap between black-box prediction and biophysical reality, we propose Dual-State Query (DSQ), a physics-informed multimodal architecture that explicitly embeds the Monod-Wyman-Changeux (MWC) model of allostery within a neural network. Unlike conventional models that rely on explicit 3D structures, DSQ utilizes learnable orthogonal queries to extract disentangled representations of active and inactive receptor states. These latent representations are governed by a novel neural MWC gating module, which mathematically derives the probability of receptor activation from thermodynamic competition between ligand-state affinities and the receptor's intrinsic conformational energy barrier. A contrastive ranking objective is also introduced to enforce differential affinity constraints, ensuring physical consistency. Extensive experiments demonstrate that DSQ outperforms other baselines, particularly for the agonist subset. Additional homology-stratified, temperature-sensitivity, perturbation, clustering, and efficiency analyses show that DSQ provides useful thermodynamic inductive bias, while also exposing a clear limitation on low-homology receptors. The code is available at https://github.com/jiankliu/DSQ.
Related
- A physics-informed hybrid deep learning model for spatiotemporal rice disease prediction using multi-source data
- Leakage-controlled benchmarking reveals generalization limits of deep learning for protein-ligand binding affinity prediction
- Bioactivity-driven prediction of antibacterial synergy using machine learning models
- AlphaGenome informed machine learning for pathogenicity prediction of germline mutations
- SIMORGH: Ensemble-Aware Geometric Deep Learning for Apo-State and Cryptic Ligand Binding Site Prediction
BibTeX
@misc{zhang2026gpcr,
title = {{GPCR Ligand Bioactivity Prediction with Physics-Informed Dual-State Query Learning}},
author = {Shuo Zhang and Huifeng Zhang and Rongqi Hong and Jian K. Liu},
howpublished = {arXiv},
year = {2026},
month = sep,
doi = {10.48550/arxiv.2609.16468},
eprint = {2609.16468},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2609.16468},
}
RIS
TY - UNPB
TI - GPCR Ligand Bioactivity Prediction with Physics-Informed Dual-State Query Learning
AU - Shuo Zhang
AU - Huifeng Zhang
AU - Rongqi Hong
AU - Jian K. Liu
PY - 2026
DA - 2026/09/15
PB - arXiv
DO - 10.48550/arxiv.2609.16468
UR - https://arxiv.org/abs/2609.16468
AB - Predicting the bioactivity profiles of small molecules against G protein-coupled receptors (GPCRs) is a challenge in drug discovery. Although deep learning has accelerated the prediction of binding affinities, existing approaches often struggle to distinguish between functional efficacies because they neglect dynamic conformational equilibria. Furthermore, structure-based methods are frequently limited by the scarcity of high-resolution active-state crystal structures and the indistinguishability of conformational states in static representations. To bridge the gap between black-box prediction and biophysical reality, we propose Dual-State Query (DSQ), a physics-informed multimodal architecture that explicitly embeds the Monod-Wyman-Changeux (MWC) model of allostery within a neural network. Unlike conventional models that rely on explicit 3D structures, DSQ utilizes learnable orthogonal queries to extract disentangled representations of active and inactive receptor states. These latent representations are governed by a novel neural MWC gating module, which mathematically derives the probability of receptor activation from thermodynamic competition between ligand-state affinities and the receptor's intrinsic conformational energy barrier. A contrastive ranking objective is also introduced to enforce differential affinity constraints, ensuring physical consistency. Extensive experiments demonstrate that DSQ outperforms other baselines, particularly for the agonist subset. Additional homology-stratified, temperature-sensitivity, perturbation, clustering, and efficiency analyses show that DSQ provides useful thermodynamic inductive bias, while also exposing a clear limitation on low-homology receptors. The code is available at https://github.com/jiankliu/DSQ.
ER -