BioLM-Score: Language-Prior Conditioned Probabilistic Geometric Potentials for Protein-Ligand Scoring

TL;DR

BioLM-Score is a novel protein-ligand scoring model that combines geometric modeling with language-augmented representation learning, achieving improved accuracy, efficiency, and interpretability for drug discovery tasks.

Contribution

It introduces a generalizable scoring approach that integrates biomolecular language models with geometric and probabilistic modeling, enhancing cross-target performance.

Findings

Significant improvements on CASF-2016 benchmark

Effective in docking, scoring, ranking, and screening

Guides docking protocols and conformational search

Abstract

Protein-ligand scoring is a central component of structure-based drug design, underpinning molecular docking, virtual screening, and pose optimization. Conventional physics-based energy functions are often computationally expensive, limiting their utility in large-scale screening. In contrast, deep learning-based scoring models offer improved computational efficiency but frequently suffer from limited cross-target generalization and poor interpretability, which restrict their practical applicability. Here we present BioLM-Score, a simple yet generalizable protein-ligand scoring model that couples geometric modeling with representation learning. Specifically, it employs modality-specific and structure-aware encoders for proteins and ligands, each augmented with biomolecular language models to enrich structural and chemical representations. Subsequently, these representations are integrated through a mixture density network to predict multimodal interatomic distance distributions, from which statistically grounded likelihood-based scores are derived. Evaluations on the CASF-2016 benchmark demonstrate that BioLM-Score achieves significant improvements across docking, scoring, ranking, and screening tasks. Moreover, the proposed scoring function serves as an effective optimization objective for guiding docking protocols and conformational search. In summary, BioLM-Score provides a principled and practical alternative to existing scoring functions, combining efficiency, generalization, and interpretability for structure-based drug discovery.