Geometric Deep Learning‐Based Drug Design Models for Small‐Molecule Drug Discovery

Topological deep learning for drug–target interaction, virtual screening, and docking scoring: a practical, benchmark-driven review

A decision-oriented taxonomy and a benchmark-driven evaluation playbook that specifies minimum standards for splits, metrics, baselines, and ablations to isolate the topological contribution are presented.

Deep Learning Pipeline for Accelerating Virtual Screening in Drug Discovery.

Deep learning has revolutionized virtual screening in drug discovery, offering unprecedented improvements in hit identification, lead optimization, and molecular property prediction. Traditional virtual screening methods, including structure-based docking and ligand-based screening, often suffer from computational inefficiencies, poor generalization, and reliance on predefined molecular descriptors. Deep learning addresses these limitations by leveraging graph neural networks (GNNs), transformer-based models, generative AI, and reinforcement learning to discover novel drug candidates more efficiently. This chapter explores the systematic deep learning pipeline for virtual screening, covering data acquisition, molecular representation learning, model architectures, training strategies, and uncertainty estimation. We discuss advanced model optimization techniques, including curriculum learning, transfer learning, and adversarial training, which enhance predictive accuracy and robustness. Despite significant progress, challenges remain, particularly in data quality, model interpretability, generalization to novel chemical spaces, and computational cost. Emerging trends, such as self-supervised learning, quantum computing for molecular simulations, and AI-integrated automated laboratories, are paving the way for the next generation of AI-driven drug discovery. By integrating machine learning with experimental validation, AI-powered virtual screening is set to accelerate early-stage drug discovery, reducing costs and improving the efficiency of therapeutic development.

Beyond SBDD: Geometric Deep Learning in Polypharmacology and Multi-target Drug Design

This review elucidates the paradigm shift in drug discovery from serendipitous exploration to rational, structure-driven polypharmacological molecular engineering, thereby providing a clear, structured guide for navigating the complexities of next-generation therapeutics.

Systematic Benchmarking of AI-Based Molecular Generation Models for Structure-Based Drug Design

Generating Developable 3D Molecules via Pocket-Conditioned Diffusion and Property-Aware Optimization

Drug discovery and development is time-consuming and resource-intensive, motivating computational approaches such as diffusion models for de novo drug design. Many such models follow the structure-based drug design (SBDD) paradigm, generating molecules to fit a target binding pocket. However, existing diffusion-based SBDD methods typically couple pocket and ligand representation learning, model interactions only at the atom level, and prioritize binding affinity over other developability properties. Here, we introduce conDitar-dev, a conditional diffusion-based SBDD framework for generating ligands with strong binding affinities and favorable ADMET properties. It consists of three modules: msPRL, a pretrained multi-scale pocket representation learning module; conDitar, a pocket-conditioned diffusion model guided by msPRL representations; and paOPT, a generation-time method for optimizing ligand developability. On a newly curated benchmark of human disease targets, conDitar outperforms state-of-the-art SBDD baselines, achieving an average binding score of -8.85 kcal/mol. Across five ADMET properties, conDitar-dev improves performance by up to 73% over conDitar. To further validate the abilities of conDitar-dev to generate developable molecules, we have applied it to two validated druggable targets: programmed death-ligand 1 (PD-L1) and colony-stimulating factor 1 receptor (CSF1R) proteins. Top-ranked generatively designed molecules and their analogs have been experimentally synthesized and biologically tested. Two molecules generated directly by conDitar-dev for PD-L1 exhibited SPR-derived $K_D$ values of 3.49 and 3.75 $\mu$M, respectively. Hit expansion based on conDitar-dev-designed molecules identified selective CSF1R inhibitors with IC$_{50}$ values as low as 200 nM, while also uncovering opportunities for drug repositioning.

Beyond Drug Discovery: The Nanotechnology Molecular Optimization (NMO) Benchmark

Generative molecular design is shaped by simple proxy benchmarks for drug-like properties and models pretrained on large pharmaceutical datasets. This combination yields strong benchmark metrics but limits transferability to domains structurally distinct from drug discovery. To overcome this limitation and drive discovery toward real, scientifically grounded targets, we introduce the Nanotechnology Molecular Optimization (NMO) Benchmark, which bridges machine learning (ML) and quantum materials science. NMO acts simultaneously as a rigorous testbed for the ML community and a discovery engine for nanotechnology research. The suite replaces proxy oracles with quantum simulations and introduces strict protocols that prioritize scientific utility over leaderboard-oriented overfitting. The physics-based NMO tasks impose hard structural constraints and rugged fitness landscapes, posing fundamentally new requirements on generative models. Notably, advanced molecular optimization methods underperform much simpler approaches on the NMO tasks. We develop a new baseline method identifying the critical components to solve the NMO tasks, including a novel representation for modeling structural constraints and a domain-agnostic pretraining strategy to eliminate pharmaceutical dataset bias. Our results surpass state-of-the-art physical properties and reveal previously unknown structural motifs, offering new insights for the nanotechnology community and demonstrating that ML can drive genuine scientific discovery.