Jun 2026· arXiv.org· Vol abs/2606.30170· 0 citations· 101 references
Computer SciencePhysics
TL;DR
A new baseline method is developed 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.
Abstract
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.
Molecular optimization in drug discovery, materials design, and catalysis requires searching vast chemical spaces under tight evaluation budgets, since high-fidelity oracles and experimental measurements are costly. The practical impact of an optimization method therefore hinges on its sample efficiency: how few evaluations it needs to find strong candidates. We introduce Sample Efficient Generative Optimization (SEGO), a framework for Bayesian optimization on adaptively generated molecules. In SEGO, a probabilistic surrogate model forms a hypothesis about where hits lie in chemical space, a generative model is steered to propose candidates in that region, the most promising candidate is selected via an acquisition function, and the resulting oracle call is used both to sharpen the surrogate and to anchor the generator in real reward. SEGO attains state-of-the-art performance on the practical molecular optimization (PMO) benchmark using only one tenth of the oracle calls consumed by other methods, and on a multiparameter docking task it reaches ten hits in roughly half the oracle calls of existing approaches. These gains move molecular optimization closer to campaigns driven by direct experimental feedback.
S. Kopf, Cristina Nevado, P. Schwaller· 0 citations
Machine learning (ML) models for molecular property prediction are increasingly deployed in drug discovery, yet their adoption in real-world scenarios requires an understanding of the conditions in which a model succeeds or fails. While standardized benchmarks are powerful instruments to measure and unlock progress in ML research, they should not be blindly treated as the end goal. Especially static and retrospective benchmarks, in which no true unknown test set is employed, limit our ability to robustly validate a model’s performance. Building on the collective expertise of a cross-industry consortium, we present a model validation framework consisting of five recommendations that would enable the community to move beyond aggregate metrics toward understanding where and why molecular property prediction models fail. We connect evaluation choices to real-world applications and case studies encountered in pharmaceutical research. The framework proposes splitting strategies that mimic realistic distribution shifts and expose common failure modes. We apply the recommended framework on a recently released dataset of absorption, distribution, metabolism, and excretion (ADME) properties. Across two complementary model algorithms, our case studies reveal four distinct failure modes (extrapolation, interpolation, representation, and evaluation) showing that model errors arise not only from distribution shift but also from limitations in molecular representations. Our results show that commonly used evaluation protocols can significantly overestimate performance and may not detect important model failure modes. All software and data are released via https://github.com/srijitseal/polaris.
Srijit Seal, Akshat Shirish Zalte, David Alencar Araripe et al.· bioRxiv· 0 citations
Drug discovery remains constrained by high development costs (often exceeding USD 2.6 billion per approved drug) and long timelines (typically 10-15 years), with substantial late-stage attrition. We present Atomica, a web-based engineering-intelligence platform designed to integrate AI-driven molecular generation with reproducible cheminformatics validation and bioactivity-context retrieval in a single workflow. Atomica uses a server-mediated architecture to orchestrate MolMIM-based generation, descriptor and rule-based filtering, and PubChem record enrichment while avoiding client-side credential exposure. Molecule quality is assessed using explicit quantitative criteria, including validity, uniqueness, novelty, QED, synthetic accessibility (SA), LogP, and constraint success rate under user-defined similarity thresholds. The platform operationalizes constrained generation as a sampling-and-ranking process in descriptor space rather than a physics-based simulation, and it reports accepted versus rejected candidates to address invalid-output risk transparently. A representative end-to-end case workflow demonstrates practical candidate prioritization from seed structure input through filtering and evidence enrichment. Atomica is implemented with a typed, modular service layer and documented reproducibility controls (versioned dependencies, defined benchmarking protocol, and repeatable evaluation settings). This work contributes an integrated and scientifically auditable framework that bridges algorithmic molecular generation and applied, collaboration-ready drug-discovery workflows.
A state-aware functional classifier (SAFC) is developed that integrates molecular dynamics derived receptor ensembles, ensemble docking and protein ligand interaction graphs that provides dynamics-aware functional activity rankings for generated molecules that were partly complementary to docking, drug-likeness and synthetic accessibility scores.
H. Kumar, Zhengxiao Yang, Yankai Yu et al.· bioRxiv· 0 citations
Deep neural network (DNN)‐based in silico models show great promise in predicting the properties and bioactivities of novel compounds, including small molecules. Among traditional approaches, structure‐based drug design (SBDD) remains a fundamental approach for drug discovery using molecular docking, scoring functions, and molecular dynamics simulations. However, these approaches are often constrained by limited flexibility, resolution, and generalizability. Geometric deep learning (GDL) offers a transformative alternative by enabling models to learn directly from non‐Euclidean molecular representations, such as graphs, point clouds, and meshes, capturing critical 3D spatial relationships inherent to protein–ligand interactions. This review highlights the theoretical underpinnings and practical applications of GDL in small‐molecule drug discovery, focusing on tasks including binding affinity prediction, virtual screening, de novo molecule generation, pose prediction, ADMET profiling, and protein flexibility modeling. We explore key GDL architectures, graph neural networks, SE(3)‐equivariant networks, 3D convolutional neural networks, point cloud models, and geometric transformers, and assess their performance across various drug discovery benchmarks. The integration of geometry‐aware AI models with experimental and computational workflows was also highlighted for its potential to streamline hit‐to‐lead optimization and advance rational drug design. Despite remarkable progress, the field faces challenges including limited high‐quality 3D structural datasets, protein flexibility representation, and the interpretability of deep models. Addressing these issues through hybrid modeling approaches, multi‐resolution learning, and self‐supervised training could further elevate GDL's impact. Ultimately, GDL stands at the frontier of AI‐enhanced pharmaceutical innovation, offering unprecedented precision, efficiency, and insight in the pursuit of next‐generation therapeutics.
A. Srivastav, Unnati Modi, Rahul Kumar et al.· Molecular Informatics· 0 citations
It is shown that prospective structure selection, rather than structure generation, represents the primary bottleneck in ensemble-based VS, highlighting an urgent need for novel structural descriptors to identify high-performing conformations.
Jaeoh Shin, K. Joo, Jejoong Yoo· Journal of Chemical Informat...· 0 citations