Scientific progress depends not only on finding solutions, but on learning the rules that explain why they work and using that understanding to design better experiments. We introduce science sandboxes, a framework for studying this capability in AI agents through repeated cycles of experimentation, feedback, and hypothesis revision. Science sandboxes invite an agent to query the natural world in different ways, ranging from"wet"physical experiments, to"damp"predictive models trained on empirical data, to"dry"invented rules. By establishing a common experimental loop and a protocol for evaluating agents within it, science sandboxes allow assessment of both quantitative performance on specific metrics and qualitative scientific reasoning, across a spectrum of empirical verifiability. Here, we instantiate this framework in two biological settings, models of regulatory genomics and protein fitness prediction, and examine the capabilities of frontier agents. Across these settings, we could see when agents successfully optimized a quantitative metric without understanding the rules underlying the system. In particular, their scientific reasoning deteriorated when they encountered systems whose rules fell outside familiar biological priors. By highlighting such failure modes, science sandboxes make the frontier of scientific capability measurable and provide a controlled setting in which to study and ultimately expand it.
Arya S. Rao, Rodrigo I. Castro, Sager J. Gosai et al.· 0 citations
This study advances the human-machine commerce literature by examining and explaining the rationality paradox, and extends traditional unidirectional PSI into bidirectional algorithmic synergy, demonstrating how distinct dimensions of AI literacy act as either propulsive accelerators or cognitive brakes in high-arousal environments.
Wan-Yun Ma, Ze-Feng Shao, Kifayat Nahiyan Rafi et al.· Asia Pacific Journal of Mark...· 0 citations
This system framework provides an efficient and interpretable solution for compliance verification, verifying the feasibility of lightweight AI in vertical fields and can also provide key data support for active and passive safety research such as the prevention of pedal misoperation in electric commercial vehicles.
Covalent inhibitors have garnered renewed attention in recent years, with their rational design becoming increasingly critical in drug discovery. Among the technologies facilitating the discovery of covalent inhibitors, covalent docking has emerged as a pivotal tool in various stages of drug development including virtual screening, lead optimization, and mechanistic studies. Since its inception as an extension of conventional docking methods in the early 2000s, covalent docking tools have undergone substantial advancements. This review provides a comprehensive overview of covalent docking algorithms, systematically categorizing their approaches according to covalent bond formation, which primarily include tethered docking, biased docking, and dynamic covalent docking approaches. A comparative analysis of current covalent docking tools is provided, alongside a critical discussion of remaining challenges. Special emphasis is placed on the growing impact of artificial intelligence (AI) in shaping novel methodologies and expanding the capabilities of covalent docking. Finally, we discuss prospects for advancing covalent docking methodologies and their applications in drug discovery.
Shi Li, Hongyan Du, Hui Zhang et al.· WIREs Computational Molecula...· 2 citations
Reach audiences
Advertise in front of researchers, engineers, and readers.
Voltage-gated sodium channels (VGSCs/Navs) are essential targets for the treatment of numerous neurological, muscular, and cardiac disorders. Despite the increasing clinical interest in subtype-selective modulators, current public databases provide fragmented and inconsistent information on VGSC-related compounds and targets, particularly lacking coverage on peptides. To address this limitation, we developed NavDB, a specialized and open-access database focusing on VGSC modulators and targets. NavDB integrates 8023 curated data records covering 5168 compounds, including small molecules, toxins, drugs, and peptides, along with comprehensive annotations on biological activity, druggability, and structural feature. NavDB also features advanced functions such as text-based and structure-based search, peptide similarity matching, and AI-powered property prediction. Moreover, the database offers high-quality 3D visualizations of targets and peptides, with disulfide bond and signal peptide annotations. All data are freely downloadable to support both experimental and computational drug discovery. NavDB is publicly available at: http://cadd.zju.edu.cn/navdb/.
Gaoang Wang, Jiahui Yu, Haiyi Chen et al.· Journal of Chemical Informat...· 0 citations
Colorectal cancer (CRC) exhibits substantial molecular heterogeneity, necessitating the inference of subtype-specific driver genes and their interactions for drug-target discovery and precision oncology. Prior studies often fail to capture subtle, latent nonlinear regulatory mechanisms (dark causal relationships) driving tumor progression in specific subtypes. Here, we develop an explainable intelligence computational framework, Symbolic Trajectory-Embedded Dark Causal Interaction Inference (STE-DC2I), which combines symbolic trajectory embedding with historical prediction mechanisms to model nonmonotonic oscillatory dependencies between genes. Integrating single-cell transcriptomic and multiomics profiles from malignant epithelial subpopulations, STE-DC2I classifies CRC subtypes, reconstructs developmental trajectories, and uncovers interpretable subtype-specific driver genes with functional relevance. Unlike correlation-based and explicit causal approaches, STE-DC2I captures weak yet biologically critical regulatory signals, outperforming state-of-the-art methods in predicting subtype-specific CRC driver genes. Functional assays in CRC cell lines (in vitro) validated nine predicted driver genes, highlighting their therapeutic potential.This work systematically explores dark causal interactions between genes in CRC subtypes. STE-DC2I offers interpretable insights and a generalizable strategy for CRC drug-target discovery.
Meng Huang, Huijin Hu, Ming Li et al.· Journal of Chemical Informat...· 0 citations
ConspectusThe field of covalent drug discovery has witnessed a remarkable resurgence in recent years, a trend underscored by the approval of more than 125 covalent drugs by the US FDA as of 2025, which demonstrates their immense therapeutic potential. Driven by ever-increasing computational power and vast amounts of data, deep learning (DL) is profoundly transforming numerous fields, from natural language processing to drug discovery. In the development of covalent drugs, in particular, advanced computational methods centered on data-driven approaches and artificial intelligence (AI) exhibit immense potential. The realization of this potential depends on the construction of a synergistic ecosystem. Here, we define this "ecosystem" as an integrated set of components─including (i) curated covalent-relevant databases, (ii) AI/physics-based predictive and scoring models, (iii) interoperable computational workflows spanning site identification, docking/virtual screening, and lead optimization, and (iv) closed-loop feedback that systematically incorporates experimental outcomes to update data resources and refine/validate models. This begins with the systematic collection of past experimental results to build high-quality databases. These databases, in turn, provide the foundation for developing AI-driven computational tools capable of precisely interfacing with and accelerating downstream tasks, such as molecular docking (for generating physically plausible conformations and conducting large-scale virtual screening) and lead optimization. The application of these AI tools not only guides experimental design, but the resulting key data also feed back into and enrich the databases. Furthermore, in the cutting-edge field of covalent drugs, the precise identification of "druggable" covalent sites on target proteins has emerged as another critically important downstream task.In this Account, we describe a computational and AI-driven ecosystem for structure-based covalent drug discovery and highlight our contributions to this field. By explicitly linking databases, models, workflows, and experimental feedback into a single framework, this Account moves beyond a simple inventory of individual tools to instead offer a systematic and panoramic perspective on an integrated ecosystem for covalent drug discovery, driven by data and computational engines including AI. We focus on how this ecosystem systematically addresses the challenges from covalent binding site identification to lead discovery, thereby fundamentally accelerating the development of next-generation covalent therapies. We first articulate the philosophy behind the construction and updating of covalent databases, emphasizing the necessity of high-quality data. Subsequently, we delve into a suite of cutting-edge, AI-driven computational methods, exploring the potential of deep learning in tasks such as molecular docking, covalent binding site prediction, and lead optimization. To bridge the gap between computational theory and experimental validation, we will use the discovery of potent covalent CRM1 inhibitors as a specific case study, detailing how our customized, structure-based virtual screening pipeline was utilized to achieve a seamless workflow from computational prediction to biological validation. This section is intended to offer actionable guidance for experimental researchers seeking to leverage these powerful computational tools. Finally, we highlight the limitations and potential pitfalls of this AI engine─concerns that are equally relevant when developing AI-driven covalent docking algorithms. Building on our group's recent benchmarking of AI docking methods, we objectively evaluate current performance and discuss how transformative advances such as AlphaFold3 may reshape the field.
Shi Li, Hongyan Du, Xujun Zhang et al.· Accounts of Chemical Researc...· 4 citations
The integration of organic synthesis with enzymatic catalysis offers a promising route toward efficient and sustainable construction of complex molecules. While organic synthesis enables diverse transformations, enzymatic catalysis enhances stereoselectivity under mild conditions, improving cost-effectiveness and environmental impact. However, current enzymatic synthesis planning algorithms face challenges in formulating robust hybrid organic–enzymatic strategies. Key issues include the difficulty in devising hybrid planning approaches and the reliance on template-based enzyme recommendations, which limits their adaptability across diverse scenarios. Here we show ChemEnzyRetroPlanner, an open-source hybrid synthesis planning platform that combines organic and enzymatic strategies with AI-driven decision-making. The platform features advanced computational modules, including hybrid retrosynthesis planning, reaction condition prediction, plausibility evaluation, enzymatic reaction identification, enzyme recommendation, and in silico validation of enzyme active sites. A central innovation is the RetroRollout* search algorithm, which outperforms existing tools in planning synthesis routes for organic compounds and natural products across multiple datasets. ChemEnzyRetroPlanner provides an intuitive graphical interface and programmatic APIs for scalability, while leveraging the chain-of-thought strategy and the Llama3.1 model to autonomously activate hybrid synthesis strategies for diverse scenarios. The results indicate that this fully automated, open-source system holds potential value for improving the efficiency and sustainability of molecular synthesis. The integration of organic and enzymatic synthesis enhances molecule construction efficiency. Here, the authors present ChemEnzyRetroPlanner, an AI-driven platform for automated hybrid synthesis planning, improving synthesis route efficiency and sustainability.
Designing effective mRNA sequences for therapeutics remains a formidable challenge. Inspired by successes in protein design, language models (LMs) are now being applied to RNA, but progress is often impeded by the lack of comprehensive training data. Existing models are frequently limited to UTR or CDS regions, restricting their application for complete mRNA sequences. We introduce mRNABERT, a robust, all-in-one mRNA designer pre-trained on the largest available mRNA dataset. To enhance performance, we propose a dual tokenization scheme with a cross-modality contrastive learning framework to integrate semantic information from protein sequences. On a comprehensive benchmark, mRNABERT demonstrates state-of-the-art performance, outperforming previous models in the majority of tasks for 5’ UTR and CDS design, RNA-binding protein (RBP) site prediction, and full-length mRNA property prediction. It also surpasses large protein models in several related tasks. In conclusion, mRNABERT’s superior performance across these diverse tasks signifies a substantial leap forward in mRNA research and therapeutic development. Designing complete mRNA sequences for new vaccines and therapies is a complex challenge. Here, the authors develop mRNABERT, a foundational AI model that designs entire mRNA sequences and demonstrates superior performance across comprehensive benchmarks.
Ying Xiong, Aowen Wang, Yu Kang et al.· Nature Communications· 22 citations· ⚡1
Molecular representation learning (MRL) has shown promise in accelerating drug development by predicting chemical properties. However, imperfectly annotation among datasets pose challenges in model design and explainability. In this work, we formulate molecules and corresponding properties as a hypergraph, extracting three key relationships: among properties, molecule-to-property, and among molecules, and developed a unified and explainable multi-task MRL framework, OmniMol. It integrates a task-related meta-information encoder and a task-routed mixture of experts (t-MoE) backbone to capture correlations among properties and produce task-adaptive outputs. To capture underlying physical principles among molecules, we implement an innovative SE(3)-encoder for physical symmetry, applying equilibrium conformation supervision, recursive geometry updates, and scale-invariant message passing to facilitate learning-based conformational relaxation. OmniMol achieves state-of-the-art performance in properties prediction, reaches top performance in chirality-aware tasks, demonstrates explainability for all three relations, and shows effective performance in practical applications. Our code is available in our https://github.com/bowenwang77/OmniMol public repository. AI models for drug discovery often struggle with real-world, incomplete data. Here, the authors present OmniMol, a framework using hypergraphs to improve predictions of molecular properties, addressing challenges of imperfect data annotation and enhancing model explainability.
The integration of large language models (LLMs) into drug design is gaining momentum; however, existing approaches often struggle to effectively incorporate three-dimensional molecular structures. Here, we present Token-Mol, a token-only 3D drug design model that encodes both 2D and 3D structural information, along with molecular properties, into discrete tokens. Built on a transformer decoder and trained with causal masking, Token-Mol introduces a Gaussian cross-entropy loss function tailored for regression tasks, enabling superior performance across multiple downstream applications. The model surpasses existing methods, improving molecular conformation generation by over 10% and 20% across two datasets, while outperforming token-only models by 30% in property prediction. In pocket-based molecular generation, it enhances drug-likeness and synthetic accessibility by approximately 11% and 14%, respectively. Notably, Token-Mol operates 35 times faster than expert diffusion models. In real-world validation, it improves success rates and, when combined with reinforcement learning, further optimizes affinity and drug-likeness, advancing AI-driven drug discovery. In this work the authors present Token-Mol, a token-only 3D drug design model, which deploys the Gaussian cross-entropy (GCE) loss function for regression tasks. It exhibits superior performance in molecular conformation generation, property prediction, and pocket-based generation, thus opening up new avenues for drug design.
Jike Wang, Rui Qin, Mingyang Wang et al.· Nature Communications· 30 citations· ⚡1
Reaction representation learning is of paramount importance for adopting deep-learning-based chemistry modeling to solve real-world tasks such as synthesis planning. Most prevailing models are prestrained by self-supervised objectives that rely solely on the chemical structure information. Since structurally similar reactions could possess entirely distinct properties (e.g., reaction yields) and the synthesis-related tasks are highly heterogeneous, there are inherent limitations in constructing a foundational reaction model within the existing approaches. To tackle this limitation, we propose HiCLR, a knowledge-induced hierarchical contrastive learning framework for chemical reactions, by introducing relational inductive bias to forge chemically meaningful and generally applicable reaction fingerprints. Critically, the pretraining scheme combining both retrosynthesis prediction and contrastive loss enables HiCLR to tackle generation-based and understanding-based tasks simultaneously. Comprehensive experiments demonstrate that HiCLR successfully organizes the reaction space into hierarchical global semantic clusters, aligned well with prior knowledge. Consequently, HiCLR is the first foundation model that can be broadly applied to various synthesis-related tasks, and it achieves state-of-the-art performance in reaction classification, reaction condition recommendation, reaction yield prediction, synthesis planning, and even molecular property prediction. HiCLR demonstrates clear benefits in incorporating domain knowledge to guide the learning of neural networks, expediting AI-driven advancements in chemistry.
Jialu Wu, Yiheng Zhu, Xiaorui Wang et al.· JACS Au· 0 citations
A new method, called CW-Net, translates the reasoning process of an autonomous vehicle’s AI system into understandable concepts that explain its behavior.
