reinforcement learning

Computational and AI-Driven Ecosystem for Structure-Based Covalent Drug Discovery.

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.

DRHIN: An Integrated and Interactive Web Server for Drug Repositioning

Drug repositioning (DR) identifies new therapeutic uses for approved drugs, reducing development burdens and offering safer treatment options for patients. While high-throughput technologies generate complex, large-scale multiomics data, existing DR tools struggle to comprehensively analyze the resulting biological networks. To address this challenge, we present DRHIN, an integrated, interactive web server for DR over heterogeneous information networks (HINs) using advanced deep learning techniques. DRHIN integrates transcriptomics, proteomics, and microbiome data, incorporating eight biological entities and 19 association types to build diverse HINs and elucidate the underlying molecular mechanisms. It includes 19 state-of-the-art graph representation algorithms, enabling flexible training, comparison, and evaluation of heterogeneous network data. The platform provides a code-free portal supporting three key predictive tasks: discovering drug-disease associations, repurposing existing drugs for new indications, and identifying potential therapies for specific diseases, making analyses accessible and reproducible. Leveraging high-performance computing, DRHIN efficiently processes million-scale networks, ensuring practical applicability in real-world scenarios. The web server is freely accessible at http://drhin.tianshanzw.cn.

Integration of molecular coarse-grained model into geometric representation learning framework for protein-protein complex property prediction

Structure-based machine learning algorithms have been utilized to predict the properties of protein-protein interaction (PPI) complexes, such as binding affinity, which is critical for understanding biological mechanisms and disease treatments. While most existing algorithms represent PPI complex graph structures at the atom-scale or residue-scale, these representations can be computationally expensive or may not sufficiently integrate finer chemical-plausible interaction details for improving predictions. Here, we introduce MCGLPPI, a novel geometric representation learning framework that combines graph neural networks (GNNs) with the MARTINI molecular coarse-grained (CG) model to predict overall PPI properties accurately and efficiently. This framework maps proteins onto a concise CG-scale complex graph, where nodes represent CG beads and edges encode chemically plausible interactions. The GNN-based encoder is tailored to extract high-quality representations from this graph, efficiently capturing the overall properties of the protein complex structure. Extensive experiments on three different downstream PPI property prediction tasks demonstrate that MCGLPPI achieves competitive performance compared with the counterparts at the atom- and residue-scale, but with only a third of the computational resource consumption. Furthermore, the CG-scale pre-training on protein domain-domain interaction structures enhances its predictive capabilities for PPI tasks. MCGLPPI offers an effective and efficient solution for PPI overall property predictions, serving as a promising tool for the large-scale analysis of biomolecular interactions.

A Multi-Modal Deep Learning Framework with Both Sequence and Structure for Tumor Antigens Prediction

mRNABERT: advancing mRNA sequence design with a universal language model and comprehensive dataset

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.

Unified and explainable molecular representation learning for imperfectly annotated data from the hypergraph view

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.

Token-Mol 1.0: tokenized drug design with large language models

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.

A fused deep learning approach to transform drug repositioning

Drug repositioning holds promise for discovering new therapeutic applications for existing drugs, accelerating drug development and reducing associated costs. However, current methodologies encounter difficulties in managing diverse network representations, tackling cold start issues, and handling intrinsic attribute representations. Here we introduce a Unified Knowledge-Enhanced deep learning framework for Drug Repositioning (UKEDR), which integrates knowledge graph embedding, pre-training strategies, and recommendation systems to address these challenges. To overcome the cold start issue, UKEDR utilizes a semantic similarity-driven embedding approach. Our evaluations show that UKEDR performs better than various baselines, including classical machine learning, network-based, and deep learning approaches. In cold start scenarios, it demonstrates an improved capability in handling unseen nodes and generalizing to new compounds. The model also demonstrates strong robustness on imbalanced datasets and shows excellent generalization capabilities in specific drug-centric and disease-centric cold-start scenarios, validating its potential for real-world applications. Drug repositioning offers a promising avenue for accelerating drug development, yet existing methods struggle with network diversity, cold start issues, and intrinsic attribute representation. Here, the authors introduce UKEDR, a deep learning framework that integrates knowledge graph embedding and pre-training strategies to overcome the intractable cold start issue, achieving superior performance and interpretability in drug repurposing.

Enhanced Sampling in the Age of Machine Learning: Algorithms and Applications

Molecular dynamics simulations hold great promise for providing insight into the microscopic behavior of complex molecular systems. However, their effectiveness is often constrained by long timescales associated with rare events. Enhanced sampling methods have been developed to address these challenges, and recent years have seen a growing integration with machine learning techniques. This Review provides a comprehensive overview of how they are reshaping the field, with a particular focus on the data-driven construction of collective variables. Furthermore, these techniques have also improved biasing schemes and unlocked novel strategies via reinforcement learning and generative approaches. In addition to methodological advances, we highlight applications spanning different areas, such as biomolecular processes, ligand binding, catalytic reactions, and phase transitions. We conclude by outlining future directions aimed at enabling more automated strategies for rare-event sampling.

HiCLR: Knowledge-Induced Hierarchical Contrastive Learning with Retrosynthesis Prediction Yields a Reaction Foundation Model

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.

RSGPT: a generative transformer model for retrosynthesis planning pre-trained on ten billion datapoints

Retrosynthesis planning is a crucial task in organic synthesis, and deep-learning methods have enhanced and accelerated this process. With the advancement of the emergence of large language models, the demand for data is rapidly increasing. However, available retrosynthesis data are limited to only millions. Therefore, we pioneer the utilization of the template-based algorithm to generate chemical reaction data, resulting in the production of over 10 billion reaction datapoints. A generative pretrained transformer model is subsequently developed for template-free retrosynthesis planning by pre-training on 10 billion generated data. Inspired by the strategies of large language models, we introduce reinforcement learning to capture the relationships among products, reactants, and templates more accurately. Experiments demonstrate that our model achieves state-of-the-art performance on the benchmark, with a Top-1 accuracy of 63.4%, substantially outperforming previous models. Computer-aided synthesis-planning methods have significantly assisted synthesis planning. In this work, the authors present RSGPT, a generative model pre-trained on ten billion data points, achieving state-of-the-art performance for synthesis planning

AntiBMPNN: Structure‐Guided Graph Neural Networks for Precision Antibody Engineering

Antibodies are crucial for medical applications, yet traditional methods for designing sequences are inefficient. This study introduces AntiBMPNN, an advanced deep‐learning framework that leverages an antibody‐specific 3D dataset, a fine‐tuned message‐passing neural network (MPNN), a frequency‐based scoring function, and AlphaFold 3 to achieve highly accurate antibody sequence design. AntiBMPNN surpasses ProteinMPNN with a perplexity of 1.5 and over 80% sequence recovery. Its scoring function, combined with AlphaFold 3, effectively prioritizes sequences based on structural recovery, positional stability, and biochemical or complex properties. Experimental validation highlights a 75% success rate in single‐point antibody design. AntiBMPNN consistently outperforms AbMPNN, AntiFold, and ProteinMPNN in designing complementarity determining regions (CDR) 1‐3, yielding stronger binding affinities. For CDR1 of huJ3 (anti‐HIV nanobody), it achieves a half maximal effective concentration (EC₅₀) of 9.2 nM (nanomolar), better than ProteinMPNN (135.2 nM) and AntiFold (59.3 nM), and comparable to AbMPNN (6.6 nM). For CDR2 of the D6 nanobody (targeting CD16), AntiBMPNN reaches 0.3 nM, outperforming AbMPNN (2.3 nM), AntiFold (0.7 nM), and ProteinMPNN (0.7 nM). In CDR3 of huJ3, it achieves 1.7 nM, surpassing AbMPNN (51.2 nM), with no detectable activity from AntiFold or ProteinMPNN. These findings confirm that AntiBMPNN‐designed sequences for J3 and D6 outperform the originals, highlighting its potential to improve therapeutic antibody design.