Yuquan Li

Accurately predicting drug–target affinity (DTA) is crucial for accelerating virtual screening and guiding lead optimization in drug discovery. However, current computational approaches face a critical trade‐off: interaction‐free models lack fine‐grained binding details, while interaction‐based models overlook higher‐order contextual and functional patterns. This limitation hinders both prediction performance and real‐world generalization. To overcome this, we propose MF‐Net, a unified hierarchical multiscale fusion framework that integrates sequence‐, atomic‐, and fragment‐level representations to model drug–target interactions across complementary scales. MF‐Net achieves state‐of‐the‐art performance on the PDBBind v2016 benchmark and demonstrates strong early enrichment across multiple virtual screening datasets. Additionally, ADP‐Glo assays confirm that the MF‐Net‐guided virtual screening pipeline identifies seven novel nanomolar inhibitors targeting hematopoietic progenitor kinase 1 (HPK1). Among them, one compound achieves sub‐nanomolar activity (IC ₅₀ = 0.41 nM), outperforming the positive control inhibitor Sunitinib. These results demonstrate that MF‐Net not only excels on standard benchmarks but also delivers tangible lead discovery outcomes, underscoring its practical value for structure‐based drug design.

Discovering molecules with desirable molecular properties, including ADMET profiles, is of great importance in drug discovery. Existing approaches typically employ deep learning models, such as Graph Neural Networks and Transformers, to predict these molecular properties by learning from diverse chemical information. However, these models often lack mechanisms for effective interaction among multi-level features. To address these limitations, we propose a Hierarchical Interaction Message Passing Mechanism, which serves as the foundation of our model, the Hierarchical Interaction Message Net (HimNet). Our method enables interaction-aware representation learning across atomic, motif, and molecular levels via hierarchical attention-guided message passing. This design allows HimNet to effectively balance global and local information, ensuring rich and task-relevant feature extraction for downstream property prediction tasks. We systematically evaluate HimNet on eleven datasets, including eight widely-used MoleculeNet benchmarks and three challenging, high-value datasets for metabolic stability, malaria activity, and liver microsomal clearance, covering a broad range of pharmacologically relevant properties. Extensive experiments demonstrate that HimNet achieves the best or near-best performance in most molecular property prediction tasks. We believe that HimNet offers an accurate and efficient solution for molecular activity and ADMET property prediction, contributing significantly to advanced decision-making in the early stages of drug discovery.

Accurately predicting physicochemical and biological properties of molecules is vital for modern drug discovery, yet existing deep learning models struggle to replicate the multi‐level reasoning of chemists. Relying on single molecular graphs, they fail to capture the interplay among global scaffolds, functional groups, and pharmacophoric patterns, and often miss subtle perturbations causing “activity cliffs”. PrismNet is proposed as a spectral graph network that mimics chemical intuition through a computational prism analogy. It applies a dual‐decomposition strategy: refracting molecules into three chemical perspectives—scaffolds, functional groups, and pharmacophores—and resolving each into spectral frequencies. A dynamic learning strategy further enhances its ability to handle heterogeneous data. PrismNet achieves state‐of‐the‐art performance across 64 benchmark datasets, including 30 activity cliff datasets. Importantly, its predictions are chemically interpretable, autonomously identifying key substructures aligned with known structure‐activity relationships. This framework unifies multi‐scale semantics and spectral decomposition, enabling reliable and trustworthy in silico screening for drug discovery.

Developing selective kinase inhibitors is challenging due to the conserved kinase structures and costly kinome profiling experiments, highlighting the need for accurate prediction of kinase-inhibitor affinity and specificity. Here we present MMCLKin, an attention consistency-guided contrastive learning framework that integrates geometric graph and sequence networks with multi-head attention and multimodal, multiscale contrastive learning to accurately and interpretably predict kinase-inhibitor activity and selectivity. MMCLKin outperforms existing methods across two 3D kinase-drug datasets and demonstrates strong generalizability on ten diverse protein-drug and one mutation-aware datasets, and effectively screens on both known and unknown kinase structures. In-depth analysis of attention coefficients reveals that MMCLKin can identify key residues and molecular functional groups critical for kinase-inhibitor binding. Additionally, ADP-Glo assays confirm that five out of 20 MMCLKin-identified compounds inhibit the pathogenic LRRK2 G2019S mutant, with four exhibiting nanomolar-level potency. Collectively, MMCLKin represents a useful tool for discovering potent and selective kinase inhibitors.

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.

Discovering molecules with desirable molecular properties, including ADMET profiles, is of great importance in drug discovery. Existing approaches typically employ deep learning models, such as Graph Neural Networks and Transformers, to predict these molecular properties by learning from diverse chemical information. However, these models often lack mechanisms for effective interaction among multi-level features. To address these limitations, we propose a Hierarchical Interaction Message Passing Mechanism, which serves as the foundation of our novel model, the Hierarchical Interaction Message Net (HimNet). Our method enables interaction-aware representation learning across atomic, motif, and molecular levels via hierarchical attention-guided message passing. This design allows HimNet to effectively balance global and local information, ensuring rich and task-relevant feature extraction for downstream property prediction tasks. We systematically evaluate HimNet on eleven datasets, including eight widely-used MoleculeNet benchmarks and three challenging, high-value datasets for metabolic stability, malaria activity, and liver microsomal clearance, covering a broad range of pharmacologically relevant properties. Extensive experiments demonstrate that HimNet achieves the best or near-best performance in most molecular property prediction tasks. We believe that HimNet offers an accurate and efficient solution for molecular activity and ADMET property prediction, contributing significantly to advanced decision-making in the early stages of drug discovery.

Annotating active sites in enzymes is crucial for advancing multiple fields including drug discovery, disease research, enzyme engineering, and synthetic biology. Despite the development of numerous automated annotation algorithms, a significant trade-off between speed and accuracy limits their large-scale practical applications. We introduce EasIFA, an enzyme active site annotation algorithm that fuses latent enzyme representations from the Protein Language Model and 3D structural encoder, and then aligns protein-level information with the knowledge of enzymatic reactions using a multi-modal cross-attention framework. EasIFA outperforms BLASTp with a 10-fold speed increase and improved recall, precision, f1 score, and MCC by 7.57%, 13.08%, 9.68%, and 0.1012, respectively. It also surpasses empirical-rule-based algorithm and other state-of-the-art deep learning annotation method based on PSSM features, achieving a speed increase ranging from 650 to 1400 times while enhancing annotation quality. This makes EasIFA a suitable replacement for conventional tools in both industrial and academic settings. EasIFA can also effectively transfer knowledge gained from coarsely annotated enzyme databases to smaller, high-precision datasets, highlighting its ability to model sparse and high-quality databases. Additionally, EasIFA shows potential as a catalytic site monitoring tool for designing enzymes with desired functions beyond their natural distribution.

Improving drug discovery efficiency is a core and long-standing challenge in drug discovery. For this purpose, many graph learning methods have been developed to search potential drug candidates with fast speed and low cost. In fact, the pursuit of high prediction performance on a limited number of datasets has crystallized them, making them lose advantage in repurposing to new data generated in drug discovery. Here we propose a flexible method that can adapt to any dataset and make accurate predictions. The proposed method employs an adaptive pipeline to learn from a dataset and output a predictor. Without any manual intervention, the method achieves far better prediction performance on all tested datasets than traditional methods, which are based on hand-designed neural architectures and other fixed items. In addition, we found that the proposed method is more robust than traditional methods and can provide meaningful interpretability. Given the above, the proposed method can serve as a reliable method to predict molecular interactions and properties with high adaptability, performance, robustness and interpretability. This work would take a solid step forward to the purpose of aiding researchers to design better drugs with high efficiency.