Accurate prediction of drug-target interactions (DTIs) plays a pivotal role in drug discovery, facilitating optimization of lead compounds, drug repurposing and elucidation of drug side effects. However, traditional DTI prediction methods are often limited by incomplete biological data and insufficient representation of protein features. In this study, we proposed KG-CNNDTI, a novel knowledge graph-enhanced framework for DTI prediction, which integrates heterogeneous biological information to improve model generalizability and predictive performance. The proposed model utilized protein embeddings derived from a biomedical knowledge graph via the Node2Vec algorithm, which were further enriched with contextualized sequence representations obtained from ProteinBERT. For compound representation, multiple molecular fingerprint schemes alongside the Uni-Mol pre-trained model were evaluated. The fused representations served as inputs to both classical machine learning models and a convolutional neural network-based predictor. Experimental evaluations across benchmark datasets demonstrated that KG-CNNDTI achieved superior performance compared to state-of-the-art methods, particularly in terms of Precision, Recall, F1-Score and area under the precision-recall curve (AUPR). Ablation analysis highlighted the substantial contribution of knowledge graph-derived features. Moreover, KG-CNNDTI was employed for virtual screening of natural products against Alzheimer's disease, resulting in 40 candidate compounds. 5 were supported by literature evidence, among which 3 were further validated in vitro assays.

The accurate prediction of drug absorption, distribution, metabolism, excretion, and toxicity (ADMET) properties represents a crucial step in early drug development for reducing failure risk. Current deep learning approaches face challenges with data sparsity and information loss due to single-molecule representation limitations and isolated predictive tasks. This research proposes molecular properties prediction with parallel-view and collaborative learning (MolP-PC), a multi-view fusion and multi-task deep learning framework that integrates 1D molecular fingerprints (MFs), 2D molecular graphs, and 3D geometric representations, incorporating an attention-gated fusion mechanism and multi-task adaptive learning strategy for precise ADMET property predictions. Experimental results demonstrate that MolP-PC achieves optimal performance in 27 of 54 tasks, with its multi-task learning (MTL) mechanism significantly enhancing predictive performance on small-scale datasets and surpassing single-task models in 41 of 54 tasks. Additional ablation studies and interpretability analyses confirm the significance of multi-view fusion in capturing multi-dimensional molecular information and enhancing model generalization. A case study examining the anticancer compound Oroxylin A demonstrates MolP-PC’s effective generalization in predicting key pharmacokinetic parameters such as half-life (T0.5) and clearance (CL), indicating its practical utility in drug modeling. However, the model exhibits a tendency to underestimate volume of distribution (VD), indicating potential for improvement in analyzing compounds with high tissue distribution. This study presents an efficient and interpretable approach for ADMET property prediction, establishing a novel framework for molecular optimization and risk assessment in drug development.

The glucagon receptor (GCGR) is a critical target for the treatment of metabolic disorders such as Type 2 Diabetes Mellitus (T2DM) and obesity. Activation of GCGR enhances systemic insulin sensitivity through paracrine stimulation of insulin secretion, presenting a promising avenue for treatment. However, the discovery of effective GCGR agonists remains a challenging and resource-intensive process, often requiring time-consuming wet-lab experiments to synthesize and screen potential compounds. Recent advances in artificial intelligence technologies have demonstrated great potential in accelerating drug discovery by streamlining screening and efficiently predicting bioactivity. In the present work, we propose DeepGCGR, a two-layer deep learning model that leverages graph convolutional networks (GCN) integrated with a multiple attention mechanism to expedite the identification of GCGR agonists. In the first layer, the model predicts the bioactivity of various compounds against GCGR, efficiently filtering large chemical libraries to identify promising candidates. In the second layer, DeepGCGR classifies high bioactive compounds based on their functional effects on GCGR signaling, identifying those with potential agonistic or antagonistic effects. Moreover, DeepGCGR was specifically applied to identify novel GCGR-regulating compounds for the treatment of T2DM from natural products derived from traditional Chinese medicine (TCM). The proposed method will not only offer an effective strategy for discovering GCGR-targeting compounds with functional activation properties but also provide new insights into the development of T2DM therapeutics.

Artificial intelligence (AI) has emerged as a transformative technology in accelerating drug discovery and development within natural medicines research. Natural medicines, characterized by their complex chemical compositions and multifaceted pharmacological mechanisms, demonstrate widespread application in treating diverse diseases. However, research and development face significant challenges, including component complexity, extraction difficulties, and efficacy validation. AI technology, particularly through deep learning (DL) and machine learning (ML) approaches, enables efficient analysis of extensive datasets, facilitating drug screening, component analysis, and pharmacological mechanism elucidation. The implementation of AI technology demonstrates considerable potential in virtual screening, compound optimization, and synthetic pathway design, thereby enhancing natural medicines’ bioavailability and safety profiles. Nevertheless, current applications encounter limitations regarding data quality, model interpretability, and ethical considerations. As AI technologies continue to evolve, natural medicines research and development will achieve greater efficiency and precision, advancing both personalized medicine and contemporary drug development approaches.

Traditional Chinese medicine formula (TCMF) represents a fundamental component of Chinese medical practice, incorporating medical knowledge and practices from both Han Chinese and various ethnic minorities, while providing comprehensive insights into health and disease. The foundation of TCMF lies in its holistic approach, manifested through herbal compatibility theory, which has emerged from extensive clinical experience and evolved into a highly refined knowledge system. Within this framework, Chinese herbal medicines exhibit intricated characteristics, including multi-component interactions, diverse target sites, and varied biological pathways. These complexities pose significant challenges for understanding their molecular mechanisms. Contemporary advances in artificial intelligence (AI) are reshaping research in traditional Chinese medicine (TCM), offering immense potential to transform our understanding of the molecular mechanisms underlying TCMFs. This review explores the application of AI in uncovering these mechanisms, highlighting its role in compound absorption, distribution, metabolism, and excretion (ADME) prediction, molecular target identification, compound and target synergy recognition, pharmacological mechanisms exploration, and herbal formula optimization. Furthermore, the review discusses the challenges and opportunities in AI-assisted research on TCMF molecular mechanisms, promoting the modernization and globalization of TCM.

Traditional Chinese medicine (TCM) represents a paradigmatic approach to personalized medicine, developed through the systematic accumulation and refinement of clinical empirical data over more than 2000 years, and now encompasses large-scale electronic medical records (EMR) and experimental molecular data. Artificial intelligence (AI) has demonstrated its utility in medicine through the development of various expert systems (e.g., MYCIN) since the 1970s. With the emergence of deep learning and large language models (LLMs), AI’s potential in medicine shows considerable promise. Consequently, the integration of AI and TCM from both clinical and scientific perspectives presents a fundamental and promising research direction. This survey provides an insightful overview of TCM AI research, summarizing related research tasks from three perspectives: systems-level biological mechanism elucidation, real-world clinical evidence inference, and personalized clinical decision support. The review highlights representative AI methodologies alongside their applications in both TCM scientific inquiry and clinical practice. To critically assess the current state of the field, this work identifies major challenges and opportunities that constrain the development of robust research capabilities—particularly in the mechanistic understanding of TCM syndromes and herbal formulations, novel drug discovery, and the delivery of high-quality, patient-centered clinical care. The findings underscore that future advancements in AI-driven TCM research will rely on the development of high-quality, large-scale data repositories; the construction of comprehensive and domain-specific knowledge graphs (KGs); deeper insights into the biological mechanisms underpinning clinical efficacy; rigorous causal inference frameworks; and intelligent, personalized decision support systems.

Network pharmacology has gained widespread application in drug discovery, particularly in traditional Chinese medicine (TCM) research, which is characterized by its “multi-component, multi-target, and multi-pathway” nature. Through the integration of network biology, TCM network pharmacology enables systematic evaluation of therapeutic efficacy and detailed elucidation of action mechanisms, establishing a novel research paradigm for TCM modernization. The rapid advancement of machine learning, particularly revolutionary deep learning methods, has substantially enhanced artificial intelligence (AI) technology, offering significant potential to advance TCM network pharmacology research. This paper describes the methodology of TCM network pharmacology, encompassing ingredient identification, network construction, network analysis, and experimental validation. Furthermore, it summarizes key strategies for constructing various networks and analyzing constructed networks using AI methods. Finally, it addresses challenges and future directions regarding cell-cell communication (CCC)-based network construction, analysis, and validation, providing valuable insights for TCM network pharmacology.

Natural product-based drug combinations (NPDCs) present distinctive advantages in treating complex diseases. While high-throughput screening (HTS) and conventional computational methods have partially accelerated synergistic drug combination discovery, their applications remain constrained by experimental data fragmentation, high costs, and extensive combinatorial space. Recent developments in artificial intelligence (AI), encompassing traditional machine learning and deep learning algorithms, have been extensively applied in NPDC identification. Through the integration of multi-source heterogeneous data and autonomous feature extraction, prediction accuracy has markedly improved, offering a robust technical approach for novel NPDC discovery. This review comprehensively examines recent advances in AI-driven NPDC prediction, presents relevant data resources and algorithmic frameworks, and evaluates current limitations and future prospects. AI methodologies are anticipated to substantially expedite NPDC discovery and inform experimental validation.

Artificial intelligence (AI) researchers and cheminformatics specialists strive to identify effective drug precursors while optimizing costs and accelerating development processes. Digital molecular representation plays a crucial role in achieving this objective by making molecules machine-readable, thereby enhancing the accuracy of molecular prediction tasks and facilitating evidence-based decision making. This study presents a comprehensive review of small molecular representations and AI-driven drug discovery downstream tasks utilizing these representations. The research methodology begins with the compilation of small molecule databases, followed by an analysis of fundamental molecular representations and the models that learn these representations from initial forms, capturing patterns and salient features across extensive chemical spaces. The study then examines various drug discovery downstream tasks, including drug-target interaction (DTI) prediction, drug-target affinity (DTA) prediction, drug property (DP) prediction, and drug generation, all based on learned representations. The analysis concludes by highlighting challenges and opportunities associated with machine learning (ML) methods for molecular representation and improving downstream task performance. Additionally, the representation of small molecules and AI-based downstream tasks demonstrates significant potential in identifying traditional Chinese medicine (TCM) medicinal substances and facilitating TCM target discovery.

Due to its synergistic effects and reduced side effects, combination therapy has become an important strategy for treating complex diseases. In traditional Chinese medicine (TCM), the “monarch, minister, assistant, envoy” compatibilities theory provides a systematic framework for drug compatibility and has guided the formation of a large number of classic formulas. However, due to the complex compositions and diverse mechanisms of action of TCM, it is difficult to comprehensively reveal its potential synergistic patterns using traditional methods. Synergistic prediction based on molecular compatibility theory provides new ideas for identifying combinations of active compounds in TCM. Compared to resource-intensive traditional experimental methods, artificial intelligence possesses the ability to mine synergistic patterns from multi-omics and structural data, providing an efficient means for modeling and optimizing TCM combinations. This paper systematically reviews the application progress of AI in the synergistic prediction of TCM active compounds and explores the challenges and prospects of its application in modeling combination relationships, thereby contributing to the modernization of TCM theory and methodological innovation.

Traditional Chinese medicine (TCM) demonstrates distinctive advantages in disease prevention and treatment. However, analyzing its biological mechanisms through the modern medical research paradigm of “single drug, single target” presents significant challenges due to its holistic approach. Network pharmacology and its core theory of network targets connect drugs and diseases from a holistic and systematic perspective based on biological networks, overcoming the limitations of reductionist research models and showing considerable value in TCM research. Recent integration of network target computational and experimental methods with artificial intelligence (AI) and multi-modal multi-omics technologies has substantially enhanced network pharmacology methodology. The advancement in computational and experimental techniques provides complementary support for network target theory in decoding TCM principles. This review, centered on network targets, examines the progress of network target methods combined with AI in predicting disease molecular mechanisms and drug-target relationships, alongside the application of multi-modal multi-omics technologies in analyzing TCM formulae, syndromes, and toxicity. Looking forward, network target theory is expected to incorporate emerging technologies while developing novel approaches aligned with its unique characteristics, potentially leading to significant breakthroughs in TCM research and advancing scientific understanding and innovation in TCM.