Research Appraisals
Evidence-based critical appraisals of the latest medical research, systematically evaluated using Oxford CEBM methodology.
Showing 11 appraisals
Current opinion in chemical biology
Prediction of protein-protein interactions and co-complex models with deep learning
Protein-protein interactions (PPIs) are fundamental to cellular processes, and essential for understanding biological function and disease mechanisms. In this review, we emphasize recent deep learning-based methods for protein interaction study. Focusing on three closely related tasks of proteome-wide PPI prediction, PPI interface prediction, and PPI co-complex structure prediction, we discuss how emerging concepts and computation approaches have evolved to shape these fields We categorize recent approaches according to their methodological paradigms, summarize their strengths and limitations, and further explore diverse biological and biomedical applications, highlighting how computational methods in PPI prediction, PPI interface prediction, and PPI structure prediction jointly contribute to understanding of complex biological systems.
3 Aug 2026
Read appraisal →Journal of chemical information and modeling
HyperDC: A Non-Uniform Hypergraph Framework for Dual- and Higher-Order Drug Combination Recommendation Across Diverse Complex Diseases
Complex diseases are commonly characterized by dysregulation across multiple targets and pathways, making drug combinations an important therapeutic strategy. This creates a growing need for computational methods to prioritize candidate combinations, yet current methods face several practical challenges, including cross-disease application, unified prediction of dual- and multidrug combinations, lack of reliable negative labels, and prediction for low-resource diseases. In this study, we proposed HyperDC, a unified cross-disease drug combination recommendation framework. HyperDC constructs a nonuniform hypergraph based on clinical and knowledge-driven drug-disease association data, representing single drugs and dual- and multidrug combinations in a unified modeling space. It further integrates knowledge graph pretraining and adversarial negative sampling to enhance model discrimination across tasks with different difficulty levels. In the unified dual-drug benchmark and disease-specific prediction tasks, HyperDC outperformed representative methods by up to 12.8 and 30.0 percentage points, respectively. In fixed-anchor clinical ranking tasks, HyperDC showed superior performance across multiple top-ranked recall settings and preferentially recalled FDA-approved dual-drug combinations and clinically supported three-drug combinations. In the data-sparse metabolic dysfunction-associated steatohepatitis (MASH) scenario, HyperDC completed a full workflow from anchor-drug identification and combination partner prioritization to in vitro experimental validation: 70% of the top 10 single-drug candidates were supported by recent literature, and 4 of 6 tested combinations showed synergistic lipid-lowering and anti-inflammatory effects, yielding a hit rate of 66.7%. Overall, HyperDC may narrow the screening space, improve prioritization efficiency, and provide methodological support for the development of combination therapy strategies for complex diseases.
29 July 2026
Read appraisal →Journal of chemical information and modeling
Reinforcement Learning-Driven Multiproperty Optimization in Molecular Design Using Multicontext Transcriptome Data
Drug discovery inherently involves multiparameter optimization in the molecular design because drug candidate molecules must meet diverse properties such as bioactivity, synthesizability, and pharmacokinetic properties. This optimization has traditionally relied on iterative manual design and experimental testing, which are labor-intensive and time-consuming. There is therefore a strong incentive to develop computational methods that efficiently design drug-like molecules with multiple favorable properties using chemical and biological data on therapeutic targets. This study proposes a novel computational method for multiproperty optimization in the molecular structure design of bioactive molecules using multicontext (i.e., chemically and genetically perturbed) transcriptome data on human cells. We integrate a molecular generative model conditioned on a transcriptome profile observed with the target gene knockdown or overexpression into a reinforcement learning framework, enabling simultaneous optimization of a quantitative estimate of drug-likeness, synthetic accessibility score, and water/octanol partition coefficient, while accounting for system-level biological effects on a therapeutic target. Using comprehensive benchmarking against established baselines and rigorous validation across multiple metrics, we demonstrate that the proposed method consistently yields molecules with more favorable drug-like characteristics than existing methods. This proposed method can help achieve more efficient identification of novel drug candidates.
29 July 2026
Read appraisal →Bioconjugate chemistry
Artificial Intelligence for Discovery in Life Sciences
Artificial intelligence is becoming a transformative tool in life sciences, not just by improving the results of existing technologies but also by introducing fundamental new ways of discovery. Initially applied to denoising, segmentation, or pattern recognition, it now extends across microscopy, structural biology, protein engineering, experimental design, and hypothesis generation. In imaging, deep learning enhances fluorescence, cryo-EM, and expansion microscopy and increasingly links optical and non-optical modalities. Beyond imaging, AI accelerates fluorescent probe development, while large language models and multi-agent systems are beginning to synthesize literature, generate hypotheses, and guide experiments. We survey these developments across imaging and non-imaging domains, from microscopy and structural biology to molecular design, hypothesis generation, and autonomous experimentation. We discuss the convergence of AI with tools from chemistry to instrumentation and explain challenges in validation, interpretability, generalizability, and autonomy. We conclude that AI is beginning to connect measurement, design, and reasoning to accelerate biological discovery.
16 July 2026
Read appraisal →Nucleic acids research
DeepCYP: an integrated deep learning web server for the holistic 'pathway-site product' prediction of CYP450 metabolism
CYP450 (cytochrome P450)-mediated drug metabolism is a critical determinant of pharmacokinetics and clinical safety, making comprehensive metabolic profiling essential for rational drug discovery. Here, we present DeepCYP (https://deepcyp.scbdd.com), a freely accessible deep-learning web server for end-to-end CYP450 metabolic profiling. Trained on an expanded dataset and a mechanism-based reaction rule library, DeepCYP uses a multi-task graph neural network (GNN) combined with multi-scale descriptors. Operating directly on 2D molecular graphs, this architecture bridges the entire "pathway-site-product" continuum across nine major CYP isoforms (CYP1A2, CYP2A6, CYP2B6, CYP2C8, CYP2C9, CYP2C19, CYP2D6, CYP2E1, and CYP3A4) within a unified pipeline. Benchmarking demonstrates that DeepCYP outperforms established tools, including FAME3, SMARTCyp, and BioTransformer 3.0, improving Top-1 and Top-2 ranking metrics by over 10%. Furthermore, the server supports high-throughput batch processing, capable of evaluating ~280 molecules per minute. DeepCYP also enhances interpretability through an interactive visualization interface, featuring susceptibility radar charts and dynamic transformation tables. By translating abstract predictions into biological insights, DeepCYP provides a practical tool to accelerate lead optimization and mitigate toxicity risks.
13 July 2026
Read appraisal →Journal of medicinal chemistry
Machine Learning-Based Models to Predict Drug-Induced Liver Injury (DILI) to Assist Medicinal Chemistry
Drug-induced liver injury (DILI) is a leading cause of drug failure and post-market withdrawals. Traditional preclinical methods fail to detect up to 40-45% of clinical hepatotoxicity cases. Computational approaches, particularly those based on machine learning and deep learning (DL), are emerging as promising tools to support medicinal chemistry and early drug discovery, though their predictive capabilities remain under active investigation. In this perspective, we review the development of DILI annotation data sets, tracing their growth from small collections to large, comprehensive resources. We also outline the evolution of computational methods, from simple descriptor-based models to advanced DL and ensemble approaches that incorporate interpretable features. Finally, we highlight recent efforts to integrate standardized causality frameworks, pharmacogenomics, and mechanistic models, aiming to connect computational advances with clinical relevance. This perspective provides valuable insight for researchers and promotes the development of more robust and consensual DILI prediction strategies.
10 July 2026
Read appraisal →Journal of computer-aided molecular design
Two faces of drug repurposing data in machine learning-driven structure-based virtual screening supported by interaction fingerprints
Ensemble docking is a prominent source of protein-ligand complex structures, which could be conveniently analyzed with interaction fingerprints approach in a machine learning framework. Nevertheless, the chemical nature and provenance of the source data libraries used for model development may influence the predictive ability. We assessed the performance of SARS-CoV-2 main protease (Mpro) inhibitors classification by random forest models trained on different fingerprint implementations using three inhibitor libraries, comprising drug repurposing data or compounds rationally designed as Mpro inhibitors. Models trained on drug repurposing data showed a low prediction performance on their own, while infusion of these data into libraries with specific inhibitors greatly improved applicability domains of the models. Our results highlight the importance of balanced dataset preparation for machine learning applications in medicinal chemistry, especially when relied on drug repurposing experiments.
8 July 2026
Read appraisal →Molecular pharmaceutics
Computational Identification of Active Drug Metabolites for Human Protein Targets
Understanding drug metabolism helps mitigate toxicity risks and anticipate pharmacological effects beyond the parent compound. Here, we explore high-confidence in vitro human bioactivity annotations from the public domain associated with a curated data set of drug-metabolite pairs. Our findings show that 26% of all drug-metabolite-target combinations contain metabolites with retained or increased bioactivity relative to their parent drugs, showing a high proportion of active metabolites with potencies below 100 nM. Moreover, these active metabolites display similar predicted physicochemical and ADME properties to their parent drugs, indicating that their biological activity may be preserved in vivo. Two key features of the identified active metabolites are noted: (1) the metabolite is more likely to be formed via an O-demethylation or an N-demethylation at a tertiary nitrogen, and (2) these drug-metabolite pairs are frequently active against the membrane receptor target class. To support further research in this area, we make our data compilation, including pairs with identified active metabolites and recorded bioactivity data, openly available.
7 July 2026
Read appraisal →PloS one
A multi-modal co-attention model for accurate drug-target interaction prediction
Accurate prediction of drug-target interactions (DTIs) plays a crucial role in modern drug discovery and repositioning. Despite recent advances in deep learning, existing methods often fail to effectively integrate heterogeneous data, such as molecular structures and protein sequences, into a unified representation. To address this limitation, we propose MMCA (Multi-Modal Co-Attention), a novel deep learning framework that introduces a multi-modal co-attention mechanism to dynamically align and fuse graph-based drug features with sequence-based protein embeddings. Our model leverages parallel encoding pathways to capture both structural and semantic information, followed by a context-aware fusion module that adaptively weighs cross-modal dependencies. Evaluation on three benchmark datasets-BioSNAP, BindingDB, and Human STRING-demonstrates that MMCA outperforms state-of-the-art methods in terms of AUC, AUPR, and F1-score, achieving up to 98.4% AUC. Ablation studies confirm the significance of our co-attention fusion mechanism in enhancing both accuracy and robustness. Case studies of high-confidence predictions reveal biologically plausible drug-protein interactions, supporting MMCA's potential for prioritizing candidates for experimental validation. By enabling end-to-end multi-modal reasoning, MMCA provides a powerful framework for advancing DTI prediction systems and offers broad applicability for various bioinformatics tasks. The source code of MMCA is publicly available at https://github.com/Join-xiaobai/MMCA.
25 June 2026
Read appraisal →Journal of chemical information and modeling
Generative Artificial Intelligence Optimization of Albumin Binders: Coumarin and Fatty Acid Derivatives
Previously, we reported a dual combination based on 4-hydroxycoumarin and dodecanedioic acid that could synergistically bind to human serum albumin (HSA). However, optimizing this combination remains challenging and could often be guided by empirical selection and extensive experimental screening, which may limit the chemical diversity and suboptimal affinity. In this study, we established a systematic artificial intelligence framework that integrates computational optimization with wet-lab synthesis and experimental validation, enabling improvement of the dual combination while preserving the core chemotypes. We first trained a machine learning classifier on curated HSA binding data and used it as an external scoring function to guide reinforcement learning-driven scaffold decoration with LibINVENT, enabling goal-directed generation of coumarin derivatives and fatty acid derivatives. Candidate molecules were prioritized through multiparameter filtering and diversity-aware selection, followed by synthesis and experimental validation using surface plasmon resonance. The optimized representatives show nanomolar HSA binding and enhanced affinity compared to the original ligands. Molecular docking and molecular dynamics simulations further provide a mechanistic rationale for the affinity improvements by revealing additional stabilizing interactions and more favorable binding energetics at the corresponding HSA sites. Besides, the optimized coumarin derivative (CD1) is a warfarin-derived coumarin analogue, yet it did not show detectable anticoagulant activity in an acute clotting time assay, whereas warfarin did. Overall, this work demonstrates a practical AI-guided route to expand chemical diversity and improve affinity for a synergistic HSA binding combination.
23 June 2026
Read appraisal →Science advances
Discovery of TYR inhibitors from de novo molecular generation to dual-track lead optimization: 'Competition' between AI and chemists.
This study introduces a unified framework combining artificial intelligence (AI)-directed de novo molecular generation with dual-track lead optimization-comprising expert-guided strategies and AI-driven pathways-to discover tyrosinase (TYR) inhibitors for hyperpigmentation disorders. Using a reinforcement learning (RL)-based generative model, the lead compound AI10 was identified. Subsequent optimization followed two parallel routes. The expert-guided approach yielded AI10-m15 as the most potent TYR inhibitor, with notable antipigmentation activity and excellent cellular safety profiles. In contrast, the AI-driven pathway explored broader chemical spaces, generating unconventional chemotypes, exemplified by the potent TYR inhibitor AI10-a2, highlighting AI's capacity to uncover nonintuitive activity cliffs despite greater output variability. Systematic comparison revealed that the AI model offers exploratory diversity, whereas expert-guided optimization provides predictable improvements in activity and developability. In summary, starting from an AI-generated lead and subsequently integrating both expert-guided and AI-driven structural optimization strategies, these findings further underscore that combining AI technologies with experts' medicinal chemistry insights can substantially accelerate the discovery of viable candidate compounds.
21 June 2026
Read appraisal →