Research Appraisals
Evidence-based critical appraisals of the latest medical research, systematically evaluated using Oxford CEBM methodology.
Showing 3 appraisals
Journal of chemical information and modeling
Unveiling Large-Scale Kinase-Centric Protein-Protein Interactions through a Knowledge-Informed Workflow
Protein phosphorylation regulates signaling, yet atomic-level substrate specificity remains elusive due to sparse structural data and phosphorylation-site-insensitive deep-learning predictors. Here we present a pipeline reformulating kinase-substrate modeling as a Bayesian inference problem. By integrating curated data sets and literature evidence parsed by Large Language Models, we converted diverse biological knowledge into structural restraints for the restraint-guided deep-learning model GRASP. For EGFR, BRAF and JNK1, we obtained 336 new phosphorylation-site-specific structure candidates refined by molecular dynamics. These models recapitulate known features, such as JNK1's hydrophobic docking groove, and enabled a Virtual Position Scanning Peptide Array (V-PSPA) to map recognition patches and derive sequence preferences. Cross-referencing predicted interfaces with AlphaMissense pathogenicity scores reveal that the interaction types and distances to the catalytic pocket significantly influence pathogenicity scores. A comparison with clinical mutation data sets further connects pathogenic mutations to the kinase-substrate interface. This high-resolution, high-throughput pipeline can be broadly applicable to kinase specificity studies and general drug discovery.
28 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 →Journal of chemical theory and computation
MolXProt: A Cross-Attention Transformer-Based Graph Neural Network for Protein-Ligand Binding Affinity Prediction
Accurate and fast prediction of drug-target binding affinities (DTAs) is key for drug discovery; however, many methods, such as docking and empirical scoring, fail when generalizing to unseen cases. In this study, we introduced the MolXProt architecture, a novel transformer-based graph neural network that integrates graph ligand representations with protein language models using bidirectional multihead cross-attention. Our model is shown to be scalable to over 100000 protein-ligand pairs of mixed data sets, achieving 50% of predictions within ±1.0 kcal/mol and 80% within ±2.0 kcal/mol. We show that the architecture can explicitly learn residue-atom interactions while being computationally friendly via protein-token compression. By mapping token-residue interactions, we demonstrated that the model learns key binding pocket residues in benchmark complexes, such as CDK2-Staurosporine and DHFR-Methotrexate, but under-represents the hydrogen-bonding networks. Our calibration bias analysis revealed that the model overpredicted strong binders and underpredicted weak binders, which are linked to data imbalances and heteroscedastic noise. A simple posthoc isotonic correction partially mitigated the bias. Latent space analysis showed that the model learned continuous binding affinity manifolds without split leakage. Our work highlights a novel architecture that offers unique insights into binding mechanisms via transformer-based cross-attention and is computationally inexpensive.
27 May 2026
Read appraisal →