Natarajan Arul Murugan

Linear B-cell epitopes are antigenic regions recognised by antibodies that play crucial roles in vaccine development, antibody production, and other therapeutic applications. Their prediction can support peptide-based vaccine candidate screening and diagnostic assay development, but the experimental data required for model development may be distributed across institutions that cannot freely pool their records. We present FedEpitope, a federated framework that adapts the ESM-2 protein language model for peptide-level linear B-cell epitope prediction using Low-Rank Adaptation (LoRA), keeping client-partitioned data local and restricting the communicated trainable model state to approximately 1.11 MB. Simulated benchmarks of FedAvg and FedProx algorithms, evaluated using homology-aware data splits of five biologically heterogeneous, organism-partitioned clients, achieve promising global test performance without centralising training data, with FedAvg outperforming all single-client models in mean AP, F1, and MCC. Additional experiments characterise post-federation personalisation, record-level differential privacy, sensitivity to controlled client heterogeneity, LoRA rank, and generalisation to the independent BCPreds and NetBCE benchmarks, demonstrating the feasibility of parameter-efficient federated protein language model adaptation for data-localised B-cell epitope prediction and the associated trade-offs among predictive performance, personalisation, privacy, communication efficiency, and distribution shift. VISUAL

Protein–ligand pose prediction is central to structure-based drug discovery, yet the relative performance of physics-based and AI-driven methods under realistic cross-docking conditions remains insufficiently characterized.

Protein kinases are among the most intensively pursued therapeutic targets in oncology and beyond, yet selectivity remains largely unsolved; around 536 Manning kinase domains share a conserved ATP-binding pocket, making it difficult to target one without hitting others. Allosteric binding modes which exploit conformational states unique to individual kinases or narrow kinase subfamilies offer a principled route to selectivity. Yet the absence of a kinome-wide structural landscape of these pockets limits their translational potential. Here we construct a machine learning-guided structural atlas of 11,945 kinase inhibitor complexes, training an Extra Trees classifier on pocket residue interaction with ligand to assign all seven canonical binding modes and resolve allosteric subclasses with pharmacological precision. Our structural analysis reveals that approximately 303 Manning kinase domains have known inhibitors bound to them, representing ~56.5% of the Manning kinase domain; of these, only 26% (78 kinases) are targeted by non-ATP-competitive allosteric inhibitors, indicating substantial unexplored pharmacological space. Integrating these classifications with the Manning kinome phylogeny, we demonstrate that evolutionary proximity is a statistically significant predictor of shared allosteric pocket accessibility. Because a functionally similar target has similar conformational dynamics and similar druggable pockets, 'phylogenetic druggability transfer' can act as a strong signal for identifying whether a given kinase can be targeted using an allosteric inhibitor or not. In addition, this work repositions the kinome phylogeny as a map of pharmacological opportunity and provides a reusable predictive framework for drug discovery programs - including orthosteric, allosteric, covalent, bifunctional inhibitors, and chemical degrader - across the understudied kinome.

In recent years, peptides have grabbed significant attention across many fields, including pharmaceutical, biomedical, and biotechnological industries, owing to their notable biological activity, low toxicity, and high specificity. Naturally occurring peptides play crucial roles in handling different biological processes (cellular signaling, immune responses, and enzymatic functions, etc.), while laboratory-made synthetic peptides can be adopted for many applied industrial applications. Following the practical problems in large-scale peptide synthesis in the laboratory which demand high cost and time, recent developments have benefited from the best use of machine learning (ML), deep learning, active learning, reinforcement learning (RL), generative artificial intelligence (AI), and large language models (LLMs) to reduce the number of experiments. ML algorithms enable the prediction of the peptide structure–activity relationship, bioavailability, and other drug-like properties with high accuracy. The integration of AI with peptide-based therapeutics design marks a paradigm shift in drug discovery which was otherwise dominated by small organic molecules. This review comprehensively examines AI-driven methodologies, including classical ML approaches, deep generative models, RL, and LLMs, that overcome historical limitations in peptide design, such as structural flexibility, enzymatic degradation, and membrane impermeability. Recent advances in structure-aware algorithms and sequence-based frameworks have accelerated peptide-based therapeutic development across oncology, metabolic disorders, and infectious diseases. Despite challenges in data scarcity and validation gaps, the convergence of computational prediction with experimental automation promises clinical translation of AI-designed peptides in the near future. This review highlights the transformative potential of AI in ushering a new era of precision peptide therapeutics.

Comprehensive evaluation of docking pipelines is crucial for determining which computational strategies yield the most reproducible ligand-binding poses.