Comprehensive assessment of protein loop modeling programs on large-scale datasets: prediction accuracy and efficiency

TRAP: a contrastive learning-enhanced framework for robust TCR-pMHC binding prediction with improved generalizability

The binding of T cell receptors (TCRs) to peptide-MHC I (pMHC) complexes is critical for triggering adaptive immune responses to potential health threats. Developing highly accurate machine learning (ML) models to predict TCR-pMHC binding could significantly accelerate immunotherapy advancements. However, existing ML models for TCR-pMHC binding prediction often underperform with unseen epitopes, severely limiting their applicability. We introduce TRAP, which leverages contrastive learning to enhance model performance by aligning structural and sequence features of pMHC with TCR sequences. TRAP outperforms previous state-of-the-art models in both random and unseen epitope scenarios, achieving an AUPR of 0.84 (a 22% improvement over the second-best model) and an AUC of 0.92 in the random scenario, and an AUC of 0.75 (almost 11% higher than the second-best model) in the unseen epitope scenario. Furthermore, TRAP demonstrates a noteworthy capability to diagnose potential issues of cross-reactivity between TCRs and similar epitopes. This highly robust performance makes it a suitable tool for large-scale predictions in real-world settings. A specific case study confirmed that TRAP can discover hit TCRs with binding free energies comparable to referenced experimental results. These findings highlight TRAP's potential for practical applications and its role as a powerful tool in developing TCR-based immunotherapies.

In silico drug repurposing of potential antiviral inhibitors targeting methyltransferase (2'-O-MTase) domain of Marburg virus

Marburg Virus (MARV) presents a significant threat to human health, highlighting the urgent need for effective therapeutics. The MARV genome encodes a multifunctional 'large' L protein that plays a crucial role in polymerase, capping, and methyltransferase activities. Within this protein, the 2'-O-methyltransferase (2'-O-MTase) domain is essential for viral replication and immune evasion, making it a promising therapeutic target. However, the lack of structural data on this domain limits drug discovery efforts. To address this challenge, we utilized AlphaFold2 to predict a 3D structure of the MARV 2'-O-MTase domain. Molecular docking with its natural ligand, S-adenosyl methionine (SAM), allowed us to identify key active-site residues involved in ligand binding. We then screened 62 known inhibitors against this domain and identified four promising candidates: Lifirafenib (- 9.5 kcal/mol), Dolutegravir (- 8.5 kcal/mol), BRD3969 (- 8.3 kcal/mol), and JFD00244 (- 8.2 kcal/mol). Further, we assessed the pharmacokinetic and pharmacodynamic properties of these compounds to evaluate their drug-likeness. Molecular dynamics simulations, along with MM/GBSA free energy calculations, confirmed stable interactions between the selected inhibitors and the target domain. While these findings highlight promising candidates for MARV, experimental validation through in vitro and in vivo assays is essential to assess their safety and efficacy.

Graphical abstract

Supplementary Information

The online version contains supplementary material available at 10.1007/s40203-025-00355-z.

ESM-Ezy: a deep learning strategy for the mining of novel multicopper oxidases with superior properties

The UniProt database is a valuable resource for biocatalyst discovery, yet predicting enzymatic functions remains challenging, especially for low-similarity sequences. Identifying superior enzymes with enhanced catalytic properties is even harder. To overcome these challenges, we develop ESM-Ezy, an enzyme mining strategy leveraging the ESM-1b protein language model and similarity calculations in semantic space. Using ESM-Ezy, we identify novel multicopper oxidases (MCOs) with superior catalytic properties, achieving a 44% success rate in outperforming query enzymes (QEs) in at least one property, including catalytic efficiency, heat and organic solvent tolerance, and pH stability. Notably, 51% of the MCOs excel in environmental remediation applications, and some exhibited unique structural motifs and unique active centers enhancing their functions. Beyond MCOs, 40% of L-asparaginases identified show higher specific activity and catalytic efficiency than QEs. ESM-Ezy thus provides a promising approach for discovering high-performance biocatalysts with low sequence similarity, accelerating enzyme discovery for industrial applications.

Tackling Undruggable Targets with Designer Peptidomimetics and Synthetic Biologics

The development of potent, specific, and pharmacologically viable chemical probes and therapeutics is a central focus of chemical biology and therapeutic development. However, a significant portion of predicted disease-causal proteins have proven resistant to targeting by traditional small molecule and biologic modalities. Many of these so-called "undruggable" targets feature extended, dynamic protein-protein and protein-nucleic acid interfaces that are central to their roles in normal and diseased signaling pathways. Here, we discuss the development of synthetically stabilized peptide and protein mimetics as an ever-expanding and powerful region of chemical space to tackle undruggable targets. These molecules aim to combine the synthetic tunability and pharmacologic properties typically associated with small molecules with the binding footprints, affinities and specificities of biologics. In this review, we discuss the historical and emerging platforms and approaches to design, screen, select and optimize synthetic "designer" peptidomimetics and synthetic biologics. We examine the inspiration and design of different classes of designer peptidomimetics: (i) macrocyclic peptides, (ii) side chain stabilized peptides, (iii) non-natural peptidomimetics, and (iv) synthetic proteomimetics, and notable examples of their application to challenging biomolecules. Finally, we summarize key learnings and remaining challenges for these molecules to become useful chemical probes and therapeutics for historically undruggable targets.

Highly Accurate and Efficient Deep Learning Paradigm for Full-Atom Protein Loop Modeling with KarmaLoop

Protein loop modeling is a challenging yet highly nontrivial task in protein structure prediction. Despite recent progress, existing methods including knowledge-based, ab initio, hybrid, and deep learning (DL) methods fall substantially short of either atomic accuracy or computational efficiency. To overcome these limitations, we present KarmaLoop, a novel paradigm that distinguishes itself as the first DL method centered on full-atom (encompassing both backbone and side-chain heavy atoms) protein loop modeling. Our results demonstrate that KarmaLoop considerably outperforms conventional and DL-based methods of loop modeling in terms of both accuracy and efficiency, with the average RMSDs of 1.77 and 1.95 Å for the CASP13+14 and CASP15 benchmark datasets, respectively, and manifests at least 2 orders of magnitude speedup in general compared with other methods. Consequently, our comprehensive evaluations indicate that KarmaLoop provides a state-of-the-art DL solution for protein loop modeling, with the potential to hasten the advancement of protein engineering, antibody-antigen recognition, and drug design.

Orphan G protein-coupled receptors: the ongoing search for a home

G protein-coupled receptors (GPCRs) make up the largest receptor superfamily, accounting for 4% of protein-coding genes. Despite the prevalence of such transmembrane receptors, a significant number remain orphans, lacking identified endogenous ligands. Since their conception, the reverse pharmacology approach has been used to characterize such receptors. However, the multifaceted and nuanced nature of GPCR signaling poses a great challenge to their pharmacological elucidation. Considering their therapeutic relevance, the search for native orphan GPCR ligands continues. Despite limited structural input in terms of 3D crystallized structures, with advances in machine-learning approaches, there has been great progress with respect to accurate ligand prediction. Though such an approach proves valuable given that ligand scarcity is the greatest hurdle to orphan GPCR deorphanization, the future pairings of the remaining orphan GPCRs may not necessarily take a one-size-fits-all approach but should be more comprehensive in accounting for numerous nuanced possibilities to cover the full spectrum of GPCR signaling.