Jul 2026· Journal of Medicinal Chemistry· Vol 69, pp. 18705-18722· 0 citations· 63 references
Medicine
Abstract
Predicting small molecule-protein interactions across nonhomologous proteins remains challenging because shared ligand recognition is often not evident from sequence, fold, or pocket similarity. Here, we introduce pocket hopping, a machine-learning framework that learns residue-level interaction patterns from coligand binding pockets and infers compatibility between nonhomologous pockets for similar chemotypes. Using shared ligands as supervision rather than explicit geometric alignment, pocket hopping identifies pocket relationships that are not readily captured by conventional chemical-, sequence-, or structure-based comparisons. In two case studies, pocket hopping demonstrates broad utility in drug discovery by enabling de novo hit identification and mechanistic interpretation, identifying fedratinib and its analogues as helicase WRN inhibitors. The model also identified the clinical-stage HDAC inhibitor abexinostat as a direct ENPP1 binder and inhibitor, and cellular assays showed enhanced cGAMP-STING signaling under cGAMP stimulation. Together, these results indicate that pocket-level compatibility can complement existing approaches for target identification, hit discovery, and polypharmacology analysis.
Generating molecules that jointly fit heterogeneous protein binding environments while retaining medicinal-chemistry plausibility remains challenging in computational dual-target design. We present PSGS-Drug, a generation-time dual-pocket framework that fuses localized token priors from the mitogen-activated protein kinase kinase 1 (MEK1) adenosine triphosphate (ATP)-site context in Protein Data Bank (PDB) entry 7PQV and the FK506-binding protein 12 (FKBP12)-FKBP12-rapamycin-binding (FRB) composite context of mechanistic target of rapamycin (mTOR) in PDB entry 3FAP, and uses contact-guided prefix initialization for rank-head exploration. The selected pair represents pathway-linked but structurally nonsymmetric intervention contexts: the druggable MEK1 ATP site and the mTOR-associated FKBP12-FRB composite interface. Their joint consideration is motivated by documented MEK/ERK-PI3K/AKT/mTOR cross-talk, compensatory resistance, and disease-specific preclinical evidence in NRAS mutant melanoma. [ Mendoza, M. C.; et al.Trends Biochem. Sci.2011, 36, 320-328.Kakadia, S.; et al.Onco Targets Ther.2018, 11, 7095-7107.Posch, C.; et al.Proc. Natl. Acad. Sci. U.S.A.2013, 110, 4015-4020.Mita, M.; et al.Invest. New Drugs2017, 35, 616-626, and.Wang, B.; et al.Oncogene2021, 40, 5590-5599]. Across five independent contact-guided runs standardized to 1889 unique valid molecules, PSGS-Drug achieved a mean summed two-context docking score (docksum) of -17.700 ± 0.242 and 29.00 ± 2.98% coverage of the stated operational dual-hit ≤-9.0 criterion; relative to independently repeated Pocket2Mol and PCMol comparators under the shared downstream protocol, it showed lower full-set docksum and higher operational dual-hit coverage after six-test Holm adjustment, and a five-seed matched A0 to A1 validation on the additional 5L2I-3ERT kinase-nuclear-receptor pair supported transfer of the fused-prior population-level effect. Docking scores, operational dual-hit labels, and residue-level contact analyses are interpreted as fixed-protocol computational prioritization signals that support candidate selection for this pathway-linked dual-context hypothesis. The biochemical and cellular activities of individual candidates remain to be tested; PSGS-Drug is therefore presented as an early stage, limitation-aware computational prioritization framework.
Yuchen Zhou, Tianhe Gu, Liang Tian et al.· Journal of Chemical Informat...· 0 citations
A five-agent workflow to systematically identify divergent protein-membrane-interface sites across class A GPCRs and exploit them for selective allosteric ligand discovery is developed, establishing a scalable strategy for translating GPCR membrane-interface divergence into precise allosteric sites and testable subtype-selective ligand candidates.
Jing-Yi Zhu, Hengde Li, Min Xiao et al.· bioRxiv· 0 citations
Allostery offers a powerful route to regulate protein function and expands drug discovery beyond the orthosteric paradigm. By acting at sites distinct from the active site, allosteric modulators can achieve greater selectivity, reduce off-target effects, and overcome resistance. The discovery of the cryptic switch-II pocket of KRAS, which turned a long-"undruggable" oncoprotein into a clinically validated target, exemplifies this promise. Yet allosteric drug discovery is demanding: it requires not only identifying a suitable, often transient pocket, but also demonstrating that this pocket is functionally coupled to the active site, and then translating that mechanistic insight into design. This perspective surveys the computational strategies addressing each of these challenges in turn: sequence, structure, and machine-learning-based methods for locating allosteric and cryptic sites; network and dynamical analyses for mapping communication pathways; and enhanced-sampling and generative deep-learning approaches for rational modulator design. Throughout, we emphasise a central theme: that generative AI delivers speed and breadth, while physics-based simulation supplies thermodynamic rigour, and that their integration, rather than either alone, defines the most promising path forward. Together with experimental validation, these advances are rapidly expanding our ability to exploit allosteric regulation in therapeutics.
Sutanu Mukhopadhyay, Suman Chakrabarty· Chemical Communications· 0 citations
A structural database that systematically maps the complete activation trajectories of pharmaceutically relevant targets, encompassing TS, IS, and all connecting conformational ensembles is presented, offering multiple strategic advantages for drug discovery.
Certain proteins known to be involved in life-threatening diseases have remained challenging therapeutic targets for decades, simply because a suitable binding pocket for a potent molecular inhibitor could not be identified in their ground-state apo structures. In the past decade, the discovery of cryptic pockets in challenging targets like KRAS and Werner helicase has proven to be a major turning point for therapeutic development. However, the alternate protein conformations required for these cryptic pockets to exist were only revealed by experiments conducted in the presence of ligands that can bind to them. Time-consuming and expensive experiments currently used to uncover these biologically rare events could be usefully complemented by a computational method capable of reliably identifying cryptic pockets. We have previously shown that aqueous and mixed-solvent Weighted Ensemble molecular dynamics (WEMD) simulations, driven by normal modes representing the direction of the most collective motion of a protein, can predict known cryptic pockets in the KRAS oncoprotein. Here, we evaluate this cryptic pocket detection technique on a data set of diverse proteins and show that it successfully samples cryptic pockets within 2 Å of the known holo conformation 57% of the time, starting with just the apo structure. The predicted pockets in the most holo-like conformations show at least 20%, 50%, and 80% volume overlap with the bound ligand in the holo structure, with success rates of 92%, 84%, and 46%, respectively. We also show that we can successfully rank candidate pockets from WEMD using our pocket ligandability prediction model, Target X.
N. Vithani, She Zhang, Judith Günther et al.· Journal of the American Chem...· 0 citations
Ptarmigan-1 is presented, a contrastive model that co-embeds the residues of a protein with candidate small molecules in a shared latent space, from sequence and two-dimensional chemistry alone, and without ever constructing a pose.
W. Fondrie, D. Canzani, L. Tatka et al.· bioRxiv· 1 citation
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
