From Latent Manifolds to Targeted Molecular Probes: An Interpretable, Kinome-Scale Generative Machine Learning Framework for Family-Based Kinase Ligand Design
Biomolecules · 2026
DOI: 10.3390/biom16020209 ↗Kurz gefasst
Fachartikel in der Zeitschrift Biomolecules, 2026. Verfasst von Gennady Verkhivker und 2 weiteren Autor:innen. Beteiligte Einrichtung: Graduate Program in Computational and Data Sciences, Keck Center for Science and Engineering, Schmid College of Science and Technology, Chapman Unive…. Hauptthemen laut MEDLINE: Machine Learning, Protein Kinase Inhibitors, Molecular Probes, Drug Design. Die Arbeit nennt 111 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: NIH HHS, National Institutes of Health.
Abstract (Originalsprache)
Scaffold-aware artificial intelligence (AI) models enable systematic exploration of chemical space conditioned on protein-interacting ligands, yet the representational principles governing their behavior remain poorly understood. The computational representation of structurally complex kinase small molecules remains a formidable challenge due to the high conservation of ATP active site architecture across the kinome and the topological complexity of structural scaffolds in current generative AI frameworks. In this study, we present a diagnostic, modular and chemistry-first generative framework for design of targeted SRC kinase ligands by integrating ChemVAE-based latent space modeling, a chemically interpretable structural similarity metric (Kinase Likelihood Score), Bayesian optimization, and cluster-guided local neighborhood sampling. Using a comprehensive dataset of protein kinase ligands, we examine scaffold topology, latent-space geometry, and model-driven generative trajectories. We show that chemically distinct scaffolds can converge toward overlapping latent representations, revealing intrinsic degeneracy in scaffold encoding, while specific topological motifs function as organizing anchors that constrain generative diversification. The results demonstrate that kinase scaffolds spanning 37 protein kinase families spontaneously organize into a coherent, low-dimensional manifold in latent space, with SRC-like scaffolds acting as a structural “hub” that enables rational scaffold transformation. Our local sampling approach successfully converts scaffolds from other kinase families (notably LCK) into novel SRC-like chemotypes, with LCK-derived molecules accounting for ~40% of high-similarity outputs. However, both generative strategies reveal a critical limitation: SMILES-based representations systematically fail to recover multi-ring aromatic systems—a topological hallmark of kinase chemotypes—despite ring count being a top feature in our structural similarity metric. This “representation gap” demonstrates that no amount of scoring refinement can compensate for a generative engine that cannot access topologically constrained regions. By diagnosing these constraints within a transparent pipeline and reframing scaffold-aware ligand design as a problem of molecular representation our work provides a conceptual framework for interpreting generative model behavior and for guiding the incorporation of structural priors into future molecular AI architectures.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Substanzen
Autor:innen und Institutionen
- Graduate Program in Computational and Data Sciences, Keck Center for Science and Engineering, Schmid College of Science and Technology, Chapman University, Orange, CA 92866, USA.
- Department of Biomedical and Pharmaceutical Sciences, Chapman University School of Pharmacy, Irvine, CA 92618, USA.
ORCID-Profile: Gennady Verkhivker
Förderung
- NIH HHS
- National Institutes of Health
Zitieren
APA
Verkhivker, G., Kassab, R., & Krishnan, K. (2026). From Latent Manifolds to Targeted Molecular Probes: An Interpretable, Kinome-Scale Generative Machine Learning Framework for Family-Based Kinase Ligand Design. Biomolecules. https://doi.org/10.3390/biom16020209
Vancouver
Verkhivker G, Kassab R, Krishnan K. From Latent Manifolds to Targeted Molecular Probes: An Interpretable, Kinome-Scale Generative Machine Learning Framework for Family-Based Kinase Ligand Design. Biomolecules. 2026. doi:10.3390/biom16020209
BibTeX
@article{Verkhivker2026,
author = {Verkhivker, Gennady and Kassab, Ryan and Krishnan, Keerthi},
title = {From Latent Manifolds to Targeted Molecular Probes: An Interpretable, Kinome-Scale Generative Machine Learning Framework for Family-Based Kinase Ligand Design},
journal = {Biomolecules},
year = {2026},
doi = {10.3390/biom16020209}
}
EUVIMED