AI-Driven De Novo Design and Development of Nontoxic DYRK1A Inhibitors

E. González García, P. Varas, P. González-Naranjo, E. Ulzurrun, G. Marcos-Ayuso, C. Pérez, J.A. Páez, D. Ríos Insua, S. Rodríguez-Santana, N.E. Campillo

Journal of Medicinal Chemistry

Summary:

Dual-specificity tyrosine-phosphorylation-regulated kinase 1A (DYRK1A) is implicated in several human diseases, including DYRK1A syndrome, cancer, and neurodegenerative disorders such as Alzheimer’s disease, making it a relevant therapeutic target. In this study, we combine artificial intelligence with traditional drug discovery methods to design nontoxic DYRK1A inhibitors. An ensemble QSAR model was used to predict binding affinities, while a directed message passing neural network evaluated toxicity. Novel compounds were generated using a hierarchical graph-based generative model and subsequently refined through molecular docking, chemical synthesis, and experimental validation. This pipeline led to the identification of pyrazolyl-1H-pyrrolo[2,3-b]pyridine 1 as a potent inhibitor, from which a new derivative series was developed. Enzymatic assays confirmed nanomolar DYRK1A inhibition, and additional assays demonstrated antioxidant and anti-inflammatory properties. Overall, the resulting compounds exhibit strong DYRK1A inhibition and favorable pharmacological profiles.

Spanish layman's summary:

Empleamos modelos predictivos y generativos de IA para la inhibición de  DYRK1A con múltiples compuestos. Guiamos el diseño de novo de nuevos fármacos con estos modelos, y los compuestos propuestos y sintetizados mostraron potencia en el rango nanomolar así como otros efectos deseables.

English layman's summary:

We employed predictive and generative AI models for DYRK1A inhibition with multiple compounds. These models guided the de novo drug design, and the proposed and synthesized compounds showed nanomolar potency as well as other desirable effects.

Keywords: AI-driven drug design, Molecular generative models, DYRK1A inhibition

JCR Impact Factor and WoS quartile: 6,800 - Q1 (2023)

DOI reference: https://doi.org/10.1021/acs.jmedchem.5c00512

In press: May 2025.

Citation:
E. González García, P. Varas, P. González-Naranjo, E. Ulzurrun, G. Marcos-Ayuso, C. Pérez, J.A. Páez, D. Ríos Insua, S. Rodríguez-Santana, N.E. Campillo, AI-Driven De Novo Design and Development of Nontoxic DYRK1A Inhibitors. Journal of Medicinal Chemistry.