Comillas participates in the development of a molecule to treat Alzheimer's and cancer

Simón Rodríguez, researcher and lecturer in Telematics and Computation at Comillas ICAI, has collaborated in the development of an innovative computational strategy that makes it possible to design therapeutic molecules from scratch, even with limited experimental data. Specifically, together with researchers from the CSIC, he has designed a molecule that could be used in future therapies against Alzheimer's and certain types of cancer.

The technique, published in the Journal of Medicinal Chemistry, is based on a hierarchical generative model, built on molecular representations in the form of graphs. "This model integrates different approaches to use flexible and larger structural motifs as the basic units of molecule generation," Rodriguez explains.

These motifs are recurring patterns in the three-dimensional structure of molecules, which allow them to fulfil essential biological functions. "Thus, we can generate thousands of new molecules, even from limited experimental data sets, making more robust and reliable predictions," adds the Comillas ICAI researcher.

According to the researchers, the work focuses on the DYRK1A protein, whose overexpression is implicated in diseases such as Down's syndrome, Alzheimer's and certain types of cancer. "Recent studies suggest that inhibiting this protein may help prevent or slow down pathological processes such as the accumulation of hyperphosphorylated tau proteins, which are associated with neurodegeneration," they say in a statement.

This inhibition has been achieved thanks to the development of a new family of compounds (pyrazolyl-1H-pyrrolo[2,3-b]pyridine) through generative artificial intelligence and predictive modelling, combined with traditional techniques such as molecular docking and density functional theory (DFT) calculations. In addition, these elements have antioxidant and anti-inflammatory properties, and good brain permeability, which is essential to cross the blood-brain barrier and be able to function therapeutically.

According to Simón Rodríguez, "the protocol developed is adaptable to other therapeutic targets, which opens up the possibility of applying it in the search for treatments for various diseases". This work shows how the integration of artificial intelligence with traditional methods can revolutionise drug design, offering new ways to treat complex diseases.