An important new discovery has been made in the field of oncology research, thanks to a collaboration between researchers from the Sbarro Institute in Philadelphia, the National Cancer Institute-Pascal Foundation, and the University of Pisa. This study shows that the use of artificial intelligence (AI) can be a highly effective tool for designing new molecules with potential antitumor activity. Specifically, the researchers employed advanced AI algorithms to design and identify new molecules that can inhibit the enzymatic activity of the CDK9 protein.
The paper titled “Machine Learning-Based Virtual Screening for the Identification of Novel CDK-9 Inhibitors” was published in the journal biomolecule.
The CDK9 protein (cyclin-dependent kinase 9) is an enzyme involved in fundamental cellular processes, such as regulating gene transcription and cell proliferation. Discovered and characterized several years ago by Antonio Giordano, MD, founder and director of the Sbarro Health Research Organization (SHRO), CDK9 has gradually emerged as one of the most promising therapeutic targets in the fight against cancer, as its hyperactivation is often associated with uncontrolled tumor cell proliferation and the ability to withstand conventional treatments.
Within the framework of this study, the researchers exploited the potential of machine learning, a specific branch of artificial intelligence that allows computers to learn from data and identify complex patterns. Through this innovative approach, a large-scale virtual screen was performed with the aim of selecting new molecules that could potentially block the enzymatic activity of CDK9. Thanks to this advanced computational analysis, 14 candidate molecules were identified and subsequently subjected to experimental testing.
The selected molecules were evaluated in cell models of two clinically major tumor types: cervical cancer and breast cancer. The results showed that two of these compounds exhibited significant cytotoxic activity and were able to reduce the survival rate of tumor cells, demonstrating their promising therapeutic potential.
This scientific study proved to us that the use of artificial intelligence in research can be the basis for identifying new molecules used in the fight against cancer. In fact, AI can significantly reduce time and costs in the early stages of drug discovery, while increasing the likelihood of identifying truly effective compounds.
Professor Tiziano Tuccinardi, University of Pisa
“We have launched a new drug discovery project focused on the identification of new molecules of both natural and synthetic origin, designed by artificial intelligence,” said Dr. Luigi Alfano, a researcher at the Pascal Foundation National Cancer Institute. “This pathway has already produced very promising results and lays a solid foundation for the development of new potential anti-cancer drugs.”
“Artificial intelligence has proven to be one of the fundamental tools for basic and applied research thanks to its vast analytical and predictive capabilities,” said Professor Antonio Giordano, Director of the Sbarro Institute. “However, human experimental validation remains an important and irreplaceable step in the overall scientific process.”
Overall, this study shows how the integration of human expertise and advanced technology can open up new and promising prospects in the fight against cancer and accelerate the development of more targeted and effective treatments.
sauce:
Sbarro Health Research Organization
Reference magazines:
Piazza, L. others. (2025). Machine learning-based virtual screening to identify novel CDK-9 inhibitors. biomolecule. doi:10.3390/biom16010012. https://www.mdpi.com/2218-273X/16/1/12
