A new and important discovery comes from the field of oncological research thanks to the joint work of researchers from the Sbarro Institute in Philadelphia, the National Cancer Institute—Pascale Foundation, and the University of Pisa.
The study has shown how the use of artificial intelligence (AI) can represent an extremely effective tool for the design of new molecules with potential antitumor activity. In particular, the researchers employed sophisticated AI algorithms for the design and identification of new molecules capable of inhibiting the enzymatic activity of the CDK9 protein.
The paper titled, “Machine Learning-Based Virtual Screening for the Identification of Novel CDK-9 Inhibitors,” is published in the journal Biomolecules.
Understanding CDK9 and its role in cancer
The CDK9 protein (Cyclin-Dependent Kinase 9) is an enzyme involved in fundamental cellular processes, such as the regulation of gene transcription and cell proliferation. Discovered and characterized several years ago by Prof. Antonio Giordano, M.D., Ph.D., Founder and Director of the Sbarro Health Research Organization (SHRO), CDK9 has progressively emerged as one of the most promising therapeutic targets in the fight against cancer, as its hyperactivation is often associated with uncontrolled tumor cell growth and their ability to survive conventional treatments.
Within the framework of this study, the researchers harnessed the potential of machine learning, a specific branch of artificial intelligence that allows computers to learn from data and identify complex patterns.
AI-driven discovery and experimental results
Through this innovative approach, a large-scale virtual screening was carried out with the aim of selecting new molecules potentially capable of blocking 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 cellular models of cervical carcinoma and breast cancer, two tumor types of major clinical relevance. The results showed that two of these compounds were able to exert significant cytotoxic activity and reduce the viability of tumor cells, thus demonstrating promising therapeutic potential.
Expert perspectives and future directions
“This scientific work has confirmed for us how the use of artificial intelligence in research can be fundamental for the identification of new molecules to be used in the fight against cancer,” says Prof. Tiziano Tuccinardi of the University of Pisa.
“AI, in fact, makes it possible to drastically reduce the time and costs of the initial drug discovery phase, while at the same time increasing the likelihood of identifying truly effective compounds.
“We have launched a new Drug Discovery project focused on the identification of new molecules, both of natural and synthetic origin, designed through artificial intelligence,” says Dr. Luigi Alfano, a researcher at the National Cancer Institute of the Pascale Foundation.
“This pathway is already producing very encouraging results and lays solid foundations for the development of new potential anticancer drugs.”
“Artificial intelligence is proving to be one of the fundamental tools for basic and applied research, thanks to its enormous analytical and predictive capabilities,” says Prof. Antonio Giordano, Director of the Sbarro Institute. “However, experimental validation by humans remains a crucial and irreplaceable phase of the entire scientific process.”
Overall, this study demonstrates how the integration of human expertise and advanced technologies can open up new and promising perspectives in the fight against cancer, accelerating the development of increasingly targeted and effective therapies.
More information
Lisa Piazza et al, Machine Learning-Based Virtual Screening for the Identification of Novel CDK-9 Inhibitors, Biomolecules (2025). DOI: 10.3390/biom16010012
Clinical categories
Provided by
Sbarro Health Research Organization (SHRO)
The content is provided for information purposes only.