Researchers from the Sbarro Institute in Philadelphia, the National Cancer Institute – Pascale Foundation, and the University of Pisa have used artificial intelligence (AI) to design new molecules that may help treat cancer. Their study, published in Biomolecules under the title "Machine Learning-Based Virtual Screening for the Identification of Novel CDK-9 Inhibitors," focuses on using AI algorithms to find compounds that inhibit the CDK9 protein.
CDK9, or Cyclin-Dependent Kinase 9, is an enzyme involved in gene transcription and cell proliferation. It was discovered and characterized by Prof. Antonio Giordano, M.D., Ph.D., who is also Director of the Sbarro Health Research Organization (SHRO). The protein has become a key target in cancer research because its overactivity is linked to tumor growth and resistance to treatment.
The researchers applied machine learning techniques to conduct a virtual screening of potential inhibitors. This process led to the identification of 14 candidate molecules. These were then tested in laboratory models for cervical carcinoma and breast cancer. Two compounds showed significant cytotoxic effects, reducing tumor cell viability.
Dr. Luigi Alfano from the National Cancer Institute of the Pascale Foundation commented: "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. This pathway is already producing very encouraging results and lays solid foundations for the development of new potential anticancer drugs."
Prof. Antonio Giordano added: "Artificial intelligence is proving to be one of the fundamental tools for basic and applied research, thanks to its enormous analytical and predictive capabilities. However, experimental validation by humans remains a crucial and irreplaceable phase of the entire scientific process."
The study highlights how combining human expertise with advanced technology can accelerate progress toward more targeted cancer therapies.
