Using artificial intelligence (AI), researchers at the Hadassah Medical Organization’s Cancer Research Institute have developed an algorithm to identify, with an unprecedented 96.5 percent level of accuracy, all possible harmful mutations of the TP53 gene. The information this breakthrough provides can potentially result in improved genetic screening and more customized treatment for cancer patients.
Prof. Thierry Soussi of the Sorbonne Université in Paris, a world-renowned researcher of the TP53 gene, lent his expertise to an international research collaboration, led by Dr. Shai Rosenberg, Hadassah senior neuro-oncologist and head of the Hebrew University’s laboratory for Computational Biology of Cancer. The goal of the research was to identify within a database of 2,314 variants of the TP53 gene all those that pose a risk of cancer.
Prof. Soussi’s and Prof. Rosenberg’s collaborative research has been supported in the past by Hadassah France, which is also financially contributing to this latest collaborative effort. As Dr. Rosenberg and colleagues explain in their article in Briefings in Bioinformatics, “Correctly identifying the true driver mutations in a patient’s tumor is a major challenge in precision oncology. Most efforts address frequent mutations, leaving medium- and low-frequency variants mostly unaddressed.” The researchers’ new “gene-specific machine learning model,” they note, can predict “the functional consequences of every possible missense mutation {mistake} in TP53.”
“Not only does the research and technology behind this breakthrough provide life-saving screening for carriers of previously unknown cancerous mutations who may be at increased risk, but they are also critical for genomic analysis of somatic mutation profiles in all tumors," reports Prof. Michal Lotem, head of Hadassah’s Center for Melanoma and Cancer Immunotherapy.
Prof. Aron Popovtzer, head of Hadassah’s Sharett Institute of Oncology, adds, “Hadassah has been at the forefront of promoting technological innovation in medicine to provide patients in our care with the most advanced treatment options. Following this important milestone, Dr. Rosenberg's research group will continue actively working to develop similar models for additional cancer genes.”