Regina Barzilay is the AI faculty lead of the Abdul Latif Jameel Clinic for Machine Learning in Health (Jameel Clinic), the epicentre of artificial intelligence (AI) and healthcare at the Massachusetts Institute of Technology (MIT). She is also a School of Engineering Distinguished Professor for AI and health in the department of electrical engineering and computer science and a member of the Computer Science and Artificial Intelligence Laboratory.
Regina’s research interest focuses on machine learning models for molecular modelling with applications to drug discovery and clinical AI. She also concentrates on natural language processing and oncology, developing algorithms that can learn from cancer patient data to improve models of disease progression, treatment and potential cures.
Regina’s work has received various awards, including the UNESCO/Netexplo award (2021), AACC Wallace H. Coulter Lectureship Award (2021), a Top 100 AI Leaders in Drug Discovery & Advanced Healthcare Award (2019), Xconomy Boston Digital Trailblazer Award (2019), the NSF Career Award (2005) and several best paper awards at NAACL and ACL. In 2017, Regina received a MacArthur "genius grant" Award, an ACL fellowship and an Association for the Advancement of Artificial Intelligence (AAAI) fellowship. In 2020, she was awarded a $1 million prize by AAAI's Squirrel AI Award for Artificial Intelligence for the Benefit of Humanity in recognition for her work applying AI to drug discovery and breast cancer detection, using an AI model, Mirai.
Also in 2020, alongside co-principal investigator Jim Collins and other colleagues at MIT Jameel Clinic, Regina published research identifying a powerful new antibiotic compound, Halicin, using a machine-learning algorithm. The drug killed many of the world’s most problematic disease-causing bacteria in laboratory tests, including some strains that are resistant to all known antibiotics. It also cleared infections in two different mouse models. Following on from the antibiotic-AI project, Regina and team received seven-year funding from the Audacious Project, a collaborative funding initiative with a goal of supporting solutions to global challenge.
In 2023, Regina and fellow researchers at MIT Jameel Clinic developed an AI model that can detect future lung cancer risk up to six years' in advance. Called Sybil, the name was inspired by feminine figures in ancient Greek mythology who read oracles of the past, present and future. The technology provides a personalised approach to assessing each patient’s risk of lung cancer based on CT scans, without the need for a radiologist.
In the same year, Regina was elected to the National Academy of Engineering, one of the highest professional distinctions for engineers, for her development of machine learning models that understand structures in text, molecules and medical images. Later in the year, with her team at MIT, she developed DiffDock, a molecular docking model that has the potential to discover new drugs faster than traditional methods and reduce the risk of adverse side effects.