These wide-ranging research projects will use AI and machine learning tools to understand and reduce the threat posed by the SARS-CoV-2 virus in a variety of ways, from tracking the transmission dynamics of the virus in Mexico to speeding the discovery of small molecules that could one day serve as pharmaceutical treatments for the disease.
The C3.ai Digital Transformation Institute, a research consortium established in March by enterprise AI software company C3.ai and headquartered at Berkeley and the University of Illinois at Urbana-Champaign, aims to mobilize AI, machine learning and the Internet of Things to transform societal-scale systems.
The six Berkeley-led projects are among 26 projects awarded a total of $5.4 million by the institute to accelerate AI research for COVID-19 mitigation through advances in medicine, urban planning and public policy.
Stefano Bertozzi, dean emeritus and professor of health policy and management, will lead a project using data from the Mexican Social Security Institute to determine possible clinical, individual, facility and structural determinants of exposure and susceptibility to SARS-CoV-2, in hopes of better guiding prevention efforts and finding mechanisms that might improve COVID-19 patient outcomes.
A project led by Alberto Sangiovanni-Vincentelli, a professor of electrical engineering and computer sciences, will develop algorithms for AI that will help health care institutions better detect and contain emerging diseases like COVID-19.
Gerbrand Ceder, Chancellor’s Professor in the Department of Materials Science and Engineering, will head a project harnessing natural language processing techniques to scan and synthesize information in tens of thousands of emergent research articles, patents and clinical trials on COVID-19 to facilitate the formulation of actionable insights and new knowledge.
Karen Chapple, professor and chair of city and regional planning, will lead an interdisciplinary project to track housing evictions during and after the outbreak in an effort to better understand housing precarity and to inform public policy regarding U.S. housing inequality.
Teresa Head-Gordon, Chancellor’s Professor of chemistry, bioengineering and chemical and biomolecular engineering, will use machine learning techniques inspired by physics to speed the discovery of small molecules that could bind and disable the SARS-CoV-2 virus, leading to future drugs to treat the disease.
A project headed by Jennifer Listgarten, professor of electrical engineering and computer sciences, will draw upon techniques such as reinforcement learning, robust uncertainty estimation and probabilistic modeling to develop new and trustworthy methods for therapeutic drug discovery for COVID-19.