U-M receives NSF grant for data-driven drug discovery


The University of Michigan will launch a new center to significantly accelerate drug development and assessment of the various outcomes associated with these treatments, while also reducing national health care expenditures.

The Center for Data-Driven Drug Development and Treatment Assessment — to be known as DATA — will support the use of machine learning and artificial intelligence techniques to research drug design, treatment assessment, repositioning, patient phenotyping and quantitative pharmacovigilance.

It will be supported through a five-year, $749,000 grant from the National Science Foundation that requires a minimum of $750,000 in matching membership fees from industry partners over the same period. The center will be a central hub for collaborative research that seeks to fulfill an important national need for improved drug repositioning and repurposing, health monitoring and post-market surveillance.

DATA will be led by Kayvan Najarian, professor of computational medicine and bioinformatics, and of emergency medicine in the Medical School, and professor of electrical engineering and computer science in the College of Engineering. It will be overseen by the Michigan Institute for Data Science, a unit based within the Office of the Vice President for Research.

“It was evident, after conversations with health care systems and pharmaceutical partners, that they would put high priority on the use of data-driven AI methods for drug assessment,” said H.V. Jagadish, director of MIDAS and the Bernard A. Galler Collegiate Professor of Electrical Engineering and Computer Science.

“In response, we will position DATA to support and empower our industry partners, with an emphasis on the development of tools and techniques focused on drug assessment while analyzing the data collected by health care systems when drugs and other interventions are used for treatment in clinical settings.”

Currently, pharmaceutical data silos stymie comprehensive pharmacovigilance efforts. Pharmacovigilance refers to the science and activities relating to the detection, assessment, understanding and prevention of adverse effects or any other medicine or vaccine related problem.  All medicines and vaccines undergo rigorous testing for safety and efficacy through clinical trials before they are authorized for use.

DATA aims to alleviate those concerns by employing an AI-driven computational approach to treatment monitoring that uses novel techniques to identify patient phenotypes related to adverse events, drug-targeted interactions and treatment outcomes in integrated public and proprietary datasets, ultimately improving the state of patient care nationally.

“While the value and potential of using AI and machine learning have been long recognized, we have few such techniques for teasing out the complexities for screening drugs to target and drug-to-drug inactions, pre-existing conditions, and unique patient phenotypes that result in disparate treatment effects and outcomes,” Najarian said.

“DATA will bring together data scientists, mathematicians, biomedical researchers and health care providers to produce methodologies that can be replicated to make a broad impact on drug discovery and biomedical applications of data science and AI.”

Industry partners in DATA are from diverse fields and sectors, including pharmaceuticals, health care systems, biotechs, information technology companies, medical monitoring device companies and software companies active in the field of biomedical informatics.

The center will focus on five research areas and capabilities, but will readily extend to meet the needs of participating industry partners. Those areas are:

  • Development, testing and validation of algebraic, machine learning and AI techniques for drug development, health monitoring and patient phenotyping with respect to drug treatments.
  • Design and development of advanced AI methods for treatment assessment by designing and implementing monitoring systems and algorithms that can continuously monitor the health of individuals receiving different types of drugs and treatments.
  • Provide an industrywide and vendor-agnostic secure data hub with third-party private search capabilities for the development, testing, validation and assessment of drugs and treatments.
  • Enable privacy-preserving machine learning for drug design, health informatic and pharmacovigilance, and optimization of drug-based treatment over encrypted databases.
  • Provide unique laboratory resources for development and validation of patient phenotypes and new drug discovery.

DATA will work with partners from industry, state and professional organizations whose research efforts align with the center’s focus and who will be active collaborators in shaping the future paradigm of integrated and cost-effective patient care.


Leave a comment

Commenting is closed for this article. Please read our comment guidelines for more information.