The .gov means it’s official.
Federal government websites often end in .gov or .mil. Before sharing sensitive information, make sure you’re on a federal government site.

The site is secure.
The https:// ensures that you are connecting to the official website and that any information you provide is encrypted and transmitted securely.

Center for Data-Driven Drug Development and Treatment Assessment (DATA)

Center Overview

The Center for Data-Driven Drug Development and Treatment Assessment (DATA) advances U.S. competitiveness by working with industry to solve challenges in drug discovery and repurposing and in treatment assessment, optimization, and quantitative pharmacovigilance. DATA uses novel computational and data science techniques such as metrology, machine learning (ML), and artificial intelligence (AI), and also trains the next generation of talent in this field. With new methodologies and infrastructure for industry-wide collaboration, DATA seeks to significantly accelerate drug development to help target the right drug to the right person at a safe and effective dose while reducing R&D costs.

DATA’s mission is to address two principal areas of unmet or underserved computational research needs within the (bio)pharmaceutical and healthcare sectors:

Challenges related to data, such as silos and skewed research results caused by small, non-diverse databases of patient and pharmaceutical data, or the lack of data standards across the pharmaceutical and healthcare industries.
AI and machine learning algorithmic challenges, including the lack of transparency of AI/ML models, lack of customization of the existing AI/ML methods to address the specific needs of the pharmaceutical and healthcare industries, and the inability of many AI/ML methods to learn from incomplete databases.

The advent of generative AI has created an urgent need for stakeholders in all stages of the drug life cycle to come together, share experiences with this revolutionary technology, and jointly address its implications for health care. Thanks to its cross-industrial and cross-disciplinary nature designed to bring together data scientists, mathematicians, biomedical researchers, pharmaceutical companies, healthcare providers and payers, as well as government agencies, DATA is ideally positioned to catalyze these conversations, identify best practices, and develop solutions to the challenges generative AI brings to the healthcare sector.

The Center also addresses the growing demand for data science professionals with expertise in drug design and treatment assessment through a robust education and training program focused on exposing the next generation of data science leaders to real-world needs and by connecting DATA industry partners with emerging talent in this field.

DATA's solutions are applicable at all stages of the drug discovery and treatment optimization pipeline, including during the initial screening for potential candidates, in the mechanistic and machine learning stage, during the testing of in-vitro/in-vivo disease models, in the assessment of clinical trials, through post-market pharmacovigilance and treatment monitoring. The Center will also have a broad impact on the society. For example, privacy-preserving and encryption techniques, while developed in the healthcare context, have a universal application and are readily transferable to other industries that handle sensitive identifiable information.

Universities

University of Michigan

View Center Website

Center Personnel

Kayvan Najarian
Center Director
+1 734 763 3924
kayvan@umich.edu

Chloe Winnie
Director of Operations
+1 734 763 3924
cmwinnie@umich.edu

Ivana Tullett
Compliance Coordinator

itullett@umich.edu

Research Focus

DATA's research program focuses on the following areas to advance the design, testing, validation and assessment of drugs and treatments:

Developing, testing, and validating novel data science and AI techniques, including generative AI, for drug development, treatment monitoring and patient phenotyping with respect to drugs and treatments.
Designing, testing, and validating data science and AI techniques for assessing drugs and treatments through systems for continuous health monitoring.
Sharing of unique laboratory resources for drug discovery and the development and validation of patient phenotypes.
Creating tools that enable federated machine learning for drug design, health informatics and pharmacovigilance over encrypted databases.
Providing an industry-wide and vendor-agnostic secure data hub of pharmaceutical and patient data with third-party private search capabilities for which data owners and providers of computational tools only need to share databases and algorithms in encrypted forms.
Developing and enhancing privacy-preserving and transparent machine learning for drug design, health informatics, pharmacovigilance and optimization of drug-based treatments over encrypted databases.

Awards

2209546

IUCRC Phase I University of Michigan Ann Arbor: Center for Data-Driven Drug Development and Treatment Assessment (DATA)

Drug development and assessment present major challenges, in particular: 1) In the early stages of drug discovery, it is costly and time-consuming to screen thousands of possible drugs. 2) When healthcare providers use the drug for treatment, it is highly important to assess their efficacy as well as potential adverse effects. Novel computational approaches, such as machine learning (ML) and artificial intelligence (AI), present solutions not only for drug design but also for personalized treatments. The Center for Data-Driven Drug Development and Treatment Assessment (DATA), through collaboration with its industry partners, intends to promote such computational solutions within precompetitive research.

In recent years AI and ML methods have impacted many aspects of society; DATA will develop and apply novel AI/ML methods for several aspects of drug design and assessment such as screening/detecting interactions between drugs and targets, and treatment customization considering preexisting conditions. DATA’s mathematical algorithms and methodologies can result in tools and solutions to address major obstacles throughout the lifecycle of drug design and treatment monitoring. The Center also develops large databases by integrating and curating new/existing public and proprietary healthcare/pharmaceutical datasets, allowing new resources for modeling, development, and assessment of new drugs.

DATA will develop programs to educate the next generation of data scientists, especially those from underrepresented groups. DATA will form new collaborations beyond academia to translate data science applications into impactful products/services, thereby reducing drug development costs while optimizing treatments and improving overall patient health. This in turn reduces the financial/societal burden on patients and providers alike. DATA will enable direct interactions between trainees and pharmaceutical/healthcare industry leaders, providing trainees with invaluable insight into real-world needs. DATA will address the urgent need for additional graduates with combined expertise in data science, drug design, and treatment assessment by directly training this future workforce.

The data integration, curation and storage processes are intended to continue beyond the scope and duration of the Phase I (and Phase II, if applicable). DATA intends to continue collecting, curating, integrating, and pre-processing databases shared by the current and future members of DATA as well as publicly available databases. A subset of these integrated databases, some of which will be encrypted through our Fully Homomorphic Encryption approach, can be shared with external entities under the guidelines set by the Center’s bylaws. Databases and software tools will be shared by the partners through a dedicated and secure website with documentation.

This award reflects NSF's statutory mission and has been deemed worthy of support through evaluation using the Foundation's intellectual merit and broader impacts review criteria. Read More >

Member Organizations

IUCRC affiliated member organizations are displayed as submitted by the Center. Non-federal organizations are not selected, approved, or otherwise endorsed by the U.S. National Science Foundation.

AbbVie
Amgen
CardioSounds
DataSpeaks
i2b2 tranSMART Foundation
miLEAD
PathwaysGI
Sanofi
tellic
Zero

The opinions, findings, and conclusions or recommendations expressed are those of the Center author(s) and do not necessarily reflect the views of the U.S. National Science Foundation.