Life Sciences Building, Room 206
501 S. Nedderman Drive
Box 19047
Arlington, TX 76019
UTA project aims to improve access to environmental health research
Shen receives $605K NIH grant to create knowledgebase of children's cohort studies

Yike Shen, UTA assistant professor of Earth and environmental sciences (photo courtesy of Yike Shen)
A new federally funded project at The University of Texas at Arlington will build an environmental health knowledge base designed to help researchers more easily find, organize and use knowledge from previously published children’s cohort studies.Yike Shen, assistant professor of Earth and environmental sciences, received a three-year, $605,000 grant from the National Institutes of Health (NIH) National Institute of Environmental Health Sciences (NIEHS) for the project, titled “CONNECT: Cohort-Oriented Network kNowledgebase for Enhanced CollaboraTion.”
The project will focus on cohort studies, which are observational studies that follow a group of individuals sharing some characteristics and are followed up over time. Cohort studies are important in environmental health sciences because they can improve our understanding of how chemical exposures, lifestyle factors, and genetics contribute to human health.
“Summarizing and managing the findings and knowledge from cohort studies are indispensable components of cohort development, yet these tasks have often been overlooked,” Shen said. “It will inevitably result in a significant loss if the knowledge and findings from cohort studies are not easily available or accessible to the entire environmental health community and public.”
The goal of Shen’s project is to create a knowledgebase of existing cohort studies on children’s health and align it with the direction of future environmental health development cohort studies so that researchers can share information and use the insights to inform their own studies.
The project has three principal aims:
- Develop an AI-assisted knowledge extraction pipeline with prompt engineering for harmonizing environmental health knowledge from published cohort studies;
- Develop the CONNECT knowledgebase for children’s environmental health;
- Develop a CONNECT knowledgebase webtool and showcase its utility for users.
The first step will be to use artificial intelligence to assist in the creation of a pipeline for knowledge extraction, validation, and harmonization from more than a dozen NIEHS-funded children’s cohort studies, Shen said. Next, knowledge extracted from the pipeline will be used to construct the CONNECT knowledge base, which will consist of key findings from each cohort study. This will result in an overall knowledge graph with standardized environmental health language, Shen said. A webtool will be developed to share knowledge with the environmental health community.
Shen added that the CONNECT knowledge base will feature various applications, including exposure-outcome evidence mapping, mechanistic insights and hypothesis generation, and statistical querying for meta-analysis, among others. It will also provide a unique opportunity to train undergraduate students to become biomedical scientists in both data science and environmental health.
“We are entering a new era of AI, where knowledgebases and databases are becoming increasingly important for environmental health research,” Shen said. “Our CONNECT knowledgebase will serve as an important resource for environmental health researchers and cohort communities by making published cohort knowledge easier to access, standardize and use.”
The project is a collaboration among principal investigator Shen; co-investigators Feng Gao from UCLA, Jeanette Stingone from Columbia University, Xinlei Wang from UTA, and Jacob Luber from St. Jude Children’s Research Hospital; and consultant Andrea Baccarelli from Harvard University.
--
The UTA College of Science, a Carnegie R1 research institution, is preparing the next generation of leaders in science through innovative education and hands-on research and offers programs in Biology, Chemistry & Biochemistry, Data Science, Earth & Environmental Sciences, Health Professions, Mathematics, Physics and Psychology. To support educational and research efforts visit the giving page, or if you're a prospective student interested in beginning your #MaverickScience journey visit our future students page.