Development of Data Science Methods

National Institute Of Environmental Health Sciences

Investigators

Linked publications & trials

Abstract

Work under this program stems from activities conducted by the Office of Data Science (ODS), led by Dr. Schmitt. In 2024-2025, Dr. Schmitt and the ODS were primarily focused on ongoing operational and administrative duties, including overseeing and supporting the management of research data for the NIEHS Division of Translational Toxicology, serving as chair of the Environmental Health Language Collaborative (EHLC), co-leading the development of a NIEHS strategic plan for advancing the environmental health data ecosystem, overseeing ODS support to the NIEHS Division of Intramural Research (DIR), serving as NIEHS representatives to NIH data science related efforts and working groups, serving as a executive committee member for the NIEHS Personalized Environment and Genes Study (PEGS), and supporting a projects funded by the Patient Centered Outcomes Research (PCOR) Trust Fund and the NIH Health and Extreme Weather program to develop digital resources to support health researcher in conducting research on the impacts of external exposures on health. As such, research was limited to the following activities: 1) Dr. Schmitt and collaborators are researching methods to adopt AI, in particular large language models, to improve the discoverability and integration of environmental health data and knowledge. This work is part of a project termed Navigator which is building a platform to search for environmental health data and knowledge and a related project called ToxPipe which is using large language models to aid in interpreting toxicology data and mining toxicology knowledge.