Development of Data Science Methods

National Institute Of Environmental Health Sciences

Investigators

Linked publications, trials & patents

Abstract

Work under this program stems from activities conducted by the Office of Data Science (ODS), led by Dr. Schmitt. In 2021-2022, ODS was focused on ongoing operational and administrative duties, as well as leading the launch of a new program called the Environmental Health Language Collaborative (EHLC) and the development of a NIEHS strategic plan for advancing the environmental health data ecosystem. As such, research was limited to the following activities: 1) The NIEHS, under Dr. Schmitt and Mrs Holmgren, has launched the Environmental Health Language Collaborative (EHLC) in 2021 Holmgren2021. EHLC is a new program intended to provide an ongoing NIEHS commitment to advance the development and use of a common language for describing EH data and knowledge, in order to: facilitate finding data and knowledge products; integrating data for pooled analysis, reuse, and meta-analysis; building scientific tools; and integrating knowledge into knowledge organization systems (e.g., ontologies, knowledge graphs) that can support hypothesis discovery and mining. As part of the EHLC effort, Dr. Schmitt has been advising on the development of knowledge graphs, in particular the NCATS Data Translator, to advance the adoption of environmental health concepts into larger scale biomedical knowledge graphs Fecho2021, Fecho2022. 2) A significant challenge in environmental health research is extracting and aggregating known information about exposures that are recorded within research journals in free text, figures, and images. Dr. Schmitt collaborated with the DNTP and Oak Ridge National Labs to advance the development of methods to extract information from unstructured text and tables using natural language processing (NLP) and image analysis techniques. This past year has advanced methods to incorporate the use of weak supervision approaches to support development of NLP models Herrmannova2021. 3) This past year Dr. Schmitt continued to serve as a member of the NIEHS Personalized Environment and Genes Study executive management committee, helping to oversee research directions and activities primarily led by Dr. Allison Motsinger-Reif and Dr. Jan Hall. This effort has advanced new research into genetics by environment interactions Lee2021, Lowe2022.