DOC Computational Biology & Data Science Program
Overview
The Dental, Oral, and Craniofacial (DOC) Computational Biology and Data Science Program promotes data-driven research in DOC biology, disorders, and health disparities to inform and develop prevention strategies, diagnostics, and therapies of DOC disorders for all individuals. Program priorities include Big Data and multimodal data sharing and integration into data ecosystems, as well as development and application of data science tools—including computational methods, machine learning, deep learning, and large language models (LLMs)—in all foundational, translational, and clinical areas of NIDCR’s strategic interests. Relevant research topics include, but are not limited to:
- Computational, mathematical and predictive modeling and methods development, including machine learning and deep neural networks, for classification, prognosis, diagnosis, treatment planning, and assessment of treatment outcomes for dental care and DOC conditions
- Maximizing the reuse of research, health, and clinical data by making existing and new data FAIR and model-ready, and enabling data-driven research in DOC biology, health, and health disparities by developing Common Data Elements, ontologies, natural language processing, LLMs and other data analytics
- Development of robust analytics to accommodate integration of multiple data types (e.g., RNA-Seq-based diagnostics and pathology information; imaging, electronic medical and dental records) and large data volume, to serve research and clinical applications
- Bioethics research in privacy, confidentiality, and bias issues related to the collection, analysis, and dissemination of research and clinical data, as well as reuse of data for different research questions, particularly with regard to facial images, genetic variants, multi-omics, other deep phenotyping data, and associated metadata collected during prenatal, postnatal, and through adulthood