AI in cancer genomics: educational modules in DC-area universities - artificial intelligence (AI) is transforming cancer research by enabling scalable integration and interpretation of…

The National Institutes of Health Office of the Director awarded George Washington University $166,000 on September 3, 2026, under the Trans-NIH Research Support program (CFDA 93.310) to develop and deliver an interdisciplinary graduate-level course on artificial intelligence applications in cancer genomics.

The course, jointly developed by George Washington University, Georgetown University, and the University of Maryland and offered through the DC-region cross-registration framework, will equip students with advanced competencies in applying AI and machine learning to bulk and single-cell cancer datasets. Instruction spans supervised and unsupervised learning, neural networks, multi-omics integration, dimensionality reduction, and explainable AI, with content anchored in key challenges in cancer biology. A multi-week mentored capstone project will enable students to generate interpretable, reproducible AI-driven analyses using published and institutional datasets, with structured support for peer-reviewed dissemination. The course emphasizes hands-on, case-based learning and ethical considerations in data use.

Performance occurs in Washington, DC 20052, with period of performance from award date through August 31, 2028. This Project Grant addresses a critical educational gap in graduate-level training that integrates AI methods with single-cell cancer genomics, which remains limited or absent across most academic institutions.

AI in cancer genomics: educational modules in DC-area universities - artificial intelligence (AI) is transforming cancer research by enabling scalable integration and interpretation of high-dimensional genomic data. When applied to single-cell datasets, AI provides deep insight into tumor heterogeneity, clonal dynamics, and therapeutic response - capabilities increasingly central to precision oncology. AI not only enables modeling of response trajectories at the cellular level but also allows dynamic tuning of predictive frameworks for individualized treatment strategies. Moreover, an increasing number of anticancer compounds are being identified and optimized through AI-driven discovery pipelines, underscoring AI's growing impact on both diagnostics and therapeutics. Yet, graduate- level training that integrates AI methods with single-cell cancer genomics remains limited or entirely absent across most academic institutions. This initiative addresses a critical educational GAP by developing, delivering, and disseminating an interdisciplinary graduate-level course titled AI in cancer genomics. Jointly developed by george washington university (GWU), georgetown university (GU), and the university of maryland (UMD), and offered through the DC-region cross-registration framework supported by partner institutions - the course will equip students with advanced competencies in applying AI and machine learning to real-world bulk and single-cell cancer datasets. Instruction will span supervised and unsupervised learning, neural networks, multi-omics integration, dimensionality reduction, and explainable AI, with content anchored in key challenges in cancer biology. A multi-week mentored capstone project will enable students to generate interpretable, reproducible AI- driven analyses using published and institutional datasets, with structured support for peer-reviewed dissemination. The course emphasizes hands-on, case-based learning, ethical considerations in data use, and the development of reproducible pipelines aligned with current research standards. The program is structured around three integrated aims: aim 1: to design and implement the modular, interdisciplinary course in collaboration with regional academic partners; aim 2: to rigorously evaluate educational effectiveness through a mixed-methods framework that includes pre/post assessments, project rubrics, reflective feedback, and longitudinal outcome tracking; and aim 3: to disseminate all instructional content, evaluation tools, and implementation resources nationally through open-access platforms, educator workshops, peer-reviewed publications, and indexing in national training directories. This initiative aligns cross-institutional expertise in AI, cancer genomics, and biomedical education to deliver a scalable and replicable national model for interdisciplinary training. IT supports NIH priorities in precision medicine, data science, and workforce development, preparing future scientists to lead at the intersection of computation and cancer biology.