Transformative Artificial Intelligence and Machine Learning Based Strategies to Identify Determinants of Exceptional Health and Life Span (R21/R33 Clinical Trial Not Allowed) | RFA AG 23 033

Opportunity Information: Apply for RFA AG 23 033

This NIH grant opportunity, titled "Transformative Artificial Intelligence and Machine Learning Based Strategies to Identify Determinants of Exceptional Health and Life Span (R21/R33 Clinical Trial Not Allowed)" (Funding Opportunity Number RFA-AG-23-033; CFDA 93.866), supports research aimed at building and then applying next-generation AI and machine learning approaches to uncover the biology behind exceptionally healthy aging and unusually long life span. The core idea is to move beyond single-data-type analyses and instead use advanced computational methods to integrate and interpret large, complex, multi-omic datasets, including genomics, epigenomics, transcriptomics, proteomics, metabolomics, microbiomics, and phenomics. The FOA emphasizes extracting meaningful, mechanistic relationships across these layers (for example, linking DNA variation and epigenetic marks to gene expression patterns, protein networks, metabolite signatures, and measurable health outcomes) and connecting these molecular signatures to disease risk, resilience, and markers of exceptional longevity.

A central scientific focus is exceptional longevity (EL) in humans, particularly cohorts characterized by unusually healthy aging, as well as comparative datasets from multiple non-human species with widely different life spans. By leveraging both human and cross-species information, the program is looking for AI/ML strategies that can detect protective factors and conserved pathways that may explain why certain individuals or species remain healthier for longer. The expectation is that these methods will help identify molecular determinants that are not obvious using traditional statistical approaches, especially given the heterogeneity of aging, the complexity of multi-omic measurements, and differences across tissues, environments, and species.

The FOA uses the NIH Phased Innovation Award mechanism (R21/R33), which is structured to support a two-step progression from method development to rigorous application. In the R21 phase, teams are expected to design and develop innovative algorithms, intelligent automation tools, and novel AI/ML computational strategies specifically suited to integrating and interpreting heterogeneous multi-omic datasets in the context of longevity and health span. This phase is essentially the high-risk, high-reward engineering and conceptual development stage, where the goal is to create transformative computational capabilities rather than simply applying existing tools. In the R33 phase, the work shifts from building the tools to using them at scale on real-world, complex datasets from exceptional healthy aging human cohorts and relevant non-human species. The R33 application stage is intended to produce biological discovery, including identifying new protective molecular factors associated with exceptional longevity, and to support the development of translational strategies based on omics-derived therapeutic targets that could help prevent or delay age-related diseases.

A notable translational emphasis is the potential to impact major age-related conditions, explicitly including Alzheimer’s disease (AD) and Alzheimer’s disease-related dementias (ADRD). While the projects supported under this FOA are not allowed to include clinical trials, the expectation is that the computational discoveries will point toward actionable targets, pathways, or interventions that could be pursued later through preclinical and clinical development pipelines. In other words, the deliverable is not a trial, but rather validated computational tools and robust, biologically grounded insights that can guide therapeutic development and strategies to extend health span.

Because the scientific and technical scope crosses multiple domains, the FOA expects multi-disciplinary investigative teams. Competitive teams are anticipated to combine strong AI/ML expertise with deep domain knowledge in areas such as aging biology, comparative biology, and bioinformatics/cheminformatics, among others. The multidisciplinary requirement reflects the reality that integrating multi-omic and phenotypic data across humans and species demands both advanced machine learning innovation and careful biological interpretation to avoid spurious associations and to generate hypotheses that are testable and meaningful.

In terms of eligibility, the FOA is broadly open to many types of U.S.-based applicant organizations, including state, county, and local governments; special district governments; independent school districts; public and state-controlled institutions of higher education; private institutions of higher education; federally recognized Native American tribal governments; tribal organizations (including those other than federally recognized governments); public housing authorities/Indian housing authorities; nonprofit organizations with or without 501(c)(3) status; for-profit organizations (other than small businesses); and small businesses. The announcement also highlights inclusion of organizations such as Historically Black Colleges and Universities (HBCUs), Hispanic-serving institutions, Tribally Controlled Colleges and Universities (TCCUs), Alaska Native and Native Hawaiian Serving Institutions, and Asian American Native American Pacific Islander Serving Institutions (AANAPISIs), as well as faith-based or community-based organizations and U.S. territories or possessions. Foreign institutions (non-U.S. entities) are not eligible to apply as applicant organizations, but non-domestic components of U.S. organizations may participate, and foreign components are allowed as defined under NIH policy, meaning international collaboration can be part of a project when justified, even though the applicant institution must be eligible.

Administratively, this is a discretionary NIH grant program from the National Institutes of Health, with an original closing date listed as 2022-11-23 and an award ceiling indicated as $350,000. Overall, the opportunity is designed to push the field toward genuinely new AI/ML frameworks for multi-omic integration and interpretation, using exceptional longevity and comparative life span biology as the lens, with the longer-term goal of discovering protective mechanisms and actionable targets that could ultimately help delay or prevent age-related diseases and improve human health span.

• The National Institutes of Health in the health sector is offering a public funding opportunity titled "Transformative Artificial Intelligence and Machine Learning Based Strategies to Identify Determinants of Exceptional Health and Life Span (R21/R33 Clinical Trial Not Allowed)" and is now available to receive applicants.
• Interested and eligible applicants and submit their applications by referencing the CFDA number(s): 93.866.
• This funding opportunity was created on 2022-06-22.
• Applicants must submit their applications by 2022-11-23. (Agency may still review applications by suitable applicants for the remaining/unused allocated funding in 2026.)
• Each selected applicant is eligible to receive up to $350,000.00 in funding.
• Eligible applicants include: State governments, County governments, City or township governments, Special district governments, Independent school districts, Public and State controlled institutions of higher education, Native American tribal governments (Federally recognized), Public housing authorities/Indian housing authorities, Native American tribal organizations (other than Federally recognized tribal governments), Nonprofits having a 501 (c) (3) status with the IRS, other than institutions of higher education, Nonprofits that do not have a 501 (c) (3) status with the IRS, other than institutions of higher education, Private institutions of higher education, For-profit organizations other than small businesses, Small businesses, Others.

Apply for RFA AG 23 033

[Watch] Creating a grant proposal using the step-by-step wizard inside the applicant portal: