Advanced Training in Artificial Intelligence for Precision Nutrition Science Research (AIPrN) Institutional Research Training Programs (T32) is sponsored by National Institutes of Health (NIH) Office of Nutrition Research (ONR). This program supports new institutional research training programs (predoctoral, postdoctoral, or both) in AI for precision nutrition (AIPrN).

Expired RFA-OD-22-027: Advanced Training in Artificial Intelligence for Precision Nutrition Science Research (AIPrN) Institutional Research Training Programs (T32) This notice has expired. Check the NIH Guide for active opportunities and notices. Department of Health and Human Services Part 1.

Overview Information Participating Organization(s) National Institutes of Health ( NIH ) Components of Participating Organizations Office of Nutrition Research ( ONR ) National Heart, Lung, and Blood Institute ( NHLBI ) Eunice Kennedy Shriver National Institute of Child Health and Human Development ( NICHD ) National Institute of Dental and Craniofacial Research ( NIDCR ) National Institute of Diabetes and Digestive and Kidney Diseases ( NIDDK ) National Institute of Neurological Disorders and National Institute of Nursing Research ( NINR ) National Institute on Minority Health and Health Disparities ( NIMHD ) National Center for Complementary and Integrative Health ( NCCIH ) National Cancer Institute ( NCI ) All applications to this funding opportunity announcement should fall within the mission of the Institutes/Centers.

The following NIH Offices may co-fund applications assigned to those Institutes/Centers. Office of Research on Women's Health ( ORWH ) Special Note : Not all NIH Institutes and Centers participate in every (or all) funding opportunity announcements. .

Applicants should carefully note which ICs participate in this announcement and view their respective areas of research interest and requirements at the Table of IC-Specific Information, Requirements and Staff Contacts website. ICs that do not participate in this announcement will not consider applications for funding. Consultation with NIH staff before submitting an application is strongly encouraged.

Funding Opportunity Title Advanced Training in Artificial Intelligence for Precision Nutrition Science Research (AIPrN) Institutional Research Training Programs (T32) T32 Institutional National Research Service Award (NRSA) NOT-OD-23-012 Reminder: FORMS-H Grant Application Forms and Instructions Must be Used for Due Dates On or After January 25, 2023 - New Grant Application Instructions Now Available NOT-OD-23-020 - Notice of Change: Advanced Training in Artificial Intelligence for Precision Nutrition Science Research (AIPrN) Institutional Research Training Programs (T32) NOT-OD-22-190 - Adjustments to NIH and AHRQ Grant Application Due Dates Between September 22 and September 30, 2022 Funding Opportunity Announcement (FOA) Number Companion Funding Opportunity See Section III.

3. Additional Information on Eligibility. Assistance Listing Number(s) 93.

213, 93. 313, 93. 853, 93.

865, 93. 847, 93. 837, 93.

838, 93. 839, 93. 840, 93.

233, 93. 361, 93. 866, 93.

307, 93. 398, 93. 121 Funding Opportunity Purpose This Funding Opportunity Announcement (FOA) invites applications for new institutional training programs (predoctoral, postdoctoral or both) in Artificial Intelligence (AI) for Precision Nutrition (AIPrN) focused on the integration of precision nutrition, AI, machine learning (ML), systems biology, systems science, Big Data, and computational analytics.

The goal is to build a future workforce that will be able to use growing data resources to tackle complex biomedical challenges in nutrition science that are beyond human intuition. It is expected that such research will lead to the development of innovative solutions to combat diet-related chronic diseases and nutrition disparities within the mission areas of the participating NIH Institutes and Offices.

The vision for the AIPrN training program is to support the development of a diverse research workforce with advanced competencies in AI, ML, and data science analytics to apply to an increasingly complex landscape of Big Data including molecular, organismal, community and societal-levels related to nutrition and diet-related conditions.

This Funding Opportunity Announcement (FOA) does not allow appointed Trainees to lead an independent clinical trial, but does allow them to obtain research experience in a clinical trial led by a mentor or co-mentor. Open Date (Earliest Submission Date) Letter of Intent Due Date(s) Renewal / Resubmission / Revision (as allowed) All applications are due by 5:00 PM local time of applicant organization.

Applicants are encouraged to apply early to allow adequate time to make any corrections to errors found in the application during the submission process by the due date. Required Application Instructions It is critical that applicants follow the Training (T) Instructions in the SF424 (R&R) Application Guide , except where instructed to do otherwise (in this FOA or in a Notice from the NIH Guide for Grants and Contracts ).

Conformance to all requirements (both in the Application Guide and the FOA) is required and strictly enforced. Applicants must read and follow all application instructions in the Application Guide as well as any program-specific instructions noted in Section IV. When the program-specific instructions deviate from those in the Application Guide, follow the program-specific instructions.

Applications that do not comply with these instructions may be delayed or not accepted for review. Part 1. Overview Information Part 2.

Full Text of Announcement Section I. Funding Opportunity Description Section II. Award Information Section III.

Eligibility Information Section IV. Application and Submission Information Section V. Application Review Information Section VI.

Award Administration Information Section VII. Agency Contacts Section VIII. Other Information Part 2.

Full Text of Announcement Section I. Funding Opportunity Description The overall goal of the NIH Ruth L. Kirschstein National Research Service Award (NRSA) program is to help ensure that a diverse pool of highly trained scientists is available in appropriate scientific disciplines to address the Nation's biomedical, behavioral, and clinical research needs.

In order to accomplish this goal, NRSA training programs are designed to train individuals to conduct research and to prepare for research careers. More information about NRSA programs may be found at the Ruth L. Kirschstein National Research Service Award (NRSA) website.

Purpose and Background Information The NRSA program has been the primary means of supporting predoctoral and postdoctoral research training programs since enactment of the NRSA legislation in 1974. Research training activities can be in basic biomedical or clinical sciences, in behavioral or social sciences, in health services research, or in any other discipline relevant to the NIH mission.

Institutional NRSA programs allow the Training Program Director/Principal Investigator (Training PD/PI) to select the trainees and develop a program of coursework, research experiences, and technical and/or professional skills development appropriate for the selected trainees. Each program should provide high-quality research training and offer opportunities in addition to conducting mentored research.

The grant offsets the cost of stipends, tuition and fees, and training related expenses, including health insurance, for the appointed trainees in accordance with agency-approved support levels. The objective of the Ruth L.

Kirschstein National Research Service Award (NRSA) Institutional Research Training Grant (T32) program is to develop and/or enhance research training opportunities for individuals interested in careers in biomedical, behavioral and clinical research that are relevant to the NIH mission.

The training program should provide: A strong foundation in research design, methods, and analytic techniques appropriate for the proposed research area; The enhancement of the trainees ability to conceptualize and think through research problems with increasing independence; Experience conducting research using state-of-the-art methods as well as presenting and publishing their research findings; The opportunity to interact with members of the scientific community at appropriate scientific meetings and workshops; and The enhancement of the trainees understanding of the health-related sciences and the relationship of their research training to health and disease.

The proposed institutional research training program may complement other ongoing research training and career development programs at the applicant institution, but must be clearly distinct from related programs currently receiving Federal support.

The duration of training, the transition of trainees to individual support mechanisms, and their transition to the next career stage are important considerations in institutional training programs.

Training PDs/PIs should limit appointments to individuals who are committed to a research career and who plan to remain in training for no less than two years, whether that support comes from a training grant or some combination of NRSA and non-NRSA support programs.

Training PDs/PIs should encourage and make available appropriate skills training so that trainees are prepared to apply for subsequent independent support for their training or research program (e.g., an individual fellowship award, mentored career development award, or research project grant), as appropriate for their career stage.

In addition, past studies have shown that health professional trainees who train in programs with postdoctoral researchers who have intensive research backgrounds are more likely to apply for and receive subsequent research grant support.

Programs that emphasize research training for individuals with the MD or other health-professional degrees are therefore encouraged to develop ties to basic science departments and include trainees with research doctorates when this approach is consistent with the goals of the proposed training program. Biomedical research and the resulting scientific knowledge are increasingly complex and multidisciplinary in nature.

Training PDs/PIs are encouraged to develop institutional training programs that will expose trainees to a variety of scientific approaches, systems for study, research approaches, and tools and technologies. Consideration of team-based research approaches may also be warranted depending upon the goals of the proposed training program.

Within the framework of the NRSA program’s longstanding commitment to excellence and the projected need for investigators in particular areas of research, attention must be given to recruiting prospective trainees from racial or ethnic groups underrepresented in the biomedical, behavioral and clinical sciences, individuals with disabilities, and individuals from disadvantaged backgrounds.

See the Training (T) Instructions in the SF424 (R&R) Application Guide for further background and instructions. The career outcomes of individuals supported by NRSA training programs include both research-intensive careers in academia and industry and research-related careers in various sectors, e.g., academic institutions, government agencies, for-profit businesses, and private foundations.

Training programs should make available structured, career development advising and learning opportunities (e.g., workshops, discussions, Individual Development Plans).

Through such opportunities, trainees are expected to obtain a working knowledge of various potential career directions that make strong use of the knowledge and skills gained during research training and the steps required to transition successfully to the next stage of their chosen career. Institutional research training grants must be used to support a program of full-time research training.

Within the full-time training period, research trainees who are also training as clinicians must devote their time to the proposed research training and must confine clinical duties to those that are an integral part of the research training experience.

The program may not be used to support studies leading to the MD, DDS, or other clinical, health-professional training except when those studies are part of a formal combined research degree program, such as the MD/PhD. Similarly, trainees may not accept NRSA support for clinical training that is part of residency training leading to clinical certification in a medical or dental specialty or subspecialty.

It is permissible and encouraged, however, for clinicians to engage in NRSA-supported, full-time postdoctoral research training even when that experience is creditable toward certification by a clinical specialty or subspecialty board. Short-term training is not intended, and may not be used, to support activities that would ordinarily be part of a research degree program, nor for any undergraduate-level training.

Short-term positions should be requested at the time of application as described in the NIH Grants Policy Statement . Research training programs solely for short-term research training should not apply to this announcement, but rather the T35 NRSA FOA, which can be found in the NIH Training Kiosk .

This Funding Opportunity Announcement (FOA) does not allow appointed Trainees to lead an independent clinical trial, but does allow them to obtain research experience in a clinical trial led by a mentor or co-mentor. NIH strongly supports training towards a career in clinically relevant research and so gaining experience in clinical trials under the guidance of a mentor or co-mentor is encouraged.

To be deemed responsive to this FOA, applications must propose programs designed for the training of predoctoral students, postdoctoral fellows, or both. The training program is intended to create new intradepartmental/intercollege programs or augment the core methods courses in potentially two types of Ph. D.

or postdoctoral training programs: Mathematics, data science, AI, ML, computer science or computer engineering. In this situation, for applications to be deemed responsive to this FOA, the applicants must describe plans and curricula that will offer new courses including practical and hands-on experience in biomedical/nutrition sciences relevant to diet-related chronic diseases across the translational spectrum and scales.

For either situation, next generation AIPrN scientists should be trained to curate, link, and mine large complex datasets.

Inferential statistics developed for small sample surveys are inappropriate for analyzing populations with billions of records, which is why these trainees will require training in innovative computational and mathematical modeling approaches, techniques for data mining and harmonization, and methods for addressing data heterogeneity.

The foundational training for these AIPrN programs should include all of the following: Coursework and training experiences in academia or industry using a multidisciplinary approach; Collaborative research opportunities; Mentorship in advanced computational methods; and Training that promotes reproducibility of results and scientific rigor This program is not intended to support training or research in nutrition epidemiology or research that examines questions in food science or agricultural sciences.

It is expected that trainees will acquire (or possess from previous experience) core knowledge in two overarching areas: (1) systems biology or systems science research in a chosen area of nutrition science or a biomedical health domain relevant to the mission of at least one NIH Institute or Center (IC) participating in this FOA; (2) AI/ML with competencies in computer science/informatics, along with biostatistics/mathematics.

Primary Organizational Focus of the Training Program Given the cross-disciplinary focus of this AIPrN program, multiple PDs/PIs are required and necessary. This FOA requires applicants to assemble an interdisciplinary team of scientific mentors to design and direct a cross-disciplinary training program. While traditional Ph.

D. or postdoctoral programs may have a primary mentor for each trainee, this program requires two primary mentors (or thesis advisors) for each trainee. Mentors should have expertise in one of the following two areas : Nutrition science or relevant biomedical research discipline; or AI including ML, computational or data science analytic approaches such as engineering, computer science, applied mathematics, or statistics.

Enhancing Trainee Diversity While projects selected for training across the translational spectrum of the sponsoring institutes are encouraged, ideally a number of those should aim to make discoveries from large datasets in order to reduce the rate of diet-related chronic diseases that disproportionally affect racial and ethnic minority populations and NIH-designated populations that experience health disparities, including less privileged socioeconomic status (SES) populations, underserved rural populations, sexual and gender minorities (SGM).

See, https://www. nimhd. nih.

gov/about/strategic-plan/nih-strategic-plan-definitions-and-parameters. html#:~:text=NIH%20defines%20health%20disparity%20populations,or%20more%20of%20these%20descriptions . and/or reduce food insecurity and hunger.

Cross-Program Team Building Coordinated by ONR The Office of Nutrition Research (ONR) will facilitate and convene annual cross-site meetings with program faculty and trainees. Training programs supported through this FOA will be required to participate in these meetings, which may be held in-person, and periodic training webinars.

The goals for these cross-site meetings are to bring together the mentors and trainees from the different programs in order to exchange best practices in training and course design, as well as to build a network for collaboration among the trainees.

Institutional Letter Ensuring Success of Training Program and Trainees As described later, responsive applications to this FOA must include a letter signed by institutional leadership (e.g., Dean, Vice President for Research, Provost, etc.) that describes the activities and resources that will be provided to ensure the success of the planned training program and its trainees and sustainability after termination of the program .

Areas of Research Interest NIH strongly encourages institutions with expertise in the areas discussed above who have not previously received training grants from NIH to apply. Proposed training programs may complement other ongoing research training and career development programs at the applicant institution.

However, the research training experiences for this new program must be distinct from those currently receiving NIH support or that already exist at the applicant institution. The purpose is to create a new predoctoral and/or postdoctoral training program that is not presently available to potential AIPrN candidates at the applicant institution.

Current P50 Program Directors or applicants at institutions with NIH center grant awards or other programmatic awards such as Clinical and Translational Science Award (CTSA) awards who wish to apply for this program are encouraged to describe how these other awards will be used to provide professional development opportunities or serve as a research hub for these new AIPrN trainees.

Institutional research training grants must be used to support a program of full-time research training. The program may not be used to support studies leading to M. D.

, D. D. S.

, or other clinical, health-professional training. Short-term training is not intended. However, trainees can be supported for the Ph.

D. part of a dual degree program designed to train academic research physicians or dentists. Research training programs solely for short-term research training should not apply to this announcement.

Applicants are strongly encouraged to contact the Scientific/Research Contacts in advance to discuss their application for its overall relevance and responsiveness to this ONR-led training program and its specific relevance to the interests of the participating ICs (see Section VII. , Agency Contacts).

Examples of the training focus for each of the participating ICs includes: National Center for Complementary and Integrative Health (NCCIH) NCCIH supports training programs that are relevant to our mission and strategic priorities for mapping a pathway to research on whole person health focusing on restoring health, promoting resilience, and preventing diseases across a lifespan.

NCCIH supports research on various nondrug and noninvasive health practices encompassing nutritional, psychological, and physical approaches.

Specific to the AIPrN program, NCCIH encourages applications for programs that integrate training in advanced data science with research on natural products, such as dietary supplements, plant-based products, probiotics, and microbial-based interventions for prevention and/or treatment of diet-related chronic diseases.

Computational methods in data science for studying complex systems to advance research on Whole Person Health including machine learning and artificial intelligence algorithms, mathematical and computational modeling, predictive multisystem models, problem-driven multi-models, mechanistic multisystem models, or simulation modeling are of interest.

Proposed research training activities should include basic, translational, clinical, and behavioral focuses on nutrition and natural products research in the context of whole person health. Investigators are strongly encouraged to discuss their plans with NCCIH program staff prior to applying. National Cancer Institute (NCI) NCI leads and supports research to advance scientific knowledge and help people live longer, healthier lives.

NCI has a strong interest in primary prevention and in understanding the development, maintenance, and improvement of diet and multiple health behaviors associated with risk of cancer and with health disparities that emerge over the life course.

Because of the long latency of cancer and tracking of diet and other health behaviors over the life course, systems science can play a vital role in understanding the development of risk-related behavior over the life course and its consequences of cancer incidence and mortality, as well as modeling positive and negative consequences of programs, policies, and environments aimed at improving health.

NCI is interested in research proposals that address cancer risk factors and cancer incidence and mortality over the life course, including, but not limited to: Models that address the complex interactions of diet, alcohol, physical activity, sedentary behavior, sleep, and/or obesity over the trajectory of the life course.

Models that address how changes in diet, nutrition, alcohol use, and other cancer risk factors influence population-level cancer incidence, treatment response, and mortality. Investigation of the interplay between nutrition and the microbiome and their impact on cancer incidence and outcome. Models that address specific programs and policies, such as obesity prevention and their cancer-related consequences.

Such models could explore how to optimize and estimate long term effects on cancer incidence of primary prevention over the life course. Models that validate and optimize mobile and wearable technologies, medical informatics and bioinformatics, big data analytics, machine learning and AI; also encourage empirical validation of new concepts through research prototypes, ranging from specific components to entire systems.

The above and other modeling efforts are encouraged to explore disparities and interactions between interventions and at-risk populations to better understand consequences of environments, programs, and policies relevant for health disparities as well as potential unintended consequences such as inadvertent increases in disparities over time.

National Heart, Lung, and Blood Institute (NHLBI) NHLBI supports programs that provide data science training to behavioral and social science fellows in research areas pertaining to the prevention and treatment of heart, lung, blood, and sleep disorders (HLBS), as well as the promotion of health in these areas, both domestically and internationally.

NHLBI also has interests in research that addresses social determinants of health and health disparities, resilience in HLBS disease, and implementation research of proven-effective evidence-based interventions in clinical, community, or other settings for the prevention and treatment of HLBS.

NHLBI strongly supports research to address health disparities and encourages individuals from diverse backgrounds, including individuals underrepresented in biomedical research to work with their institutions to apply for funding opportunity announcements related to HLBS. In addition to predocs, NHLBI will support post docs and Early-Stage Investigators for this FOA.

Details of NHLBI’s research priorities are provided in the NHLBI Strategic Vision Plan . NHLBI has the biodata Catalyst, https://biodatacatalyst. nhlbi.

nih. gov/about, a resource for investigators who need to find, access, share, store, and compute on large scale datasets. NHLBI BioData Catalyst serves as a cloud-based ecosystem providing tools, applications, and workflows for researchers.

NHLBI BioData Catalyst increases access to NHLBI datasets and innovative data analysis capabilities and accelerates efficient biomedical research that drives discovery and scientific advancement, leading to novel diagnostic tools, therapeutic options, and prevention strategies for heart, lung, blood, and sleep disorders. Datasets include TOPMed and NIH database of Genotypes and Phenotypes (dbGaP ).

NHLBI BIOLINCC ( NHLBI Biologic Specimen and Data Repository (BioLINCC ) has myriad of cohort studies data (MESA, JHS, CARDIA, FHS, HCHS, etc.). Data from these and others could be harmonized and used to develop predictive algorithms to identify metabolically healthy (or unhealthy) individuals in whom healthy dietary patterns may lead to resistance to develop chronic diseases (e.g., diabetes or cardiovascular diseases).

Advances in systems science, including computational biology, cohort datasets, machine learning, big data, omics (genomics, proteomics, metabolomics), neighborhood GIS, dietary, and environmental data could be harnessed for preventive prediction. Once such predictive models are developed and evaluated through simulation models, they could then be tested in real world settings for clinical implementation.

NHLBI is interested in supporting both pre- and post-doctoral training in response to the FOA. Phase 1: data collection, integration and statistical analysis. Applicants may leverage NHLBI datasets, link data from various sources and conduct statistical approaches including, for example matching, weighting, and sensitivity analysis, to identify clusters of individuals with specific phenotypes Phase 2: In Situ trial simulation.

Modeled effects of potential trial and what intervention may have positive effects Phase 3: Testing simulated interventions in real-world settings Potential research questions include: 1.

What are the predictive models that rely on a human systems biology framework including omics (genomics, proteomics, metabolomics), diet and timing of dietary intake, lifestyle, neighborhood GIS and environmental data, health status, social determinants of health that can be derived using big-data analytics (machine learning) to understand inter-individual variation and personalized responsiveness to various dietary approaches? 2.

Using predictive models from big data analytics, what types of dietary patterns are appropriate for individuals with HLBS diseases and conditions including timing of diet and circadian control of various disease states (e.g., circadian rhythm of blood pressure and its control?) 3. Will studies testing simulated interventions and predictive models in the real world be effective in reducing HLBS disease?

Other examples of research of interest to NHLBI are those indicated in the research recommendations from the workshop on precision nutrition: https://www. nhlbi. nih.

gov/events/2021/precision-nutrition-research-gaps-and-opportunities-workshop National Institute on Aging (NIA) NIA supports applications that are relevant to the mission and strategic priorities of NIA to improve the health and well-being of older adults through genetic, biological, behavioral, social, and economical research on aging and longevity.

NIA encourages applications that propose training in advanced data analytics, statistical learning, and data visualization for the use of Artificial Intelligence/Machine Learning (AI/ML) approaches that advance our understanding of the interplay between nutrition, age, and diseases and conditions associated with aging, with the aim to improve health span and longevity.

Proposed research training activities should include basic, translational, clinical, and behavioral focuses on nutrition and aging over the life span, in the context of health and disease.

Examples of relevant research areas include, but are not limited to: Generation of machine learning algorithms to analyze the effects of interventions in humans involving dietary patterns that affect the amount (i.e., caloric restriction), timing (e.g., time-restricted eating), source (e.g., whole-food-plant-based), or macronutrient composition (e.g., high-carbohydrate low-fat) The design of targeted dietary interventions for precision nutrition that address the special needs of older adults The prevention, reversal, and/or increased targeted resilience to age-related degenerative diseases and conditions of age, and the potential effects on life span Application of advanced computational approaches to predict longitudinal dynamics between diet and health trajectories across the lifespan and in aging.

Development of informatics platforms that interrogate health and biomedical datasets to predict the effects of diet and nutrition in special subpopulations of older people at nutritional risk (e.g., frail individuals and those with multiple chronic conditions).

Application of AI/ML methods, including linkage and use of neural network and deep learning methods to gain insight about nutrient uptake and health outcomes among older adults by integrating food shopping behavior data with contextual data, menu labeling, and health outcomes data.

Use of deep learning approaches and integrative analyses to create predictive models that elucidate age-related changes in nutritional requirements/dietary needs. The effects of age on physiological processes through which nutrients and dietary supplements are absorbed, metabolized, and excreted in humans.

Nutritional factors associated with physiologic and psychological changes such as immunocompetence, cardiovascular function, neurological and cognitive function, body composition, physical function, control of appetite, macronutrient utilization, and emotional regulation.

The role of nutritional factors, including dietary supplements, in the prevention and treatment of age-related diseases including diabetes, osteoporosis, neurological disorders, immune deficits, heart disease, cancer, gastrointestinal diseases, and other comorbidities. Using the framework of the Hallmarks of Aging and employing AI approaches to study the cellular and molecular mechanisms of aging that contribute to precision nutrition.

Specifically, the three Hallmarks: deregulated nutrient sensing, stem cell dysfunction, and epigenetic alterations are of particular interest and importance with this funding opportunity. Develop and/or use AI and machine learning approaches to study systems and/or integrative biology in middle to older ages that identify cellular or intrinsic physiological pathways in tissues that impact nutrient sensing systems.

What are the age-associated changes in nutrient sensing systems, metabolomes and microbiomes related to rates of aging and age-associated metabolic disorders? What are the mechanisms of stem cell fitness either extrinsically, in the aging niche or intrinsic to aging stem cells that impact nutrition?

What is the role of nutritional status on the cellular and molecular mechanisms impacting the rates of aging especially in communities and populations that experience health disparities related to food insecurity? What is the role of nutritional status on age-associated changes in genomic stability and epigenetic changes? What is the role of nutritional status on age-associated changes and damage in protein, DNA, and lipids.?

Research training with a focus on brain aging and age-related neurodegenerative Alzheimer’s disease (AD) and AD related dementia (AD/ADRD) is encouraged: Using AI approaches to study the cellular and molecular mechanisms of brain aging and AD/ADRD that would contribute to the development of precision nutrition What are the age-associated changes in nutrient sensing systems, metabolomes and microbiomes related to brain aging and AD/ADRD?

Acquiring skills in AI, machine learning, computational modeling and/or data science methods, and apply them to the understanding of the role of nutrition and diet in the maintenance of brain function and performance (cognition, movement, sensation, emotion) with age, the prevention of and/or slowing of progression of AD/ADRD.

Interactions between nutrition, other lifestyle/environmental factors, and genetics on age-related cognitive decline and progression of AD/ADRD in individuals of different race/ethnic backgrounds. Develop and/or use AI and machine learning approaches to study systems neurobiology in middle to older ages that identify cellular or intrinsic physiological pathways in tissues that impact nutrient sensing systems.

What is the role of nutritional status on brain function in aging especially in communities and populations that experience health disparities related to food insecurity? What are the dietary patterns/nutritional intake patterns that best support brain health and performance (cognition, movement, sensation, and/or emotion) in older adults?

Eunice Kennedy Shriver National Institute of Child Health and Human Development (NICHD) NICHD is particularly interested in precision nutrition-related research relevant to pregnancy, lactation, infants, and children, and individuals with disabilities and undergoing medical rehabilitation.

Further, NICHD is interested in sophisticated modeling and analysis of multi-level influences on racial and ethnic minority populations and NIH-designated populations that experience health disparities, including less privileged socioeconomic status (SES) populations, underserved rural populations, sexual and gender minorities (SGM). .

For any applicant, NICHD will require a strong plan for efforts to diversify the applicant pool for prospective trainees from diverse backgrounds including those from groups nationally underrepresented in biomedical, behavioral, and clinical research (see Notice of NIH’s Interest in Diversity ) .

National Institute of Dental and Craniofacial Research (NIDCR) NIDCR is interested in supporting predoctoral training and development of a diverse and innovative next generation research workforce pursuing applications of artificial intelligence (AI) and machine learning (ML) to advance knowledge in the interface of precision nutrition, and Dental, Oral and Craniofacial (DOC) diseases and conditions, and responses to treatments.

Specific areas of interest include, but are not limited to: Integration and analysis of molecular, omic, genetic, physiologic, phenotypic, behavioral, environmental, socioeconomic and other relevant data, including data from electronic health records and data repositories, to identify role of nutrition that influences underlying molecular and genetic mechanisms of DOC diseases and conditions; Identification and validation, using AI/ML approaches, of the effects of DOC conditions on human nutrition and vice versa, and effects of nutrition on development and progression of DOC diseases and conditions, to identify targets of nutrition-based clinical interventions; Development of criteria and approaches to generate AI/ML-ready, high-quality data and to transform existing data to make it usable for AI/ML applications; Develop and/or apply DOC ontologies and standard terminologies, innovative knowledge representation and exchange approaches, to facilitate findability,