 | dkNET_PPAI2024: 2024 dkNET Pilot Funding Program in AI Models to Accelerate Diabetes Heterogeneity Research |
| Website | https://dknet.org/about/ai-pilot |
| Submission link | https://easychair.org/conferences/?conf=dknet-ppai2024 |
| Abstract registration deadline | October 11, 2024 |
| Submission deadline | November 12, 2024 |
dkNET Pilot Funding Program in AI Models to Accelerate Diabetes Heterogeneity Research
Subscribe to our newsletter to receive future funding opportunity announcements
Key Dates
Posted Date: August 23, 2024
Letter of Intent Due Date: October 11, 2024 [application should be submitted by 9 pm PDT (12 am EDT); LOI is encouraged but not required]
Application Due Date: November 12, 2024 [application should be submitted by 9 pm PST (12 am EST); no prior approval is needed to submit the full application]
Earliest Start Date: January 1, 2025
Expiration Date: Nov 13, 2024
Help and Support: If you need any assistance with your submission, please contact us at submissions@dknet.org
Sections:
Section I. Funding Opportunity Purpose
One major challenge in Type 2 Diabetes (T2D) is the enormous heterogeneity associated with the disease. This pilot funding program, through the NIDDK Information Network (dkNET, https://dknet.org), is designed to capitalize on the rapid advances in AI and other data science areas in addressing major gaps in the study of Type 2 Diabetes (T2D) heterogeneity, including opportunities in extracting knowledge from the enormous amount of data and literature, and in recruiting AI experts to this area of domain science. It calls for multi-disciplinary teams to: 1) develop AI foundation models for T2D; (2) validate the models with top research questions in T2D heterogeneity; (3) disseminate the models and engage the community for further development, validation and application; and (4) develop use cases that demonstrate the models’ potential in accelerating research in diabetes heterogeneity study. The teams are expected to work with dkNET to coordinate their projects, so that awardees can integrate and share products through the dkNET platform.
Section II. Funding Opportunity Description
Background
One major challenge in Type 2 Diabetes (T2D) is the enormous heterogeneity associated with the disease, examples include the heterogeneity in genetic predisposition, environmental exposure, individual physiology, biological and pathophysiological pathways in developing disease, to heterogeneity in clinical phenotypes, i.e. response to medication and treatment, and in risk for developing complications and types of complications. To address this challenge, the T2D research community has generated a large amount of data, and has accumulated a vast amount of prior knowledge about the disease. Cross cutting gaps exist in integrating them and extracting predictive signals to advance T2D prevention, diagnosis, prognosis and treatment. Rapid advancements in data science and AI technology offer emerging opportunities and transformative potential in addressing these gaps. Most notably, advancement in generative AI and Large Language Models (LLMs) such as ChatGPT, LLaMA, and Gemini, demonstrate great potential in extracting hidden knowledge and in using the knowledge to further guide multimodal data integration, answering questions, summarizing relevant information, and proposing/evaluating hypotheses. The transformative potential of new AI technologies in biomedicine is widely appreciated. The opportunities in recruiting more AI expertise to T2D research and to strengthen and diversify its workforce are equally important. The goal of this pilot program is to recruit multi-disciplinary teams that include both AI experts and diabetes researchers developing AI foundation models, which will be shared and used by the community, in addressing the major gaps in the study of T2D heterogeneity, and accelerating innovation and translation.
Objectives and Scope
Foundation AI models are large-scale models that are broadly trained and can complete a range of tasks. Some known examples include the Chat Generative Pretrained Transformers (GPT), or ChatGPT, a general purpose foundation model; and scGPT, a foundation model for single cell multi-omics. Though these models are often trained for broad tasks, they have been applied either out of the box or after additional fine tuning, and have demonstrated great potential in biomedicine, including serving as expert systems, and support tools for research, clinical decision making, and patient self-management.
If such foundation models are developed for T2D, researchers can use them to directly support their data reuse, prior-knowledge curation and extraction, and integration and modeling of multi-modal data types with prior knowledge. They can also be further fine-tuned and serve as intelligent systems supporting specific problems relevant to T2D heterogeneity. Furthermore, researchers can use them to develop problem specific resources such as data curation and labeling tools, synthetic datasets to assist clinical studies, data analysis software tools and workflows, support tools for T2D clinical decision making and patient self-management tools, and benchmarks. The pilot funding will provide opportunities to recruit multidisciplinary teams that include both T2D and AI experts, and to develop foundation models in areas including but not limited to:
Information Extraction
- Data-efficient generative AI models for information extraction from unstructured text, and approaches that seek data efficiency and domain adaptability
- Al models that reframe knowledge extraction as a natural language generation task, allowing domain experts to use natural language descriptions to incorporate specific domain knowledge, such as the meanings of entities and relationships, into the information extraction model
- Approaches to facilitate retrieval-augmented generation (RAG) for biomedical LLMs
- Approaches to use the extracted information to augment the training of the foundation model of multimodal datasets
Representation Learning and Explainability
- Scalable, continually expanding, and factually accurate knowledge graphs comprising concepts from biomedical literature
- Knowledge graph embeddings, multimodal representation learning
- Logic and probabilistic reasoning
- Explainable AI, transparent inference mechanism
- Ethics and bias mitigation
T2D Heterogeneity and Multimodal data
- Approaches tackle systems level multi-organ/multi-scale modeling challenges in mapping the heterogeneities in biological and physiological processes and how they impact T2D etiology, pathology, and prognosis
- Precision disease subtyping with multimodal data and molecular biomarkers
- Models to assess and understand the heterogeneity in intervention effect at individual and in community levels
- Models to support study of T2D associated health disparities and the impact on disease heterogeneity
Clinical Decision Support
- Decision support system for clinicians and patients based on the subtypes of T2D
- Models to predict and guide intervention and response such as physical activity and dietary prescriptions
- Models to improve the diagnostic, prognostic, and therapeutic value of Continuous Glucose Monitoring (CGM) profiles in all persons with dysglycemia, and to define digital markers of heterogeneity from CGM profiles together patient-specific factors (e.g., SDOH, age, comorbidities)
- Interpretation and integration of real-time data from CGM and other wearables technology for real-time monitoring of behavioral and physiological parameters to explore diabetes heterogeneity, and to create and assess just-in-time interventions
- Models and digital biomarkers to understand psycho-social-behavioral components of T2D heterogeneity
Given the limited funds available and the pilot nature of the program:
- The application should aim at developing a set of performance metrics for data sets and AI models at the “proof-of-concept” level.
- Applications proposing the purchase of GPUs, or allocation of a significant portion of the budget for cloud resources will not be considered responsive.
- Collecting primary data will not be considered responsive.
Applications should also demonstrate willingness and plans to work with dkNET to coordinate model development, model sharing, AI ethics, co-design with stakeholders, community engagement, and use case development. dkNET, the NIDDK Information Network (https://dknet.org), is a program that supports the NIDDK community’s needs by providing an information portal that connects users to data, analytical tools, and other biomedical research resources. Additionally, dkNET supports researchers by providing a hub for data-driven hypothesis generation; a suite of tools that assist users in FAIR (Findable, Accessible, Interoperable, Reusable) practice, and in improving rigor and reproducibility in research; and a variety of programs to enhance community engagement and workforce development. dkNET previously successfully ran and managed the dkNET New Investigator Pilot Program in Bioinformatics. dkNET program is currently developing an open data science platform to enable the community to participate in AI model development, to share their models, and to develop use cases.
Section III. Award Information
Funding Instrument:
Fixed price subaward, awarded from the NIDDK Information Network (dkNET), University of California San Diego
Application Types Allowed:
New. Studies meeting the current NIH definition of Clinical Trials will NOT be eligible for support under this funding opportunity.
Funds Available:
dkNET intends to commit approximately $750,000 in FY2025 to fund up to 5 awards.
Award Budget:
Awards are limited to $175,000 total costs for 1 year, including applicable F&A costs to be determined at the time of award.
The award budget should not include funds for purchasing GPUs or allocation of a significant portion of the budget for cloud resources.
Project Period:
The initial award is for one year, with the possibility of renewal pending the availability of funds.
Section IV. Eligibility Information
Eligible Organizations
Higher Education Institutions
- Public/State Controlled Institutions of Higher Education
- Private Institutions of Higher EducationThe following types of Higher Education Institutions are encouraged to apply for support as Public or Private Institutions of Higher Education:
- Hispanic serving Institutions
- Historically Black Colleges and Universities (HBCUs)
- Tribally Controlled Colleges and Universities (TCCUs)
- Alaska Native and Native Hawaiian Serving Institutions
- Asian American Native American Pacific Islander Serving Institutions (AANAPISIs)
Non-profits Other Than Institutions of Higher Education
- Non-profits with 501(c)(3) IRS Status (Other than Institutions of Higher Education)
- Non-profits without 501(c)(3) IRS Status (Other than Institutions of Higher Education)
For‐Profit Organizations
- Small Businesses
- For‐Profit Organizations (Other than Small Businesses)
Foreign Institutions
- Non‐domestic (non‐U.S.) Entities (Foreign Institutions) are NOT eligible to apply.
- Non‐domestic (non‐U.S.) components of U.S. Organizations are NOT eligible to apply.
- Foreign components, as NIH Grants Policy, are allowed.
Eligible Individuals (Program Director/Principal Investigator)
For the purposes of this FOA:
Applicants must hold an independent research position at a domestic (U.S.) institution at the time of submission of the application. For the purposes of this FOA, “independent research position” means a position that automatically confers eligibility, by the applicant’s institutional policy, for an investigator to apply for R01 grants, with an appropriate commitment of facilities to be used for the conduct of the proposed research. Investigators still in training or mentored status (e.g. postdoctoral fellows) are not eligible to apply unless they have a written commitment of an independent faculty position that is certified by the institution and provided as part of the application. Investigators from groups that are underrepresented in health-related research as defined by NIH (https://grants.nih.gov/grants/guide/notice-files/NOT-OD-20-031.html) are strongly encouraged to apply. Early Stage Investigators (ESIs), investigators with no prior funding from the NIDDK, investigators with no prior research experience in diabetes, are strongly encouraged to apply.
Applicants may submit or have an R01 grant application pending concurrently with their dkNET AI Pilot Program award. However, if that pending R01 grant is awarded, the dkNET AI Pilot Program Award will not be eligible for renewal.
Section V. Application and Submission Information
Submitting an Application to the Website
dkNET AI Pilot Program Applications is now being accepted. Applications are accepted until Tuesday, November 12, 2024.
Content and Form of Application Submission
Application Forms: It is critical that applicants follow the instructions provided. Conformance to the requirements in the Application Guide is required and will be strictly enforced. Applications that are out of compliance with these instructions may be returned without review.
Letter of Intent: By the due date listed above (October 11, 2024), prospective applicants are asked to submit a letter of intent that includes the following information:
- Descriptive title of proposed activity
- Short abstract (1-2 sentences brief description)
- Name, address and telephone number of the PD/PI
- Names of other key personnel
- Participating institution
Submission Instruction for Letter of Intent
In the submission portal, under “Title and Abstract”, please include the following information:
- Under “Title”: Descriptive title of proposed activity
- Under “Abstract”: Short abstract (1-2 sentences brief description); Name, address and telephone number of the PD/PI; Names of other key personnel; Participating institution
Budget: Budgets are limited to $175,000 total costs, including applicable F&A costs to be determined at the time of award. Applicants should budget for travel to an annual meeting of the dkNET Pilot Awardees each year of the award. Except in unusual circumstances, only the PD/PI may be supported by Pilot funds to travel to a dkNET related meeting ($2000/year).
Include the following items as part of the application found here:
-
Public Health Service Grant (PHS) 398: Face Page (form page 1)
-
Public Health Service Grant (PHS) 398: Detailed Budget for Initial Budget Period (form page 4)
-
Public Health Service Grant (PHS) 398: 2nd year budget and budget justification (form page 5) (Fill out “INITIAL BUDGET PERIOD” only)
-
Investigator Biographical Sketch (Biosketch) (5 page maximum)
-
Other Key Personnel Biosketch (5 page maximum)
-
Research Plan (as detailed below)
1. Project Narrative (500 words)
2. Specific Aims
3. Research Strategy (up to 5 page)
-
Human Subjects (1 page)
-
Vertebrate Animals (1 page)
-
Resource Sharing Plan (up to 2 pages)
-
Data Management and Sharing Plan (up to 2 pages)
-
Facility and Other Resources
-
Public Health Service Grant (PHS) 398: Checklist Form Page
Does the proposed research involve human specimens and/or data?
Select "Yes" or "No" on Question #4 of PHS 398 Face Page (form page 1) to indicate whether the proposed research involves human specimens and/or data. Applications involving the use of human specimens or data may not be considered to be research involving human subjects, depending on the details of the materials to be used. To help determine whether your research is classified as human subjects research, refer to the Research Involving Private Information or Biological Specimens flowchart. If you answered “Yes” to the “Does the proposed research involve human specimens and/or data?” question, you must provide a justification for your claim that no human subjects are involved. This justification should include:
- Information on who is providing the data/biological specimens and their role in the proposed research;
- A description of the identifiers that will be associated with the human specimens and data;
- A list of who has access to subjects’ identities; and
- Information about the manner in which the privacy of research participants and confidentiality of data will be protected.
Research Plan
The research plan should conform to the following instructions with careful attention to use of the headers and word limits outlined below:
- Project Narrative (500 words): Applicants should provide a brief summary of how their objectives and research design will develop AI foundation models that will be shared and used by the community in addressing the major gaps in the study of T2D heterogeneity, and that will help accelerate innovation and translation.
- Research Strategy (up to 5 pages): Describe the scientific problem that you propose to address, its importance, and explain how the AI foundation model(s) you plan to develop will be used by the community in addressing the major gaps in the study of T2D heterogeneity, and how the model(s) will help accelerate innovation and translation. Describe the design of your model(s), approach to model and use case development, and sharing.
Program Specific Requirements: dkNET will coordinate all awarded pilot projects throughout the duration of the award. Awardees are expected to join kickoff meetings and provide regular progress reports as well as develop a plan for integration of their deliverables into dkNET.
Note: Bibliographic citations must fit within the page limit. Figures and illustrations may be included but must also fit within the page limit.
Resource Sharing Plan (2 page maximum): Individuals are required to comply with instructions for providing Resource Sharing Plans as found here NIH Grant Policy on Sharing Research Resources
The following modifications also apply:
If the application proposes the generation of a research resource, the application must provide a precise description of the resource (e.g. code) to be generated. In this section, the applicant should detail timelines and methods to ensure project-generated resources are made available to the investigator community at-large; as well as plans to ensure resources remain available beyond the funding period of the Pilot Award.
Data Management and Sharing Plan (2 page maximum): If the project proposes the generation of dataset(s), data resources, or new data-based resources, the applicant should include a Data Management and Sharing Plan. NIDDK supports the concept that data produced using NIDDK funds should strive to conform to “FAIR” principles (be Findable, Accessible, Interoperable and Reusable) as articulated in the NIH Strategic Plan for Data Science released on June 4, 2018 (NIH Strategic Plan for Data Science). In support of this goal, the plan should precisely describe: 1) the data types and file formats generated, the amount of data, and any related tools and software to be generated, along with standards, unique identifiers, and metadata concepts to be applied (the data files and tools need to be generated/transformed into formats that can be easily accessed by the research community); 2) where the data will be deposited, using established data repositories whenever possible and if established repositories do not exist for the data types to be generated, the plan should describe where the data will be held, how it will be maintained, and how it will be made accessible and advertised to the research community; 3) a precise timeline for deposition of data (within 1 year of validation or upon publication, whichever is first) as well as who will be responsible for the deposition and for maintaining records of data that have been transferred into public repositories; 4) any terms and conditions for re-use and redistribution of data to the research community, including any projected limitations on data access (including de-identification processes needed for human participants or specimens); and 5) plans for oversight of data management as well as for preserving data beyond the project period.
Details of NIH Sharing Policies and related guidance are found here: NIH Sharing Policies. NIDDK specific guidance can be found here: NIDDK Data Management & Sharing
Prior to funding, NIH Program Staff may negotiate modifications to the Resource Sharing Plan and Data Management and Sharing Plan with the applicant.
The NIDDK information network at dkNET provides data management and sharing resources (https://dknet.org/rin/research-data-management), a list of suggested Data Repositories (https://dknet.org/rin/suggested-data-repositories), and can provide assistance with the identification of appropriate resource repositories as well as finding and/or minting Research Resource Identifiers (RRIDs) (https://dknet.org/about/rrid).
Appendix: Letters from Collaborators should be submitted in the Appendix. If meetings/interactions with a collaborator(s) will be virtual, rather than face-to-face, details of these plans (including the mode, frequency and expected efficacy) for such a collaboration should be provided in the letter(s) provided by the collaborator(s). This information will be particularly important for those applicants who propose to acquire new bioinformatics expertise, as well as for those applicants with existing bioinformatics expertise who need to develop an in-depth knowledge of the biological systems that underlie the data to design relevant and practical approaches.
Submission Instruction for the Final Application
The final dkNET application should be one (1) PDF document with the sections in the following order:
Face Page
Project Narrative
Budget
Biosketch(s)
Specific Aims
Research Strategy
Human Subjects
Vertebrate Animals
Resource Sharing Plan
Data Management and Sharing Plan
Facility and Other Resources
Appendix
Checklist
An easy way to assemble the final PDF is to save each file as an Adobe PDF document (‘Save As’). Open the Face Page PDF document in Adobe Acrobat (NOT Acrobat Reader) and select ‘Documents’ => ‘Insert Pages’ => ‘From File….’. Select the remaining PDF documents and click ‘Ok’.
*Please upload your PDF file to the same submission # of your LOI submission.
Help and Support: If you need any assistance with your submission, please contact us at submissions@dknet.org
Section VI. Application Review Information
Criteria
Only the review criteria described below will be considered in the review process. All applications submitted will be evaluated for scientific and technical merit using external peer review.
Overall Impact
Reviewers will provide an overall impact score to reflect their assessment of the likelihood for the project to exert a sustained, powerful influence on the research field(s) involved, in consideration of the following review criteria and additional review criteria (as applicable for the project proposed).
Scored Review Criteria
Reviewers will consider each of the review criteria below in the determination of scientific merit and give a separate score for each. An application does not need to be strong in all categories to be judged likely to have major scientific impact. For example, a project that by its nature is not innovative may be essential to advance a field.
- Significance: Does the project address an important problem or a critical barrier to progress in the field? Is there a strong scientific premise for the project? If the aims of the project are achieved, how will scientific knowledge and technical capability be improved? How will successful completion of the aims change the concepts, methods, technologies, treatments, services, or preventative interventions that drive this field? Is the project an appropriate vehicle for a New Investigator? Is the scope of activities proposed appropriate to meet those needs? Will successful completion of the aims bring about unique advantages or capabilities regarding the application of AI and Large Language Models to compelling research problems in diabetes, endocrinology and related metabolic disorders?
- Investigator(s): Does the investigator have appropriate experience and training to carry out the experiments proposed? Is the investigator, collaborators, and other researchers well suited to the project? Are appropriate collaborations necessary to apply bioinformatics approaches to biological problems in place?
- Innovation: Does the application challenge and seek to shift current research paradigms by utilizing novel theoretical concepts, approaches or methodologies, instrumentation, or interventions? Are the concepts, approaches or methodologies, instrumentation, or interventions novel to one field of research or novel in a broad sense? Is a refinement, improvement, or new application of theoretical concepts, approaches or methodologies, instrumentation, or interventions proposed?
- Approach: Are the overall strategy, methodology, and analyses well‐reasoned and appropriate to accomplish the specific aims of the project? Has the investigator presented strategies to ensure a robust and unbiased approach, as appropriate for the work proposed? Are potential problems, alternative strategies, and benchmarks for success presented? If the project is in the early stages of development, will the strategy establish feasibility, and will particularly risky aspects be managed? Are rigorous bioinformatics approaches used to address a research problem relevant to the field of Diabetes, Endocrinology and Metabolic Diseases?
- Environment: Will the scientific environment in which the work will be done contribute to the probability of success? Are the institutional support, equipment and other physical resources available to the investigator adequate for the project proposed?
Additional Review Criteria:
As applicable for the project proposed, reviewers will evaluate the following additional items while determining scientific and technical merit, and in providing an overall impact score, but will not give separate scores for these items.
Vertebrate Animals:
When relevant, reviewers will evaluate the involvement of live vertebrate animals as part of the scientific assessment according to the following criteria: (1) description of proposed procedures involving animals, including species, strains, ages, sex, and total number to be used; (2) justifications for the use of animals versus alternative models and for the appropriateness of the species proposed; (3) interventions to minimize discomfort, distress, pain and injury; and (4) justification for euthanasia method if NOT consistent with the AVMA Guidelines for the Euthanasia of Animals.
Biohazards:
Reviewers will assess whether materials or procedures proposed are potentially hazardous to research personnel and/or the environment, and if needed, determine whether adequate protection is proposed
Applications will be evaluated for scientific and technical merit by external peer reviewers convened by dkNET using the stated review criteria. As part of the scientific peer review, all applications:
- May undergo a selection process in which only those applications deemed to have the highest scientific and technical merit (generally the top half of applications under review) will be discussed and assigned an overall impact score.
- Will receive a written critique.
- Appeals of peer review will NOT be accepted for applications submitted in response to this funding opportunity.
Applications will compete for available funds with all other recommended applications submitted in response to this funding opportunity. Following initial peer review, recommended applications will receive a second level of review by an ad hoc group convened by dkNET and NIH staff affiliated with dkNET. NIH staff affiliated with dkNET will make final funding decisions, with consideration of the following:
- Scientific and technical merit of the proposed project as determined by scientific peer review.
- Availability of funds.
- Relevance of the proposed project to program priorities.
Anticipated Announcement and Award Dates
After peer review and secondary review of the applications are complete, the PD/PI will be notified by dkNET as to funding decisions in December, 2024
Xujing Wang, Ph.D.
DDEM/NIDDK/NIH
Tel: 301-451-2862
xujing.wang@nih.gov *Preferred method of contact