Integrating Machine Learning with Computational Fluid Dynamics Models of Orally Inhaled Drug Products (U01) Clinical Trials Not Allowed | RFA FD 24 005

Opportunity Information: Apply for RFA FD 24 005

This funding opportunity, titled "Integrating Machine Learning with Computational Fluid Dynamics Models of Orally Inhaled Drug Products (U01) Clinical Trials Not Allowed" (RFA-FD-24-005), is a Food and Drug Administration (FDA) cooperative agreement focused on improving how generic orally inhaled drug products (OIDPs) are developed and evaluated for bioequivalence (BE). The core idea is to strengthen and expand "alternative BE" approaches that rely on advanced modeling and simulation, rather than depending primarily on expensive and time-consuming clinical endpoint or pharmacodynamic studies. By doing so, the program aims to make it faster and more efficient to bring high-quality generic inhalers to market while maintaining rigorous standards for demonstrating equivalence to reference products.

A major scientific foundation of the opportunity is computational fluid dynamics (CFD), which has already become an important tool in the design and assessment of inhaler devices and aerosol delivery performance. CFD can simulate airflow, particle transport, and deposition behavior in and around inhalers and airways, offering a valuable complement to benchtop testing and certain clinical evaluations. In the context of generic OIDPs, CFD-based evidence can help explain or predict performance differences and support BE arguments when used alongside other data. Despite this progress, the FDA notes that practical bottlenecks still limit broader use of CFD for regulatory and development workflows. These bottlenecks include high computational cost and long simulation times, constraints on grid resolution that can reduce accuracy in complex flow regions, heavy pre- and post-processing burdens tied to large simulation datasets, challenges in estimating model parameters, and difficulty performing robust uncertainty quantification.

The opportunity is designed to address those pain points by integrating machine learning (ML) with CFD models specifically for OIDP applications. The grant seeks development of a methodology, meaning applicants are expected to propose a coherent, defensible framework for using ML to make CFD-based approaches more usable, scalable, and informative for BE assessments. In practice, this could involve ML tools that accelerate simulations (for example, surrogate or reduced-order models that approximate CFD outputs much faster), improve parameter estimation or calibration from experimental data, automate or streamline processing of high-dimensional CFD results, and support uncertainty quantification so that predictions come with clear confidence bounds. The underlying goal is not ML for its own sake, but ML that directly alleviates known CFD limitations and produces outputs that are meaningful for evaluating equivalence of generic inhaled products.

Administratively, the award mechanism is a U01 cooperative agreement, which typically implies substantial involvement and collaboration with the funding agency during the project. The program is categorized as discretionary funding and is listed under the FDA's CFDA number 93.103. Clinical trials are explicitly not allowed under this announcement, signaling that proposed work should remain in the modeling, simulation, method development, and related non-clinical research space rather than human subject efficacy or endpoint trials.

The funding details indicate an award ceiling of $300,000 and an expectation of a single award, which makes this a relatively targeted solicitation with a competitive selection process. The original application closing date was April 8, 2024, and the opportunity was created on January 15, 2024.

Eligibility is broad and includes a wide range of potential applicants: state, county, city or township governments; special district governments; independent school districts; public and state-controlled institutions of higher education; private institutions of higher education; federally recognized tribal governments and other tribal organizations; public housing authorities/Indian housing authorities; nonprofits with and without 501(c)(3) status (excluding institutions of higher education in those nonprofit categories); for-profit organizations (other than small businesses); small businesses; and the listing also notes "unrestricted," indicating few constraints on organizational type beyond standard federal requirements.

Overall, the opportunity is aimed at advancing regulatory science and practical development tools for generic inhalers by creating a modern hybrid CFD-ML methodology that reduces runtime and workflow friction, improves interpretability and parameterization, and strengthens uncertainty handling. The intended outcome is to promote credible alternative BE approaches that can reduce reliance on costly clinical studies, accelerate review and approval timelines where appropriate, and ultimately support broader patient access to affordable generic OIDPs.

• The Food and Drug Administration in the agriculture, consumer protection, food and nutrition sector is offering a public funding opportunity titled "Integrating Machine Learning with Computational Fluid Dynamics Models of Orally Inhaled Drug Products (U01) Clinical Trials Not Allowed" and is now available to receive applicants.
• Interested and eligible applicants and submit their applications by referencing the CFDA number(s): 93.103.
• This funding opportunity was created on 2024-01-15.
• Applicants must submit their applications by 2024-04-08. (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 $300,000.00 in funding.
• The number of recipients for this funding is limited to 1 candidate(s).
• 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, Unrestricted.

Apply for RFA FD 24 005

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