Harnessing Artificial Intelligence and Polypharmacology to Discover Pharmacotherapeutics for Substance Use Disorders (R43/R44 Clinical Trials Not Allowed) | RFA DA 25 054

Opportunity Information: Apply for RFA DA 25 054

Harnessing Artificial Intelligence and Polypharmacology to Discover Pharmacotherapeutics for Substance Use Disorders (R43/R44 Clinical Trials Not Allowed) is a National Institutes of Health (NIH) small business funding opportunity that supports early-stage research and development aimed at finding better medications for substance use disorders (SUD). The central goal is to speed up discovery of new pharmacotherapeutics that are both more effective and less toxic than existing options by combining modern artificial intelligence approaches with polypharmacology, meaning drugs and drug candidates that intentionally engage multiple biological targets or pathways rather than focusing on a single receptor or enzyme.

This opportunity is issued as an SBIR-style mechanism under R43/R44, which generally corresponds to a phased small business program where Phase I (R43) emphasizes feasibility and proof of concept and Phase II (R44) supports more advanced development and validation. A key boundary for applicants is that clinical trials are not allowed under this announcement, so proposed work should remain in the preclinical or non-clinical domain, such as computational modeling, in vitro testing, ex vivo systems, and in vivo animal studies that do not meet the definition of a clinical trial. The work is intended to produce practical tools, datasets, and assays that can directly support medication discovery pipelines for SUD.

Two broad technical tracks are emphasized. The first is development of AI-driven capabilities to enable multi-target drug discovery for SUD. This can include AI tools that help identify and prioritize combinations of drug targets relevant to addiction biology, design or optimize novel molecules with desired multi-target profiles, and run virtual preclinical studies that predict efficacy and toxicity before expensive laboratory testing begins. It also explicitly includes methods to model polypharmacology across experimental contexts, such as predicting how compounds will behave in vitro and in vivo, anticipating off-target interactions, and evaluating how a molecule might influence multiple neural or peripheral systems implicated in substance use disorders. In practice, this could involve machine learning models trained on chemical, biological, and pharmacological data; generative chemistry approaches for proposing new structures; or integrative models that connect target engagement to downstream functional outcomes related to addiction and relapse.

The second track focuses on building experimental assays that can measure compound effects across multiple targets or biological functions. Rather than single-readout screens, the program is looking for assays designed to capture multi-dimensional pharmacology, which is particularly important when the therapeutic hypothesis depends on balancing effects across several pathways to improve efficacy while minimizing adverse effects. These assays might be biochemical, cellular, circuit-level, or systems-oriented, and could be configured for medium- to high-throughput screening depending on the use case. The emphasis is on assay designs that generate actionable data for polypharmacology, such as profiling panels, pathway-activity signatures, phenotypic readouts, or functional measures that connect more directly to SUD-relevant biology.

Eligibility is limited to small businesses, consistent with the R43/R44 program structure. Foreign (non-U.S.) organizations are not eligible to apply, and non-U.S. components of U.S. organizations are also not eligible to apply. However, foreign components may be allowed under NIH policy as defined in the NIH Grants Policy Statement, which typically means specific parts of the project could potentially be performed abroad if well-justified and permitted, while the applicant organization remains a U.S. small business and complies with all NIH requirements.

Administratively, the opportunity is a discretionary grant in the health domain (CFDA 93.279) administered by NIH. The funding opportunity number is RFA-DA-25-054, and the original closing date listed is July 25, 2024. The program does not list an award ceiling or expected number of awards in the provided summary, which often means applicants should rely on the full announcement for budget caps, project period expectations, and any institute-specific constraints.

Overall, this solicitation is aimed at practical, translationally oriented preclinical innovation: building AI methods that can propose and de-risk multi-target medication candidates for SUD, and building the experimental assay infrastructure needed to validate those candidates and understand their multi-target functional impacts. The intended outcome is a stronger discovery pipeline that can produce safer, more effective pharmacotherapies for substance use disorders without moving into human clinical trial testing under this particular funding announcement.

• The National Institutes of Health in the education, health sector is offering a public funding opportunity titled "Harnessing Artificial Intelligence and Polypharmacology to Discover Pharmacotherapeutics for Substance Use Disorders (R43/R44 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): 93.279.
• This funding opportunity was created on 2024-01-29.
• Applicants must submit their applications by 2024-07-25. (Agency may still review applications by suitable applicants for the remaining/unused allocated funding in 2026.)
• Eligible applicants include: Small businesses.

Apply for RFA DA 25 054

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