On September 15, 2026, Michigan State University announced a $4.6 million first-installment NIH award — part of a grant worth up to $12.8 million over three years — to build computational models that predict how women's shifting hormone levels change the way medicines move through and act within the body. Thirteen researchers from MSU, Rutgers, Emory, Tulane, the University of Colorado Anschutz, the University of Michigan and the University of Utah are collaborating on the project (award number 1OT2OD042764).

Why It Matters

Nearly every consumer-facing sexual health product that touches hormones — menopause telehealth, testosterone therapy for women, hormonal contraception, libido pharmaceuticals, and now the GLP-1 drugs that a Kinsey Institute survey found are quietly reshaping users' sex lives — is being dosed on an evidence base that largely treats hormonal variation as noise rather than signal. That is the specific gap this program is funded to close, and GLP-1s being named as a study target puts it right on top of the most commercially significant drug class in consumer health. For femtech and sexual wellness companies, the near-term value is the dataset. A public, AI-organized corpus of 40 years of hormone research plus a standard computational model of the menstrual cycle is exactly the kind of infrastructure that individual startups cannot afford to build but can all build products on — cycle-aware dosing guidance, menopause treatment personalization, symptom prediction. The timeline is long and the deliverables are academic, so nothing ships next quarter. But the strategic signal is that the federal research apparatus is funding the female-physiology baseline that the entire category has been improvising around, and the resulting tools are designed to be public.

The problem it targets is structural. Clinical trials routinely fail to account for the ways female hormones change across menstrual cycles, pregnancy, contraceptive use, menopause and hormone replacement therapy — an oversight that can leave treatments less effective or more likely to cause severe side effects in women than in men. The team plans to use AI to digitize and organize more than 40 years of hormone research data into a publicly accessible database, build a standard computational model of a 28-day menstrual cycle, and model how hormones regulate the liver, muscle and fat tissue involved in processing nutrients. Real-world patient data will then extend the models to women going through menopause, women on birth control, and women with conditions such as diabetes and obesity. Three-dimensional human tissue models and lab-grown organoids — liver, muscle and ovarian — will be used to test and refine predictions, with metformin, insulin and GLP-1 drugs among the target medicines.

Lead investigator Teresa K. Woodruff, president emerita of MSU and a Research Foundation Distinguished Professor in obstetrics, gynecology and reproductive biology, did not undersell it. "Developing computational models that provide insights into women's health — including the consequences of disease, efficacy and side effects of medicines — and integrate age and reproductive cycle stage is a moon shot," she said. "Our world-class team is taking on this project to enable a generation of healthier women." Emory's Qiang Zhang described the approach as building "mechanistically based computational models of female physiology that can make translational, quantitative predictions for women's responses to metabolic therapies."

The award sits inside the NIH Computational Modeling of Hormone Homeostasis Initiative, a joint program of the NIH Office of Research on Women's Health and the Division of Program Coordination, Planning and Strategic Initiatives, which is distributing $21 million nationally to advance understanding of sex-specific hormonal biology.

Sources

Update — 2026-09-16

Initial entry — story first created.