CAMBRIDGE, Mass. — Outer Bio has emerged from stealth with Yuna, an ex vivo human skin platform designed to keep full-thickness human skin alive and measurable for more than four weeks, significantly longer than conventional skin explant models.
The company said Yuna preserves native skin architecture and immune function while generating longitudinal biological data that can be used to support machine learning-driven discovery of new skin bioactives.
Outer Bio is positioning the platform as a way to study biological processes that develop over longer periods, including collagen remodeling, chronic inflammation and cellular senescence. Traditional ex vivo human skin models often remain viable for less than a week, limiting their usefulness for studying processes that unfold over several weeks.
Yuna maintains full-thickness human skin, including the epidermis, dermis, multiple cell types and resident immune function, for four weeks or longer. Tissue is sourced from donors across a range of ages, sexes and Fitzpatrick skin types I through VI.
The platform uses longitudinal measurements including transcriptomics, histology and secreted protein analysis. Outer Bio said each compound-sample pair generates more than 30,000 data points.
To date, the company said Yuna has generated more than 10 terabytes of proprietary data from over 300 donors and 10,000 treatments.
Outer Bio is combining those experimental datasets with machine learning to identify and prioritize compounds for testing. Its virtual screening library currently includes 5.9 million compounds across 11 databases, with plans to expand to billions of synthesizable structures.
“Skincare has never lacked demand or ambition. It has lacked the ability to study compounds and mechanisms in living human skin over a biologically relevant timeframe,” said Michael Polansky, Co-Founder and Chief Executive Officer of Outer Bio. “Most experimental platforms rely on reconstructed skin or cell monolayers. Those models can tell you whether a compound is toxic; they can’t tell you whether it works, because they lack the complexity and architecture of the real organ.”
Polansky said Yuna was designed to provide a scalable source of biologically relevant human data for AI-driven discovery.
“AI models are improving far faster than the experiments that validate and train them,” he said. “The bottleneck isn’t intelligence—it’s a scalable source of clinically valid data, and that data has to be grown, not computed.”
Outer Bio also released validation data for Yuna in a bioRxiv preprint. The company said the platform reproduced three different skin biology models over a four-week period.
Those included a psoriasis-like inflammatory response sustained for three weeks and reversed by a clinically used JAK inhibitor, senescence signatures in aged donor tissue that were reduced by a senolytic combination, and UV-induced photoaging injury mitigated by topical sunscreen.
Outer Bio said it has also tested Yuna using a broader range of benchmark bioactives and therapeutic agents in anti-aging, antioxidant, anti-inflammatory, senolytic and skin-protective applications.
Although Yuna is primarily intended for Outer Bio’s internal discovery programs, the company said it will make the platform available through select partnerships with biopharmaceutical companies, ingredient suppliers and consumer brands.
Potential uses include long-duration efficacy studies, skin toxicity assessments and collaborative discovery programs focused on specific areas of skin biology.
