Osmo’s AI Skin Irritation Test Points to a Future Without Animal Testing

Aashir Ashfaq
5 Min Read
Disclosure: This website may contain affiliate links, which means we may earn a commission if you click on the link and make a purchase. We only recommend products or services that we've personally vetted and that provide added value to our readers.
Osmo’s AI Skin Irritation Test Points to a Future Without Animal Testing

Osmo and the Institute for In Vitro Sciences (IIVS) have released a first-of-its-kind study showing that AI can accurately assess skin irritation without using animal tests, a step that could save tens of thousands of laboratory animals and speed up product development across beauty, personal care, and chemical-intensive industries.

Landmark AI study

The study, published in Alternatives to Laboratory Animals, is described as the first time an AI model for skin irritation has been trained on data generated entirely from validated human-relevant lab methods rather than animal data. The collaboration evaluated the skin irritation potential of more than 3,000 chemicals using an in vitro Skin Irritation Test, generating safety data that would otherwise have required up to 19,134 rabbits under traditional approaches.

Osmo founder and CEO Alex Wiltschko said, “With the support of AI, we’ve shown that it’s not only possible to eliminate animal testing for skin safety assessment, but that we can do it faster, more accurately, and with better relevance to human health.” The company plans to use this AI-driven method for all future skin-safety assessments to prioritize both animal welfare and consumer protection.

How the model works

The Skin Irritation Test in this project was based on reconstructed human epidermis models, a validated in vitro method already accepted by regulators as an alternative to animal testing. This platform was previously used in a Gates Foundation–funded project to discover compounds that can repel, attract, or destroy disease-carrying insects.

That same method was used to calibrate Osmo’s proprietary Olfactory Intelligence platform, which specializes in scent, enabling the AI to learn how different molecules impact skin irritation from a human-relevant dataset rather than legacy animal studies. The result is an AI tool designed to predict skin irritation for large libraries of molecules, giving formulators a way to screen many more ingredients at once before moving into later-stage testing.

Scale and speed advantages

According to IIVS toxicologist Huang (Grace) Huang, Ph.D., the team adapted a non-animal skin irritation test to handle more than 3,000 chemicals in just ten months. This intensive dataset then trains a new AI model capable of predicting irritation across a wide selection of chemicals much more efficiently than traditional methods.

Huang said, “This work marks a major step towards faster, more efficient, and more ethical safety testing, reducing reliance on animal studies while strengthening modern chemical risk assessment with a human-relevant dataset.” For beauty, home care, and fragrance brands under pressure to innovate quickly while meeting tightening safety and animal welfare expectations, this type of system could significantly compress R&D timelines.

What it means for beauty and chemicals

For the fragrance and beauty sectors, AI-based skin safety models can help de-risk ingredient decisions much earlier in the pipeline, especially when exploring novel aroma molecules or alternative preservatives. As more brands and raw material suppliers seek cruelty-free claims, technologies like Osmo’s AI skin irritation model could become an important backbone for compliance and marketing credibility.

Beyond beauty, the tool has implications across any industry that handles large catalogs of chemicals, from household products to public health and security applications. The publication positions this as a milestone in the broader shift toward “modern, human-relevant safety testing methods” that keep pace with both scientific advances and consumer expectations.

Inside Osmo and IIVS

Osmo launched in January 2023 with $60 million in Series A funding led by Lux Capital and Google Ventures, positioning itself as the first company to “digitize scent.” The company blends AI, chemistry, engineering, and neuroscience to create bespoke fragrances for brands and creators, with ambitions that stretch into public health and security applications built on its Olfactory Intelligence platform.

Founded in 1997, IIVS is a non-profit organization focused solely on promoting non-animal test methods and is recognized as a leading provider of in vitro testing for toxicological safety evaluations. Its mix of scientific programs and education initiatives has helped make it a global reference point in the push to replace animal testing with validated alternative methods

TAGGED:
Share This Article