Patina raises $2 million to build a foundation model for scent

Patina, a fragrance technology startup, has raised $2 million in funding from investors including Betaworks and True Ventures. The company plans to use the capital to support its work in molecular design, machine learning, and scent research. Currently, most scent molecules used in consumer products are created by a small number of laboratories, which then sell those molecules to fragrance houses—companies that create scents for brands—or cosmetics companies. Patina is attempting to change this model by using artificial intelligence to design new scent molecules, entering an area that has seen little innovation in almost half a century.

The company was launched last year by Sean Raspet and Laura Sisson. Raspet is an artist and perfumer, while Sisson is an engineer with a background in food and software engineering. The two founders met in 2024 at a scent art gallery in New York, where Raspet was exhibiting molecules and Sisson was building olfactory learning models. Patina is currently working on a foundation model—an AI model trained on vast data—called Sense1. The model is designed to replicate the scent receptors in the human nose to create a universal code of smell and taste, replacing imprecise descriptions of smells that can lead to inconsistencies across different regions.

Patina is positioning its technology as a more sustainable alternative to traditional plant extraction, which can be resource-intensive. “These replications are less carbon-intensive than the original plant extract, consuming significantly less water and petrochemicals,” said Sean Raspet, founder and perfumer. This approach could also ease supply-chain pressures for rare natural ingredients like rose oil, which are becoming more expensive and difficult to produce. By using AI, the company can create custom scent ingredients in weeks, not years, allowing perfumers and flavorists to develop and protect their signature styles. Patina is already in talks to work with top fragrance houses and fashion brands, competing against startups like Osmo and legacy companies like Givaudan and Symrise.

The new funding has enabled the team to move to a new office in Brooklyn, where they are working with a small group of chemists to launch new molecules and fund new partnerships. The team is collaborating with startups and academic labs to gather receptor activation data to train its models. Additionally, AI is helping to phase out animal testing, as Raspet noted that new models can predict human-skin reactions nearly as accurately. While understanding primary scents at a molecular level seemed far-fetched to researchers even five years ago, Patina’s long-term goal is to establish a universal matching system for scent, establishing the primary molecules from which any smell or flavor can be built.

Why it matters

Patina is attempting to modernize the fragrance industry by using AI and molecular design to create new scent molecules. By establishing a biological code for smell, the company aims to solve supply-chain issues for rare ingredients and make custom scent creation faster and more accessible.