Fragrance technology company Patina announced it has raised $2 million in funding from investors including Betaworks and True Ventures.
The company focuses on creating new scent molecules using advanced molecular design, machine learning, and scent research. Most of the scent molecules used in consumer products today are created by a small number of specialized laboratories and then sold to fragrance and cosmetics companies, brands that ultimately turn them into perfumes, candles, and flavored products. Patina is looking to change that by entering a field that has seen little innovation over the past half-century.
The company was founded by Sean Raspet and Laura Sisson. Raspet is an artist and perfumer who over time developed an obsession with human sensations and began creating new scent and flavor molecules as a creative pursuit. Sisson, on the other hand, comes from a background in food engineering and software engineering, and became obsessed with human senses after discovering an entire field of science dedicated to modeling human senses. Naturally, the two met in 2024 at a scent art gallery in New York. There, Razpet was exhibiting new molecules and Sison was an engineer building an olfactory learning model.
“We started collaborating and it became clear that the time was right to finally build a tool to understand scent at a biological level,” Raspet told TechCrunch. “It felt like a company.”
They launched Patina last year and began work on a foundational model called Sense1, designed to recreate the scent receptors in the nose and create what they describe as “the first universal code for smell and taste.” Currently, researchers primarily use words like “floral” and “woody” to describe scent, but this inaccurate system has led to inconsistencies across regions and languages. Working at the receptor level will allow us to “create molecules that have never been smelled before and reconstruct some of the world's rarest natural ingredients,” he said.
Patina said he is already in talks to work with top fragrance houses and fashion brands to create custom perfumes. The timing feels right. Customers are increasingly looking for “newer, safer, more expressive perfumes,” Sisson said. There are also supply chain pressures. Many natural ingredients, like rose oil, have become difficult to produce and expensive, a problem that synthetic alternatives could potentially solve. Patina's molecules can mimic natural materials without the need for botanical extraction and simulate the scent of rose oil at a biological level.
“These replicas are less carbon-intensive than the original plant extracts and consume significantly less water and petrochemicals,” Raspet said.
Other companies in the space include startups like Osmo and established companies like Givaudan and Thinrise, the world's largest flavor and fragrance giants.
Patina is also noteworthy from an intellectual property perspective. Currently, only scent molecules can be patented, not the formulation itself. This means that scents can be easily replicated. This benefits the only major fragrance houses that can afford to develop enough scent variations in the laboratory. AI is making this process cheaper and faster, allowing small companies like Patina to create custom scent ingredients in weeks instead of years.
“We believe that by expanding the palette, perfumers and flavorists of all sizes will be able to develop and protect their signature styles,” said Raspet.
AI is also transforming other parts of the fragrance industry. Raspet said the new model can predict human skin reactions with nearly the same accuracy, helping to phase out animal testing. And while understanding how key scents work at the molecular level seemed far-fetched to researchers even five years ago, Patina's team said AI can help uncover how the senses work at the molecular level.
Raspet said the new funding has already enabled the team to move from its backyard to a proper office in Bushwick, Brooklyn, with a small group of chemists, and will now work toward launching new molecules and funding new partnerships.
“All models need data to learn from, and we were able to fund collaborations with start-ups and academic research institutions to collect this receptor activation data. At the same time, we believe that more detailed computational simulations of molecules' interactions with odorant receptors hold the key to greater scale,” he added.
The long-term goal is to establish what Raspet calls a “scent pantone,” a universal color-matching system used across the design and manufacturing industries, of key scent molecules around which any scent or flavor can be built. “The information has always been there, waiting for technology to catch up and for a team with the right combination of expertise and tenacity to unlock it,” Raspet said. “These ideas can now be brought to life with Patina as the underlying intelligence layer.”
If you buy through links in our articles, we may earn a small commission. This does not affect editorial independence.