A food technology company in San Francisco is exploring a new dimension in utilizing plants in food products. Hampton Creek wants to bring “healthier and affordable food to everyone, everywhere,” and its doing so by using deep learning.
“Our slug is, we apply deep machine learning to plant biological data,” Lee Chae, Hampton Creek’s head of research and development, told VentureBeat in an interview.
Essentially they’re trying to find a “vegan equivalent of an egg” by sifting through and discarding “billions of proteins from hundreds of thousands of plants.” When they do stumble upon something relevant, the protein is tested by chefs with other ingredients.
The standard procedure, VB reports, that the company follows goes something like this:
- Analysis of the Proteins
- Quantify molecular and food-related properties of the proteins.
- Put the proteins into a food-model system and get metrics of how they will perform — like whether they will produce foam or bind with water, for instance.
- Determine the performance of related proteins with predictive models.
The predictive models is where deep learning comes in. “That way, we learn what properties are really meaningful for performance, and we can reduce that search space by just focusing on those properties and increase our hit rate,” Chae said. “Then we can search that space intelligently and efficiently — unlike any other company out there that has not developed this technology.”
“Drawbacks get sent upstairs to the data scientists, who block out the protein in question and others related to it. And Hampton Creek thereby inches closer to its noble goal,” writes Jordan Novet for VB.
So far, the 3 year old startup has landed a partnership with Compass Group to bring out ‘Just Cookies’ after the success of its first product, ‘Just Mayo’, which sold out at Safeway stores within two weeks after launching. Earlier in February this year the company managed a $23 million Series B financing round, bringing the total funding received to $30 million. Expansion overseas is on the cards now.
Read more here.
(Image credit: Hampton Creek)
The Author
