Much like the rest of the world, the biotech community has embraced the promise and buzz of all things artificial intelligence over recent years.
In the world of therapeutics, AI tools have already been integrated into many product development workflows, and this tech-meets-bio approach (dubbed TechBio) has become well-defined and the company-building frameworks increasingly well-blueprinted. This TechBio approach involves a combination of computational approaches with physical wet lab data collection to develop new and optimized products.
While these TechBio approaches are relatively well-trodden in a therapeutic product discovery context, they have received far less attention - and funding - in the context of industrial biotechnology product discovery and company building. These same toolkits will have a massive impact in consumer and industrial biotech, tackling weighty areas across food, agriculture, chemicals, climate and more.
Industrial biotechnology refers to the use of the biotechnology tool-kit to manufacture products across a wide range of physical goods industries. Industrial biotechnology companies generally come in two shapes: (1) companies making existing products better, cheaper, and or more sustainable or (2) companies creating completely novel products and ingredients.
If the field of industrial biotech is going to live up to its promise to transform our physical good economy and provide us with healthier, higher performing, and more sustainable new products, we’ll need to improve our ability to choose the molecules and ingredients we’d like to create. Scientists and inventors across food, agriculture, chemicals, materials, and more have never had access to the palette of molecules, ingredients, and building blocks that biology makes accessible. With this wider ingredient palette, there is a glaring need (and opportunity) for new approaches to help ID the most promising molecules for a given application.
Which natural, zero-calorie metabolite will taste just like sugar with no aftertaste? Which protein can endow the stretchiness of a mozzarella to a vegan cheese? Which monomer can contribute to an ultra-high-temperature resistant plastic?
In a world where we can grow anything, how the heck do we decide what to grow?
This ‘molecule selection’ problem is not new. In 1999, Senomyx was founded with a high-throughput (for the 1990s) platform to discover new flavor additives for food & beverage with a taste-receptor screening platform. In the 2010s, companies like Citrine emerged to computational tools for new materials development.
However, only today can a company cost-efficiently combine access to the full palette of molecular building blocks made available by synthetic biology, to truly powerful machine-learning approaches, and to unprecedentedly high-throughput wet lab infrastructure under one roof.
The mapping of molecules to functions and unmet customer needs across industrial verticals will be a ripe area for technology and company building in the years ahead. To read more about how machine-learning approaches will fill this ‘molecule selection’ gap in industrial biotech, check out Ferment colleague Matt Kirshner’s long-form blog post on TechBio in Industrial Biotech here.