For centuries, people chewed willow bark to relieve pain, but scientists at the chemical company Bayer didn’t isolate its energetic ingredient until the nineteenth century and finally patented it. its modified version as Aspirin.
Aspirin is just one example of a drug that comes from natural sources. In fact, the World Health Organization estimates this roughly 40% of recent pharmaceutical products have their roots in the means used by our ancestors.
Even after such impressive success in harnessing nature’s resources, scientists estimate that they have discovered only a small fraction of natural chemicals that will be transformed into powerful medicines.
In part, this is because identifying, isolating and testing naturally occurring molecules is complex and more time-consuming than synthesizing latest compounds in the laboratory.
Viswa Colluru, one of the first employees of Recursion Pharmaceuticals, which went public in 2021, decided that artificial intelligence and other techniques could speed up the means of discovering latest drugs derived from nature.
In 2019, Colluru left Recursion to found Enveda Biosciences, a biotechnology company based in Boulder, Colorado that analyzes plant chemistry to discover potential drugs.
Colluru told TechCrunch that Enveda used all the digital information from around the world about how people in different cultures used plants to treat pain and disease.
“We found that geographically separated cultures around the world were much more likely to use similar plants to treat similar diseases and symptoms, even though they had never spoken to each other,” he said. “They found that a certain plant helped with a stomach ache or a fever or a headache, and that’s literally thousands of years of human experience-based wisdom.”
Currently, the company’s database includes 38,000 medicinal plants associated with roughly 12,000 diseases and symptoms.
Once Enveda’s AI identifies the plants with the highest probability of recovery, it collects materials and tests them using the company’s AI model. Unlike traditional methods for examining single molecules, Enveda’s transformer model can decipher the “chemical language” of an entire sample.
“Once we know their shape, we can prioritize the right sets of molecules and say this will be a drug one day,” Colluru said.
Enveda’s approach is starting to bear fruit. According to Colluru, clinical trials of the company’s two drugs – one for eczema and the other for inflammatory bowel diseases – are scheduled to begin later this yr.
The company’s scientific progress attracted the attention of investors. On Thursday, Enveda announced it had raised a $55 million Series B extension from latest investors including Microsoft, The Nature Conservancy, Premji Invest and Lingotto Investment Fund, in addition to existing backers Kinnevik, True Ventures, FPV, Level Ventures and Jazz Venture Partners. The latest financing brings the company’s total capital to $230 million.
The extension round allows Enveda to add long-term strategic partners to its cap table, and the company plans to raise a Series C later this yr once clinical trials begin, Colluru said.
According to Colluru, Microsoft also provides some cloud credits as a part of the deal, but this is separate from the money investment.
While sampling plants to find drugs is an age-old approach, Enveda is one of the few firms doing it with the help of artificial intelligence. British company Pangea Bio is also researching plants to discover drugs to treat neurological conditions.
Of course, most of the attention in this field has been devoted to marijuana, and its natural sources are best known for producing psilocybin in so-called “magic mushrooms” or other psychedelics that have the potential to treat mental health disorders, but Enveda is not interested in studying their compounds.
“Everyone is focused on cannabis and psychedelics, which only make up a small fraction of the natural world,” Colluru said. “The natural world is so rich in its chemical diversity and biological effects that studying just a few 100 plants is enough to yield so many potential drugs that we don’t know what to do with them.”