“While the prospect of creating ethical pharmaceuticals from medicinal plants has spawned countless companies over the years, they have often encountered insurmountable hurdles to success. Challenges in separating anecdotal folklore from facts, identifying active molecules from complex bioactive extracts, and skepticism by the healthcare industry are but a few.  Enveda is poised to break through these obstacles by harnessing the power of advanced technologies, drawing inspiration from centuries of knowledge to create novel treatments that fill critical medical needs.”

“Several of the most effective drugs which are in clinical use today have been derived from plants. For example, the discovery of Metformin goes back to the anti-diabetic effect observed in a leaf extract from the plant Galega officinalis. With the technology available at the time it took nearly 300 years to develop a safe and efficacious drug from the plant extract. Today, the Enveda team is on the brink of a technological revolution that will enable the systematic search for novel medicines within the entirety of the plant realm by applying machine learning and the translation of AI-generated hypotheses into drug-like molecules in a fraction of the time.”

“In drug discovery, the delivery of high- quality clinical candidates usually aligns with the initial identification of credible starting points, or ”good hits”, in the early stages of projects.  Similarly, “bad hits” are very difficult (or impossible) to optimize.  In our early hit identification work at Enveda,  we access the tremendous diversity that exists in natural products from plants, which are often attractive, drug-like small molecules– “good hits!”!  This approach provides our medicinal chemists the opportunity to use the unique features found in these hits to optimize and discover New Chemical Entities (NCEs) that are different from those found using more traditional methods.”

“I spent many years in large pharma focused on drug discovery; one of our biggest challenges came when a high-throughput screen did not find any hits (credible starting points for drug discovery) that our medicinal chemists thought might progress to leads. This was because our compound deck just didn’t happen to have any suitable scaffolds or the required “chemical diversity”.  Natural products (or compounds) offer far greater molecular diversity than can be found in any company’s compound library deck, but isolating bioactive molecules from natural products or compounds was historically a very slow process. I joined Enveda because I think our approach, combining machine learning and metabolomics, promises to accelerate the identification of both novel compounds and novel targets.”