BioPharma, Startups, Artificial Intelligence

Flagship reveals machine learning-based protein drug discovery startup Generate Biomedicines

The company said it had used its machine learning platform to generate multiple antibodies and peptides against the Covid-19 virus in less than 17 days and could potentially create hitherto “impossible” protein-based therapeutics.

Life sciences venture capital firm Flagship Pioneering is bringing a new preclinical startup focused on use of machine learning to discover new drugs out of stealth mode.

The Cambridge, Massachusetts-based firm said Thursday that it had unveiled Generate Biomedicines, which it touts as being able to rapidly invent new drugs ranging from antibodies, peptides, enzymes, cytokines and what it called “heretofore undiscoverable protein therapeutics.” The company was launched out of its in-house Flagship Labs and includes scientists who have previously launched several other companies.

sponsored content

A Deep-dive Into Specialty Pharma

A specialty drug is a class of prescription medications used to treat complex, chronic or rare medical conditions. Although this classification was originally intended to define the treatment of rare, also termed “orphan” diseases, affecting fewer than 200,000 people in the US, more recently, specialty drugs have emerged as the cornerstone of treatment for chronic and complex diseases such as cancer, autoimmune conditions, diabetes, hepatitis C, and HIV/AIDS.

The process is described as starting with Generate’s machine learning system learning from all known proteins, encoding and applying principles of how genetic sequences lead to protein structure and function. It then creates new protein sequences.

“Breakthroughs in machine learning algorithms, the exponential growth in computing power and the acceleration and democratization of DNA sequencing and DNA synthesis are allowing us to learn from biology at unprecedented scale,” Flagship CEO Noubar Afeyan said in a statement. “Protein design is not a new idea, but it has been frustrated by the limitations of previous technologies.”

The company said it has used its system to build a portfolio of therapeutic candidates, including multiple ones for neutralization of the virus that causes Covid-19, SARS-CoV-2, including antibodies and peptides that target multiple epitopes of the virus’ spike protein. Moreover, the company said its effort took less than 17 days.

“In the history of modern medicine, nearly every drug has been discovered or identified from a lengthy, cumbersome and costly process of trial and error,” Generate CEO Avak Kahvejian said in a statement. “Machine learning has evolved to a point where it can unlock the underlying principles of biology. With our proprietary computational platform, we believe we can move from chance drug discovery to intentional drug generation, not only accelerating the development of existing therapeutic modalities but also creating previously impossible ones.”

Several other companies have also sprung up in recent years with the goal of using artificial intelligence and machine learning to aid drug discovery and development. On Wednesday, Recursion Pharmaceuticals announced that it had secured a $239 million Series D funding round while also partnering with Bayer, whose venture capital arm had led the round.

Photo: PhonlamaiPhoto, Getty Images