A.I. drug discovery platform Insilico Medicine announces $255 million in Series C funding – TechCrunch

Insilico Medicine, an AI-based drug development and discovery platform, announced Tuesday Series C funding of $ 255 million. The massive round reflects a recent breakthrough for the company: proof that its AI-based platform can create a new target for a disease, develop a bespoke molecule to treat that disease, and begin the clinical trial process.

This is also another indicator that AI and drug discovery are still particularly attractive to investors.

Insilico Medicine is a Hong Kong-based company founded in 2014 with one central premise: that AI-powered systems can identify new drug targets for untreated diseases, help develop new treatments, and ultimately predict how well those treatments can perform in clinical trials . The company previously raised $ 51.3 million in funding after Crunchbase.

Insilico Medicine’s goal of using AI to drive drug development isn’t particularly new, but there is some data to suggest that the company might actually achieve this tour of discovery through study prediction. In 2020, the company identified a novel drug target for idiopathic pulmonary fibrosis, a disease in which tiny air sacs in the lungs are scarred, making it difficult to breathe.

Two AI-based platforms first identified 20 potential targets, narrowed them down to one, then designed a small molecule treatment that showed promise in animal studies. The company is currently filing a new drug application with the FDA and will begin human dosing later this year, with the goal of starting a clinical trial later this year or early next year.

However, the focus here is not on the drug, but on the process. This project condensed the process of preclinical drug development, which typically takes several years and hundreds of millions of dollars to complete, to just 18 months at a total cost of approximately $ 2.6 million. Still, founder Alex Zhavoronkov doesn’t believe that Insilico Medicine’s strengths lie primarily in accelerating preclinical drug development or reducing costs.

“We currently have 16 therapeutic agents, not just IPF,” he says. “It definitely raised some eyebrows.”

“It’s about the likelihood of success,” he continues. “So the likelihood of success in pairing the right target with the right disease with a great molecule is very, very small. The fact that we made it with IPF and other diseases I can’t tell yet – it builds confidence in AI in general. ”

Aided in part by the proof of concept developed by the IPF project and the craze for AI-based drug development, Insilico Medicine drew a long list of investors in this latest round.

The round is led by Warburg Pincus but also includes investments from Qiming Venture Partners, Pavilion Capital, Eight Roads Ventures, Lilly Asia Ventures, Sinovation Ventures, BOLD Capital Partners, Formic Ventures, Baidu Ventures and new investors. These include CPE, OrbiMed, Mirae Asset Capital, B Capital Group, Deerfield Management, Maison Capital, Lake Bleu Capital, President International Development Corporation, Sequoia Capital China and Sage Partners.

This current round was oversubscribed four times, according to Zhavoronkov.

A study from 2018 Of 63 drugs approved by the FDA between 2009 and 2018, the average capitalized research and development investment required to get a drug to market was $ 985 million, which was also the cost for failed clinical trials.

These costs and the low likelihood of drug approval initially slowed the drug development process. R&D returns for biopharmaceuticals hit a low of 1.6 percent in 2019 and rebounded to a measly 2.5 percent in 2020, according to a 2021 study Deloitte report.

Ideally, Zhavoronkov envisions an AI-based platform that is trained on rich data and can reduce the number of failed attempts. There are two main pieces to this puzzle: PandaOmics, an AI platform that can identify these targets; and Chemistry 42, a platform that can make a molecule to attach to that target.

“We have a tool that encompasses more than 60 target recognition philosophies,” he says.

“You’re betting on something that’s new, but at the same time you have some evidence to back your hypothesis. Our AI does that very well. ”

Although the IPF project has not yet been fully published in a peer-reviewed journal, it is a similar project released in the Nature biotechnology was. In this work, Insilco’s deep learning model was able to identify potential connections in only 21 days.

The IPF project is a scale-up of this idea. Zhavoronkov not only wants to identify molecules for known targets, but also to find new ones and accompany them through clinical studies. And, in fact, continue to collect data during these clinical trials that could improve future drug discovery projects.

“So far, nobody has challenged us to solve an illness in partnership,” he says. “When that happens, I’ll be a very happy man.”

However, the Insilico Medicine’s approach to discovering novel target molecules has also been used piece by piece. For example, Insilico Medicine has worked with Pfizer in the discovery of novel targets and Johnson and Johnson in the design of small molecules and done both with Taisho Pharmaceuticals. Today the company also announced a new partnership with Teva Branded Pharmaceutical Products R&D, Inc. Teva will use PandaOmics to identify new drug targets.

That means, Insilico Medicine not only rakes in money and partnerships. The entire field of AI-based novel goals is experiencing considerable hype.

2019 nature found that at least 20 partnerships between large pharmaceutical companies and technology companies for AI drug discovery have been reported. In 2020, investment in AI drug development companies increased to $ 13.9 billion, a four-fold increase from 2019, according to Stanford University Artificial Intelligence Index Annual report. R&D costs

In 2020, drug discovery projects received the most private AI investment, a trend partly due to the need for rapid drug development through the pandemic. However, the roots of the hype lie before Covid-19.

Zhavorokov is aware that AI-based drug development is currently riding a certain hype wave. “Companies with no solid evidence to support their AI-powered drug discovery claims are quick to get in touch,” he notes.

Insilico Medicine can distinguish itself through the quality of its investors. “Our investors don’t gamble,” he says.

But like so many other AI-based drug discovery platforms, we need to see if they can survive the clinical trial migration.