new-trend1000

Automation, robotization and AI-controlled processes

Robots & AI Partnering in Drug Discovery

Key challenge in drug discovery: The search for good drug molecules in the vastness of chemical space. Turns out, perfect place for robots.

The trend that’s here to stay: There’s an ever-growing list of those in the AI drug discovery space quickly onboarding robots to better enable and accelerate the process: Recursion Pharmaceuticals, Arctoris, Insitro, Relay Therapeutics, and now Insilico Medicine, are the pioneers in the field.

From 4 to 5 years to 8 months!
Robots and AI are beginning to partner to swiftly process millions of molecules while searching for transformative new treatments through digital biology. One pharma-tech company, XtalPi, is even adding quantum physics to the AI, robot discovery search.

German biotechnology company Evotec, announced a new anticancer molecule from its work with UK-based Exscientia that applies artificial intelligence (AI) techniques to small-molecule drug discovery. A discovery process that would ordinarily take 4 to 5 years was accomplished in 8 months.

So, how exactly do robots fit in with AI-infused drug discovery? Well, Recursion Pharmaceuticals is a good example. Recursion “uses an array of robots to treat millions of cell samples with drugs and genetic perturbations [alterations in the function of a biological system], stain them, and image them. It then applies machine learning (ML) algorithms to search for informative relationships between the perturbations and the morphological features of the cells.”

The exciting discovery of a few target molecules out of millions is arrived at after a mind-bendingly dull, time-consuming, repetitive, and ofttimes error-prone process, when performed by human lab techs.

The same process conducted by robots makes all the difference.

“AI (actually, machine learning or ML), with its ability to look at vast quantities of existing data and learn patterns that might be too subtle or complex for humans to recognize, can then predict new small molecules with desirable properties, taking the computational screening process to a new level.”

With drug discovery taking years and costing (at minimum) between $2 to $4 billion per drug, the robot/AI partnership of faster, cheaper, better seems ideal.

As Recursion says on its website: “The industrial revolution of drug discovery is here.”

The money flowing in for investments is plentiful and substantial. Recursion has a deal going with the Bayer for Recursion to work on fibrotic diseases. “The deal included a $30 million upfront payment, plus $100 million each for reaching milestones in up to ten drug discovery programs, making the deal potentially worth more than $1 billion. At the same time, Bayer’s investment arm, Leaps, contributed $50 million to Recursion’s $239 million Series D financing.”

Andrew Hopkins, CEO at Exscientia, said AI provided the ability to search a much vaster chemical space than traditional processes could hope to handle. He predicts that by the end of the decade AI will have a part in the design of every new drug. “What we are seeing is that the competitive advantage and the capital efficiency of these approaches is so superior that actually they will win out as ways to discover drugs,” he said.

 

Growing trend?
Automated labs for AI drug discovery are not for everyone, but it is definitely a growing trend.  Automation, robotization and AI-controlled processes have been developed so far only by a few. In addition to Recursion Pharmaceuticals, there’s Arctoris, Insitro, and Relay Therapeutics.

Insilico Medicine, with its recent $60 million funding round is now automating in what’s being called “next generation experimentalists”. The new funding brings the total raised by Insilico Medicine to an eye-popping $366 million.

One strategic direction for Insilico is to use the funding to build out “a fully automated, AI-driven robotic drug discovery laboratory, and fully robotic biological data factory to complement Insilico’s existing data assets.

The reason for the build out is “the importance of possessing an in-house robotic facility for running preclinical experimentation at scale and being able to generate unique “big data” in industrial volumes, which is especially important now, in the era of deep learning and “network biology” in pharma.”

Robots: The missing partners
Most AI-platforms in the drug discovery market already have algorithms and digital infrastructure. Missing is building a physical high throughput experimentation facility. Such a facility “would enable the company to expand the volume of novel unique data assets and therefore, expand its platform capabilities towards a wider scope of disease areas and therapeutic indications.

Robot partnering is here to stay, which may well be the ultimate research model for a “digital biotech” of the future.