Using AI to leverage existing data to get new drugs faster

I’NGO Drugs for Neglected Diseases Initiative, which seeks cures for neglected diseases, launched a partnership in April with BenevolentAI, a British company working to develop new molecules using AI. BenevolentAI is not on its first try. She notably highlighted, during the pandemic, the role that a molecule, baricitinib, developed by the Eli Lilly laboratory for another disease, can play in the treatment of patients with Covid-19.

One would think that AI is now all the rage. But in the pharmaceutical sector, the change is more than cosmetic. In early 2020, Exscientia, a Scottish start-up, developed a first molecule with Japanese pharmaceutical Sumitomo Dainippon”built” by AI, entry into clinical trial.

It’s not futuristic: artificial intelligence is a methodological approach to data processing, which can be used at various stages of the pharmaceutical industry development process.“, says Dr. Thomas Borel, director of scientific affairs at the federation of pharmaceutical companies (Leem).

A visit to the Parisian facilities of the French start-up Iktos, founded in 2016, makes us realize the change of season. There are no microscopes or biology devices here, nor lab technicians in white coats. But computer screens galore, which will crunch through masses of health data at a speed no human brain could ever match.

The idea is to exploit existing data to obtain interesting new molecules, faster.“, explains Yann Gaston-Mathé, leader of the start-up, which he co-founded in 2016.

To do this, his team used a global database containing data from 100 million molecules. From this, “we train a model that will automatically generate new molecules, and identify those that will be active in biological targets of interest”, portrays Yann Gaston-Mathé.

Iktos has even created a platform to research molecules using artificial intelligence, which it provides upon subscription to pharmaceutical companies.

We use the so-called generative artificial intelligence

Aqemia, an École nationale supérieure-PSL start-up created in 2019, is developing a drug discovery platform using quantum-inspired statistical physics.

We use the so-called generative artificial intelligence“, underlines the founder, researcher Maximilien Levesque.”We invent molecules that will adhere to a specific biological target responsible for a disease. Artificial intelligence is powered by physics: just know the physical nature of the molecule and the target to calculate its affinity“, he describes.

If startups are at the forefront, big labs are increasingly analyzing the problem and paying the price. US giant Bristol-Myers Squibb signed a deal with Exscientia last year that could pay more than a billion dollars. Gafam is also in the game: in 2019, the Swiss laboratory Novartis and the giant Microsoft announced their collaboration on the matter.

Will this be the end of the chemist in his laboratory? There are major challenges, including accessing actionable data. Not forgetting the need to find future data experts, experts in artificial intelligence and pharmacology issues.

There is also an important regulatory aspect, according to Judge Thomas Borel of Leem. “For example, AI is used to create a virtual arm of patients during a clinical trial. But for this drug to be accepted, regulatory systems must recognize the value of the algorithm.“, he says.

Medicines were designed with the help of computers for years“, comments in turn Yann Gaston-Mathé, who says he wants to bring”additional tools for chemists, not wanting to replace man with machine“.

with AFP

Leave a Comment