Finding a cure for dengue fever using artificial intelligence (AI)? This is not a science fiction, but a project recently launched by a European NGO, a new sign that AI has now found its place in medicine.
The NGO Drugs for Neglected Diseases Initiative, which seeks to cure neglected diseases, in April launched a partnership with Benevolent AI, a British company that works to create new molecules using AI. Not in BenevolentAI’s first attempt. He highlighted that during the epidemic, one molecule, baricitinib, developed by Eli Lilly Laboratory for another disease, could play a role in the treatment of Kovid-19 patients.
One would think that AI is all the rage now. But the pharmaceutical sector has changed more than cosmetics. In early 2020, Exscientia, a Scottish start-up, entered a first molecular clinical trial “built” by AI with Sumitomo Dinippan, a Japanese pharmaceutical laboratory.
“This is not the future: artificial intelligence is a systematic approach to information processing that can be used at various stages of the pharmaceutical industry’s development process,” said Dr. Thomas Borel, scientific director (LIM) of the Federation of Pharmaceutical Companies.
A visit to the Paris premises of Iktos, a French start-up founded in 2016, helps us understand the changes of the era. Here, there are no microscopes or biological instruments, no lab technicians in white coats. But computer screens abound, which would transcend a huge chunk of health information at a speed that no human brain could reach.
“The idea is to use existing data more quickly to get new interesting molecules,” explained Ian Gaston-Mathe, start-up leader, who co-founded in 2016.
For this, his team used a worldwide database containing data from 100 million molecules. From this, “We have trained a model that will automatically create new molecules and identify those that will be activated for the biological goal of interest”, illustrates Ian Gaston-Mathews.
Iktos has even set up a platform for molecular research using artificial intelligence, which it offers in subscriptions to pharmaceutical companies.
– Interest in big labs –
Aqemia, a start-up from the École Nationale supérieure-PSL created in 2019, is building a drug discovery platform using quantum-inspired statistical physics.
“We use so-called generative artificial intelligence,” underlined founder, researcher Maximilian Levesque. “We invent molecules that stick to a specific biological goal responsible for a disease. Artificial intelligence is fed by physics: we just need to know the physical nature of the molecules and the goal of calculating their compatibility,” he explained.
If start-ups are ahead, major laboratories are increasingly looking at the problem and paying the price. American giant Bristol-Myers Squibb signed a deal with ExxonMobil last year for which it could pay more than a billion dollars. Gaffam is also in the game: In 2019, Swiss Laboratory Novartis and Giant Microsoft have announced their collaboration in this regard.
What is the chemist in his laboratory for all this? There are big challenges with access to workable data. Future data experts on both artificial intelligence and pharmacology, not forgetting the need to find experts.
There is also an important regulatory aspect, Judge Thomas Borel of Lim. “For example, we use AI to create a virtual arm for patients during a clinical trial. But in order to receive this drug, regulatory systems must recognize the value of the algorithm,” he said.
“Medicines have been computer-designed for years,” commented Ian Gaston-Mathews, who said he wanted to provide chemists with “additional equipment” without replacing them with machines.