Drug discovery is a very long and expensive process. It can take drug companies up to three years just to select potential drug candidates — and that’s before animal testing even begins. 90% Many treatments that then reach clinical trials in humans fail before they reach the market.
Enter AI. Ten years ago, scientists saw an opportunity to harness data and computing power to predict the most likely candidates for a targeted disease treatment. They hoped this approach could cut years off the drug discovery process and increase the success rate of clinical trials.
Investors and drug companies have poured in money to make this a reality. European companies applying artificial intelligence in medical research have raised a total of $2 billion in the past 10 years, according to data from Dealroom. Earlier this year, French pharmaceutical giant Sanofi signed a massive $5.2 billion deal with artificial intelligence company Exscientia.
“There is real acceptance now. In the next few years all drugs will be discovered this way,” says Andrew Hopkins, founder and CEO of Exscientia. UK-based Exscientia – founded in 2012 – was the first AI drug discovery company. Last year’s $510 million IPO was one of the largest ever in biotechnology.
There are 23 candidate drugs based on artificial intelligence in clinical trials as of August 2022, according to the latest drug. study. However, none of them have reached the market yet. So how close are European AI drug discovery companies to delivering on their promises?
Make it through clinical trials
Before a drug can be sold on the market, it must undergo a long process of preclinical testing followed by a series of clinical trials in humans that determine if it is safe and effective. The whole process can take 10 to 15 years old It costs billions of dollars – and most candidates still fail before reaching the market.
The first drug discovered using AI to enter clinical trials was made by Exscientia through a collaboration with its Japanese pharmaceutical partner Sumitomo Dainippon. The drug began clinical trials in 2020 as a treatment for obsessive-compulsive disorder (OCD), but the study Failed Its development was discontinued after a year.
Hopkins will not comment on these findings because Exscientia is no longer involved in the programs it started with Sumitomo. The Japanese pharmaceutical company is currently conducting a phase 1 trial of Alzheimer’s disease with another drug identified by Exscientia.
Some pioneers such as Exscientia and AI Charity Founded a year later from Exscientia, also in the UK, it has already had results from early clinical trials showing that the candidate drugs are safe for humans. But the technology has yet to prove that the drugs are also effective in treating patients.
“The jury is still out,” says Pierre Sucha, partner at VC Amadeus Capital.
The next big milestone, he says, will be seeing late-stage clinical results for these drugs. “Once we can reliably see results on a large scale and in a cost-effective manner, we will know if AI will become one of the main tools for drug discovery.”
We’ll soon start seeing the first efficacy results from clinical trials, and Socha believes we can have an answer as to whether the technology can deliver on its promise by 2026.
What is behind the discovery of drugs?
While we wait for trial results, Socha notes that AI is already affecting drug discovery in many other ways. You see technology through the entire drug development pipeline.
For example, British start-up Ori Biotech is using artificial intelligence to improve efficiency in the manufacture of cell and gene therapies, which is currently a major bottleneck in the pharmaceutical supply chain. The company raised $100 million in a Series B round in January, backed by Amadeus and Octopus Ventures, among other investors.
AI can also enable precision medicine by identifying which patients are most likely to benefit from a particular treatment. French Unicorn Auken He is one of the pioneers in this field.
Exscientia has been proven recently Clinical trial AI-assisted precision medicine could improve outcomes for cancer patients who have relapsed after at least two previous treatments. The company can look at individual cells from a patient’s sample to find the best drug for it.
“It’s the first time that an AI system has been shown to improve clinical outcomes in oncology,” Hopkins tells Sifted.
Can Pharmaceuticals Really Adopt AI?
So far, most AI drug discovery companies are undergraduate and start-up companies. But for it to make a real impact, existing drug companies will have to embrace the technology as well.
Pharmaceutical companies are beginning to integrate AI into their drug discovery pipelines. However, they have been much slower to do so – none of them have yet entered clinical trials with AI-discovered drugs.
The problem for drug companies is that they apply AI to the individual steps of existing drug development methods when it is the entire process that needs to change, says David Brown, president of AI startup Healx.
Brown has 50 years of drug discovery experience and has worked for four major pharmaceutical companies. During his time at Pfizer, he co-developed Viagra – the drug was originally intended to treat heart problems, but it was its side effects that made it popular.
This inspired him to found Healx. Headquartered in Cambridge, startup Use artificial intelligence To sort out drugs that are already safe for humans and repurpose them as treatments for rare diseases. AI Charity Use a similar approach Two years ago, they learned about a drug for rheumatoid arthritis that could also treat COVID-19.
He says one of the main reasons drug discovery fails is human bias when selecting drug targets. For example, a scientist may choose a candidate simply because he has worked in that specific field before. Healx aims to remove this bias by tasking machine learning algorithms with selecting both drugs and their targets. The startup is currently conducting a clinical trial to treat children with fragile X syndrome, a genetic condition that causes intellectual disabilities.
Ultimately, Brown believes, drug companies need to completely re-engineer their operations in order to keep pace with rapid technological advances in artificial intelligence.
“A small company of up to 5,000 people can do what AstraZeneca does [which has 76k employees] He does now,” says Brown. “We need to start increasing efficiency and getting back to previous growth rates.”
What’s Next?
The market for AI drug discovery continues to grow, and as major pharmaceutical companies sign deals worth billions of dollars in the field, new companies are joining the ranks.
One of these new contenders is Aqemia, a Parisian startup that recently raised €30m in a Series A round led by Bpifrance and Eurazeo. Maximilian Levesque, co-founder and CEO, says his team is developing a new artificial intelligence that can increase the speed at which promising candidate drugs are found using quantum physics.
“We can actually test half a billion new compounds every day with the same accuracy as the most accurate method on the market – 10,000 times faster and at the same computing cost,” Levesque tells Sifted.
Aqemia uses quantum physics algorithms to sort millions of compounds and find the ones that can best interact with the desired target. While others use “brute force” methods to test each compound, the company is able to predict interactions by solving a quantum physics equation that no one else knows how to solve, Levesque says.
“We can test half a billion new compounds every day with the same accuracy as the most accurate method on the market.”
The company already has dozens of in-house drug discovery projects, primarily targeting cancer, and has partnered with major drug companies including Sanofi, Servier and Janssen. The main advantage of pharma is that this technology can be used without any prior data – something that all other AI companies need to be able to train their machine learning algorithms. This could allow drug companies to quickly catch up with their competitors when developing new drugs.
Other startups are getting ahead Quantitative Statistics for drug discovery. Two examples are Algorithmiq in Finland and Qubit Pharmaceuticals in France – both of which raised money to develop their technology earlier this year.
While the pharmaceutical industry has been slow to welcome digitization and other new technologies, founders and scientists say the tide is turning. In every aspect – from test tube to trial – the drugs of tomorrow will not be the same as the drugs of today.
“It’s not about applying a single machine learning algorithm to a single problem. We want to re-engineer the whole process of how drug discovery is done – and that will be the biggest challenge for us,” Hopkins says.
Clara Rodriguez Fernandez is a Berlin-based Sifted deeptech reporter. follow her LinkedIn.
