When artificial intelligence entered drug discovery, expectations soared and bold claims followed: AI would slash development timelines, tame astronomical failure rates, and finally unlock cures for diseases like cancer, dementia, and even ageing. A decade on, the reality looks more complicated.
There is no shortage of technical success stories. AI has demonstrably accelerated early-stage drug discovery, compressing timelines that once spanned years into months. Companies like Insilico Medicine and Recursion have shown that machine learning can rapidly identify and advance candidate molecules through preclinical development. Yet for all this progress, a sobering fact remains: not a single AI-discovered drug has completed clinical trials and reached patients.
That disconnect, between faster discovery and unchanged clinical outcomes, sits at the heart of a growing reassessment of AI’s role in drug development. In a Nature article, Rachel DeVay Jacobson, co-founder and chief scientific officer of Powerhouse Biology, argues that while AI has delivered efficiency gains, it has failed to meaningfully improve clinical efficacy. The bottleneck, she and others suggest, was never molecule generation alone.
As Professor Peter Coveney, Director of the Centre for Computational Science (CCS) at UCL, has noted, AI is often treated as a magic bullet, find the right molecule and everything else will fall into place. However, drug development is an arduous process dominated by clinical uncertainty, biological complexity, and regulatory hurdles that AI currently does little to address. The result is a field forced to confront a difficult question: has AI been solving the wrong problems?
Dr Rachel DeVay Jacobson, Co-Founder and CSO Powerhouse Biology, authored an article in Nature called “The AI drug revolution needs a revolution” in which she outlined how AI has failed to deliver on several promises in drug design. “When the AI revolution marched into the drug development sector and flipped biotechs into techbios, it came with the hope that therapeutic program failure rates would fall and the holy grails of cancer, dementia, and even ageing would finally be found.
“We have seen several success stories where AI substantially accelerated preclinical development, including Insilico’s impressive 30-month sprint and their reported average timeline of 12–18 months to advance 22 benchmark programs from discovery to IND-enabling studies. Recursion also reported a speedy advancement of REC-1245 from discovery to IND-enabling studies in just 18 months,” noted Jacobson."
Coveney recently stated on a Science Friday broadcast, that no AI drugs have yet reached the market. While several success stories have been reported, as Coveney acknowledges, no AI drugs have yet made it through clinical trials. AI may have accelerated the selection of a new candidate drug or preclinical development, but it is not the primary obstacle preventing new drugs from reaching the market. The clinical timeline and failure rates are largely unbothered by the rise of AI in drug discovery.
“There are ones going through the approvals process. But the whole point of this story is that drug discovery is an extremely long and torturous process, and things that may have been discovered by AI, and that's a debatable issue in its own right, that it's not as if you discover something and then it immediately gets approved, it has to go through all these additional hoops, which are things that AI typically has absolutely nothing to do with,” stressed Coveney.
This is a sentiment that is further backed up by Jacobson: “While cutting time (and costs) is commendable, we have yet to see these accelerated timelines translate into revolutionary improvements in clinical efficacy,” she states.
Another point highlighted by Jacobsen is that efficacy has not improved significantly. Should pharma companies be looking at the use of AI to further their understanding of the biological mechanism rather than just selecting new candidate molecules.
Part of this is due to the relatively small number of AI-first molecules that have yet to reach the clinic, and among those, the Should pharma companies be looking at the use of AI to further their understanding of the biological mechanism, rather than just selecting new candidate molecules?majority act on previously established targets. While safety and tolerability tend to improve relative to traditionally developed molecules, their mechanisms of action are generally comparable to those of previously approved drugs. "There is not a sufficient number of cases to power statistical analyses yet, but if these first few AI drugs serve as proverbial canaries in the coal mine, our current AI approaches may not do much to improve clinical efficacy," stated Jacobsen. "Thus, while there have been measurable AI-led improvements in program speed and safety, AI efforts so far have not resulted in more effective drugs.”
Quantifying uncertainty
“The common misconception is that AI can act as a magic bullet: find a molecule, and everything else will follow. AI is good at searching for new molecules, but that is only the “base camp” of drug discovery," stressed Coveney. Many other stages have little to do with AI. In some cases, AI might reduce the overall timeline from ten years to nine. Valuable, yes, but far from the headline claims that AI can deliver new drugs in two years.”
"The problem is compounded because AI is claimed to apply to virtually every domain," Coveney contunued. "While scientific applications demand reproducibility and reliability. Take AlphaFold: despite its Nobel Prize, it predicts protein structures only under specific circumstances for sequences it has seen. For new sequences, its predictions may not be reliable. The challenge is that we need to quantify the uncertainty in AI predictions rather than take them on trust. This is an open problem in science and medicine, and addressing it would significantly improve AI’s credibility.
Many scientists fail to understand the uncertainty in molecular dynamics simulations, and the discipline of uncertainty quantification has emerged over the last decade to address this. This provides error bars or confidence levels for in silico predictions, which is crucial in applications ranging from weather forecasting to healthcare."
"The key point: AI models can fit almost any data, but we cannot currently assess the reliability of predictions on new inputs," added Coveney, "Even if a small subset of parameters dominates uncertainty, those parameters are purely fitting parameters, they do not encode physical or chemical information. We can generate outputs we hope are correct, but cannot verify their reliability."
In theory, uncertainty quantification could make AI more reliable, but doing so would require exascale computing. "In the short term, AI has a limited role in drug discovery: generating hypotheses or suggesting molecules, but not replacing experimental validation or regulatory processes,"
However, it's not all doom and gloom. As Coveney notes, AI can be useful tool in the arsenal of the computational chemist, it just needs to be used in the right place with realistic expectations, as an exploratory tool in the design of new drugs.
Antibiotic design
MIT Professor James Collins is one of the founders of synthetic biology and is a leading researcher in systems biology, the interdisciplinary approach that uses mathematical analysis and modelling of complex systems to better understand biological systems.
His research has led to the development of new classes of diagnostics and therapeutics, including in the detection and treatment of pathogens like Ebola, Zika, SARS-CoV-2, and antibiotic-resistant bacteria. Collins, the Termeer Professor of Medical Engineering and Science and professor of biological engineering at MIT, is a core faculty member of the Institute for Medical Engineering and Science (IMES), the director of the MIT Abdul Latif Jameel Clinic for Machine Learning in Health, as well as an institute member of the Broad Institute of MIT and Harvard, and core founding faculty at the Wyss Institute for Biologically Inspired Engineering, Harvard.
His recent research has explored the use of generative AI to design new antibiotics. In a recent Q&A with MIT News, Collins explained that the team used genetic algorithms and variational autoencoders to generate millions of candidate molecules. “After computational filtering, retrosynthetic modelling, and medicinal chemistry review, we synthesised 24 compounds and tested them experimentally,” Collins stated.
“Seven showed selective antibacterial activity. One lead, NG1, was highly narrow-spectrum, eradicating multi-drug-resistant Neisseria gonorrhoeae, including strains resistant to first-line therapies, while sparing commensal species. Another, DN1, targeted methicillin-resistant Staphylococcus aureus (MRSA) and cleared infections in mice through broad membrane disruption. Both were non-toxic and showed low rates of resistance.”
He goes on to say that the research aims to explore the use of deep learning to design strong antibiotic candidates for clinical development by choosing compounds with “drug-like” properties. “By integrating AI with high-throughput biological testing, we aim to accelerate the discovery and design of antibiotics that are novel, safe, and effective, ready for real-world therapeutic use,” said Collins.
