


Google DeepMind's Spinoff Company 'Very Close' to Human Trials for Its AI-Designed Drugs (fortune.com) 40
Google DeepMind's chief business officer says Alphabet's drug-discovery company Isomorphic Labs "is preparing to launch human trials of AI-designed drugs," according to a report in Fortune, "pairing cutting-edge AI with pharma veterans to design medicines faster, cheaper, and more accurately."
"There are people sitting in our office in King's Cross, London, working, and collaborating with AI to design drugs for cancer," said Colin Murdoch [DeepMind's chief business officer and president of Isomorphic Labs]. "That's happening right now."
After years in development, Murdoch says human clinical trials for Isomorphic's AI-assisted drugs are finally in sight. "The next big milestone is actually going out to clinical trials, starting to put these things into human beings," he said. "We're staffing up now. We're getting very close."
The company, which was spun out of DeepMind in 2021, was born from one of DeepMind's most celebrated breakthroughs, AlphaFold, an AI system capable of predicting protein structures with a high level of accuracy. Interactions of AlphaFold progressed from being able to accurately predict individual protein structures to modeling how proteins interact with other molecules like DNA and drugs. These leaps made it far more useful for drug discovery, helping researchers design medicines faster and more precisely, turning the tool into a launchpad for a much larger ambition... In 2024, the same year it released AlphaFold 3, Isomorphic signed major research collaborations with pharma companies Novartis and Eli Lilly. A year later, in April 2025, Isomorphic Labs raised $600 million in its first-ever external funding round, led by Thrive Capital. The deals are part of Isomorphic's plan to build a "world-class drug design engine..."
Today, pharma companies often spend millions attempting to bring a single drug to market, sometimes with just a 10% chance of success once trials begin. Murdoch believes Isomorphic's tech could radically improve those odds. "We're trying to do all these things: speed them up, reduce the cost, but also really improve the chance that we can be successful," he says. He wants to harness AlphaFold's technology to get to a point where researchers have 100% conviction that the drugs they are developing are going to work in human trials. "One day we hope to be able to say — well, here's a disease, and then click a button and out pops the design for a drug to address that disease," Murdoch said. "All powered by these amazing AI tools."
After years in development, Murdoch says human clinical trials for Isomorphic's AI-assisted drugs are finally in sight. "The next big milestone is actually going out to clinical trials, starting to put these things into human beings," he said. "We're staffing up now. We're getting very close."
The company, which was spun out of DeepMind in 2021, was born from one of DeepMind's most celebrated breakthroughs, AlphaFold, an AI system capable of predicting protein structures with a high level of accuracy. Interactions of AlphaFold progressed from being able to accurately predict individual protein structures to modeling how proteins interact with other molecules like DNA and drugs. These leaps made it far more useful for drug discovery, helping researchers design medicines faster and more precisely, turning the tool into a launchpad for a much larger ambition... In 2024, the same year it released AlphaFold 3, Isomorphic signed major research collaborations with pharma companies Novartis and Eli Lilly. A year later, in April 2025, Isomorphic Labs raised $600 million in its first-ever external funding round, led by Thrive Capital. The deals are part of Isomorphic's plan to build a "world-class drug design engine..."
Today, pharma companies often spend millions attempting to bring a single drug to market, sometimes with just a 10% chance of success once trials begin. Murdoch believes Isomorphic's tech could radically improve those odds. "We're trying to do all these things: speed them up, reduce the cost, but also really improve the chance that we can be successful," he says. He wants to harness AlphaFold's technology to get to a point where researchers have 100% conviction that the drugs they are developing are going to work in human trials. "One day we hope to be able to say — well, here's a disease, and then click a button and out pops the design for a drug to address that disease," Murdoch said. "All powered by these amazing AI tools."
Re: (Score:1)
No, "we" don't.
Re: (Score:1)
Nope. I don't enjoy being around drug and alcohol users.
Stupidity is not a disease (Score:1)
so good luck with pressing your button.
"AI" is good fit for drug discovery (Score:5, Interesting)
Re: (Score:3)
And then there's the toxicity screening part. You have to find something that adequately binds to your target in an inhibitory manner AND make sure it won't bind or accumulate anywhere else in a human body. And if it's a treatment for cancer you have to make sure that it will be infeasible for the tumor to use any of the mechanisms of resistance to evade it.
Re:"AI" is good fit for drug discovery (Score:5, Interesting)
Toxicity screening part became easy because AlphaFold2 created 3D model of all human proteins, so you just need to run the binding test against all of those to see if you have unwanted side effects or not. If the drug doesn't bind, it shouldn't in theory have any side effect.
Re: (Score:2)
Re: (Score:2)
The latter is probably considerably easier than the former. We know that "real human equivalent [A]I" can be created. There are ten billion examples walking around. We don't have an example of an oracle machine that can tell you what a drug is going to do when you put it into one of them.
We also have reasonable bounds on the amount of computation that goes into making one of those "real human" in
Re: (Score:2)
And it's not enough to screen the drug against every protein in your body. You also need to understand how it gets broken down, and test every product it gets broken down into to make sure none of them is toxic. And it can't get broken down too quickly, or it won't have a chance to work.
And even if the drug doesn't bind to anything else on its own, it might still bind in the presence of some third molecule, so you need to consider all possible combinations with other molecules found in your body.
Computati
Re: (Score:2)
That's a nice story, but it's not true. Humans all make variations on the "standard" set of human proteins. Sometimes not important variations, sometimes very important. Proteins aren't one and done either; they're reused all over the place, in different ways. You can target the such and such a receptor on such and such a cell and your drug is going to have off target effects because that same receptor is used in a dozen other cell types to do two dozen other things.
Not to mention drugs don't stay the same
Won't the real test be... (Score:2)
Re: Won't the real test be... (Score:2)
Drug delivery (Score:3)
If they can figure out how to make an LNP that can efficiently deliver a large mRNA payload (30kb) into every cell type, EVERY disease suddenly becomes curable -- today.
How? Because if you can put 30kb of RNA into a cell ... you can make all kinds of stuff. You can basically create a science lab within the cell to detect and fix what's broken (or destroy the cell if it is cancerous and has unwanted mutations).
Re: Drug delivery (Score:2)
In theory. If you can get it into the right cells. HIV for instance lays dormant in reservoirs. That's one reason it has only been treated and not cured yet, outside of very dangerous bone marrow transplants that replace the entire immune system.
Re: (Score:3)
If you can deliver 30 kb of RNA into every cell, you can excise that HIV from any such reservoir cells that contain latent provirus copies. Specifically, there's easily enough within 30kb to include gene excision tools such as CRISPR (which is only around 4kb max) and any other genes you may need to ensure you've fished it out. And btw, 30 kb is not an unreasonable size .. the coronavirus is about that size. Herpes is 150 kb.
Re: (Score:1)
You have 25-35 trillion cells. Some of them are in nearly inaccessible areas like bone marrow. Your body naturally has niches to protect things like stem cells from the systemic signals that would cause their demise (like hair coloring units). This poses challenges. The parent post touched on this dormancy that makes eliminating latent viruses difficult.
The problem with CRISPR is it changes the DNA, which triggers cells DNA damage response mechanisms like P53. The body treats the CRISPR edit like a virus
Re: (Score:2)
Uh, that stuff in that Scientific American article from 2018 is pretty mitigated by now. Reference: https://www.oligotherapeutics.... [oligotherapeutics.org] For one, the cancer risk was exaggerated (cells with broken P53 are there anyway regardless of CRISPR), and second we have better CRISPR tech now -- and it continues to improve. More importantly we have hundreds of humans and plenty of animals edited with CRISPR and they haven't died or shown signs of cancer. https://www.technologyreview.c... [technologyreview.com]
So far nobody has shown that concl
Re: (Score:2)
The vast majority (all?) of those have been editing cells that are removed, then reinjected. One of the benefits of that is you can discard any suspicious ones.
Oh yes, people have died.
Re: (Score:2)
Cells need blood to survive. Therefore they are all reachable. Besides, if a cell is so isolated it probably doesn't need to get treated. If it is virus infected, then how did the virus reach it? A virus is about the size of an LNP, if not bigger.
Re: (Score:2)
Re: (Score:2)
CRISPR has been extensively tested in cancer and no such thing has happened in any instance. Don't make up stuff based on speculation. Reference: https://pmc.ncbi.nlm.nih.gov/a... [nih.gov] Besides, for cancer there are better tech than CRISPR to identify and destroy the cell from within. And btw, most cancers are not as rapidly haphazardly mutating like you think .. if a cell mutated too fast it would not be functional and die. Anyway, I was talking about CRISPR for virus infected cells, which is also something peop
Re: (Score:2)
Re:Sorry, but... (Score:5, Interesting)
You realize that most modern blockbuster drugs, such as the ones that basically cured AIDS were designed on a computer right?
The AI will design a drug, and then it will be tested extensively on cells in a lab. If it works there, then it will be tested in a mouse. After that, it will be given to a human in a trace amount to see safety. If there is no impact, then the dose is escalated to the treatment dosage. Oh and sometimes before it goes to human it will be tested on primate.
Once it is shown that the AI is very good, then we can skip the intermediate steps and go to direct treatment, especially if it's for something like late stage cancer.
Source of new drugs is not computers but nature. (Score:1)
Granted that was early in the computer age, but things haven't changed dramatically since. 2020 study https://pubs.acs.org/doi/10.10... [acs.org]
the “influence of natural product structures” has not decreased materially over the last five years insofar as drug approvals that are based upon such structures are concerned.
That series of studies goes into great detail regarding how much the pharmaceutical industry uses existing natural 'drugs' as leads to patent their own concoctions.
Re: (Score:3)
Personally I would rather take AI designed drug that is not tested in ANY way in any animal or human. Than take a drug that has gone through all required animal and human tests. But that is only because I know how they test them with the AI.
But luckily for you and perhaps for me also. They will have to run all the same animal and human tests for the new drugs, before they are taken into use. So these drugs will be at least as safe as any traditional drugs would be. But because AI can actually check the bind
Re: (Score:2)
Literally nothing that you said in that entire post is true.
Re: (Score:2)
It depends how bad the problem you're suffering with is...
If the choice is between "100% agonising death" and "a drug that has a 1% chance of curing you or 99% change of agonising death" many sane people would choose the latter.
Re:Sorry, but... (Score:5, Informative)
I would not trust AI to write a comedy routine. Why on Earth would any SANE person trust some experiment in language processing to design a new drug???
The term AI is what is confusing you. This AI here is not a language model, and they are not asking questions to a chatbot. It's a physics simulation code, that uses a neural network trained on results of structure and properties of known molecules.
Instead of using classical physics computations on millions of randomly-chosen variations on molecules, that is so time consuming it can't be done, the neural network "guesses" molecular structures that should implement the desired physical/chemical effects, based on correlations in the training dataset.
This drastically reduces the time it takes from millions of potential molecules to a handful of candidates which you can then test one by one on cells/animals/humans.
Re: (Score:2)
I would not trust AI to write a comedy routine. Why on Earth would any SANE person trust some experiment in language processing to design a new drug???
The term AI is what is confusing you. This AI here is not a language model, and they are not asking questions to a chatbot. It's a physics simulation code, that uses a neural network trained on results of structure and properties of known molecules.
Instead of using classical physics computations on millions of randomly-chosen variations on molecules, that is so time consuming it can't be done, the neural network "guesses" molecular structures that should implement the desired physical/chemical effects, based on correlations in the training dataset.
This drastically reduces the time it takes from millions of potential molecules to a handful of candidates which you can then test one by one on cells/animals/humans.
Your post needs to be at +5 informative. 10 years ago, it wouldn't even have been called AI, probably LSNN analysis or the like. But I digress.
In addition to cures or treatments, this will probably help address the prescription drug's big elephant in the room - side effects.
Prescription drugs killing people is one of the leading causes of death. This could be a big step in getting prescription drug's killing people problem knocked way down on that sad list.
Re: (Score:2)
AlphaFold would absolutely have been "called AI" ten years ago.
What's confusing you and the OP is the popular use of the term "AI" to refer to a specific set of language-trained models. This is because humans have difficulty holding more than one concept in their brain at the same time and are also exceptionally susceptible to tech bros trying to sell them shit.
no, that's not it (Score:2)
I'm not confused by the term "AI", rather I am observing human use of such terms and the corruption that circles around the deployment of buzzwords in corporate America. I certainly get that there's a difference between the AI of some stupid chatbot, and the AI code that drives a Tesla, or assists the folks at SpaceX, or other such things. I've been in the tech world for decades and am aware of the protein folding work etc. That's not the point I was trying to make, and hoped would be apparent from the flip
In other words: Still vapor (Score:1)
Before they have completed at the very least Stage 1 human trials, this is all without significance.
In 1950 and 60's scientists worked together (Score:2)
Google will start branding everything Gemini (Score:1)
Now that its money making time ... (Score:2)