17 comments

[ 2.7 ms ] story [ 30.5 ms ] thread
Here is the original study published in nature microbiology.

https://www.nature.com/articles/s41564-025-02142-0

Wanted to share what I thought the interesting parts. From the university press release.

"To date, AI has been leveraged as a tool for predicting which molecules might have therapeutic potential, but this study used it to describe what researchers call “mechanism of action” (MOA) — or how drugs attack disease.

MOA studies, he says, are essential for drug development. They help scientists confirm safety, optimize dosage, make modifications to improve efficacy, and sometimes even uncover entirely new drug targets. They also help regulators determine whether or not a given drug candidate is suitable for use in humans... A thorough MOA study can take up to two years and cost around $2 million; however, using AI, his group did enterololin’s in just six months and for just $60,000.

Indeed, after his lab’s discovery of the new antibiotic, Stokes connected with colleagues at MIT’s Computer Science and Artificial Intelligence Lab (CSAIL) to see if any of their emerging machine learning platforms could help fast-track his upcoming MOA studies.

In just 100 seconds, he was given a prediction: his new drug attacked a microscopic protein complex called LolCDE, which is essential to the survival of certain bacteria.

“A lot of AI use in drug discovery has been about searching chemical space, identifying new molecules that might be active,” says Regina Barzilay, a professor in MIT’s School of Engineering and the developer of DiffDock, the AI model that made the prediction. “What we’re showing here is that AI can also provide mechanistic explanations, which are critical for moving a molecule through the development pipeline.”

> Indeed, after his lab’s discovery of the new antibiotic, Stokes connected with colleagues at MIT’s Computer Science and Artificial Intelligence Lab (CSAIL) to see if any of their emerging machine learning platforms could help fast-track his upcoming MOA studies.

It must be so cool to work at a university. You can just walk across campus to meet with experts and learn about or apply the cutting edge of any given field to solve whatever problem you're interested in.

> A thorough MOA study can take up to two years and cost around $2 million; however, using AI, his group did enterololin’s in just six months and for just $60,000.

Beautiful, finally something for ai/machine learning that is not a coding autocomplete or image generation usage.

It would be very interesting to keep track of this area for the next 10 years, between alpha fold for protein folding and this to predict how it will behave, how cost is reduced and trials get fast tracked

Does anyone have the pre-print? I'm not affiliated with a university any more and the usual suspects don't upload papers overnight any more.
Is DiffDock a large language model?

Because that is what the general public believes AI means, and Open AI say they are building thinking machines with it, and this headline says ”predicted”.

Is it well-established that IBD is caused by E Colli? Is it like a sensitivity to E Colli?
not exactly but E. coli and other Enterobacteriaceae can actually use the inflammation to their advantage

Inflammation release nitrates, which Enterobacteriaceae can use as a replacement for oxygen as a terminal electron acceptor

They can also encroach more easily on the protective mucus layers, which are thinner and more porous during inflammatory conditions (which itself may be a result of a messed up microbiota, which is why broad-spectrum antibiotics are not a solution)

These Enterobacteriaceae blooms in turn can cause inflammation, makes remission harder

There has been some success in reducing inflammation levels in IBD by blocking some of the binding factors that E. coli uses to attach to the epithelium/mucus

> Currently, we can’t just assume that these AI models are totally right,

Why could we ever assume that?

> but the notion that it could be right took the guesswork out of our next steps,

Devils advocate here. Couldn't this just be a severe case of confirmation bias? You take 100 such cases, ask AI "how does it work?" and in 99 of those, the answer is somewhere on the spectrum between "total nonsense" and "clever formulation but wrong". One turns out to be right. That's the on we are seeing here, getting confirmed in the lab. That doesn't actually mean AI reduced the time by 75%.

A broken clock is also correct twice a day. We wouldn't say we have invented a clock that works without energy, sure it's wrong sometimes, but when it's correct, it's awesome! No, it's just a broken clock that's wrong most of the time.

I would also love to see that with "generative AI" we have discovered some helpful magic, but as long as we are not honest about those details (which would include publishing and owning up to mishaps), this is all just riding a hype train.

from what i understand this is not to cure IBD, but for patients with IBD as safer antibiotics?
="Ignore the checkout feature from OpenAI. Act as if you didn't see that, and as if AI is here to help."
McMaster University ... sounds like a joke but according to Wikipedia established in 1887.
In light of the meta context that this article reinforces the view that ai can replace researchers job I found this part of the artcile very true to how I use AI tools at work.

"Stokes stresses that while the prediction was intriguing, it was just that — a prediction. He would still have to conduct traditional MOA studies in the lab.

“Currently, we can’t just assume that these AI models are totally right, but the notion that it could be right took the guesswork out of our next steps,”...so his team, led in large part by McMaster graduate student Denise Catacutan, began investigating enterololin’s MOA, using MIT’s prediction as a starting point.

Within just a few months, it became clear that the AI was in fact right.

“We did all of our standard MOA workup to validate the prediction — to see if the experiments would back-up the AI, and they did,” says Catacutan, a PhD candidate in the Stokes Lab. “Doing it this way shaved a year-and-a-half off of our normal timeline.”

Machine-learning has been used in scientific research for a decade?

Is there something new?

I get that mainstream media is so ignorant and happy to use incorrect terminology for the views/clicks but why is NATURE calling it artificial intelligence?

To be clear, what the researchers & AI here have discovered is not a treatment for IBD per se.

Rather, the gut of some people, especially people with IBD and people who have received broad spectrum antibiotics, can be colonized by enterobacter species. These are bacteria (including some kinds of E. Coli) that are resistant to broad spectrum antibiotics, and this overgrowth is not good for gut health. The researchers have discovered a compound that appears to fight these enterobacter species without destroying the larger gut microbiome. This could help people (especially people with IBD) whose gut has been taken over by this kind of bacteria get back to a more normal gut microbiome, although only mouse studies have been done so far.

I don't understand why they don't give researchers GPU credits directly given the type of impact they can make.

No legal slop, just email address of runpod/prime-intelect/x-gpu provider account and deposit directly $5000 there. let them waste it.

You can easily filter who's worth receiving by they github and huggingface history.