With cancer treatments and antivirals in mice, we’re not so much targeting the pathogen as targeting the host immune system in the hopes it ends up nerfing the intended target (tumor/virus/whatever).

Given that the compound seems effective against C. Difficile (even if it’s in mice), I’d expect it to work elsewhere.

Of course, I’m not a doctor and have no idea what I’m talking about so grain of salt required.

Here's an analogy which shows how the cynicism here isn't actually useful wisdom:

Lee Sedol lost at go.

Kasparov lost at chess two decades before.

The Kasparov loss was 'exactly the same thing albeit with less computing power'

"Computers can learn complicated games with more computing power"

"Compute power goes up"

"Computer learns more complicated game"

I mean, if you really think of AlphaGo on an extremely high level, it's just a really elaborate way to create and learn a dictionary of moves to take under different circumstances. Of course that's going to be completely dependent on amount of memory and CPU power.

Chess engines have clearly improved in both design and computing power over the years; doubling an engine's resources or pitting a new engine against an old one produces straightforwardly better play. But the drug-discovery technique in use here may not be "playing better" in terms of producing higher-quality predictions.

To extend the chess metaphor:

- Deep Fritz is a stronger player Deep Blue even with 4% as much computing power. This story does not appear to be an algorithmic breakthrough of that source.

- Deep Blue lost to Kasparov in 1996, then beat him in 1997 with double the computing power. That's a clear improvement in play, but not an improvement in efficiency. This story might represent such a change, modelling more prospective drugs to test higher-confidence candidates.

- If an AI that can only win 2% of games against humans plays 10 games, it has an 18% chance of beating someone. But over 100 games, it has an 87% chance of a win. This result might be a team with a larger testing budget claiming the 'first win' without any AI-side improvement.

- If a dozen grandmaster-level chess AIs play GMs, one of them will have to get the first win against a human. Labeling this result a 'breakthrough' in AI terms might be outright publication bias among equivalent projects.

As far as the drug, none of that really matters, except that efficiency improvements would have more potential to increase drug discovery. The drug itself is still useful, and the discovery is a proof of concept; in 1980 no possible computer would have beaten Kasparov. But this is being hailed as a breakthrough in AI in seriously questionable ways. The BBC article, for example, managed to imply that this specific project was novel and important for using neutral nets to produce a significant result.

I guess I'm not sure where the dismissiveness is coming from here. Are claiming this could have been trivially done before? If so, why didn't you or someone else do it already?

Or are you claiming it's an uninteresting result that is not worthy of publication or attention?

It's not a major theoretical advance in ML drug-discovery techniques or the first big step in ML drug discovery. It's certainly not the invention of ML drug discovery or neural nets as an ML technique, both things I've seen implied in news stories on this work.

This is attention-worthy, absolutely. (I'll leave "publication-worthy methodology" to experts.) But it's newsworthy on actual merits, as a drug breakthrough and a demonstration of an increasingly-important technique. So I share the frustration when lazy or confused reporting implies this is the same style of ML-theory breakthrough as CNNs, Transformers, or even neural nets themselves.

Do you not want any non-technical summary articles like this to be written? So that only those with the training to understand a Cell journal article would be able to learn anything about the result?

Or do you prefer that no journal articles be published that rely on 2020-era NN models, because older articles based on less state-of-the-art NNs have been published already?

But I think you raise an interesting point about non-technical summary articles: what do they do and who are they for? Does the non-technical public need to know about this research? Do they gain anything vs. reading the study's actual summary? I'm not sure. I do think there isn't much for non-technical people to get from this article that would be useful. I think the best reason would be for younger people to pique their interest in the field. Though, I honestly don't know the answer.

I do think this one gives non-technical people get something useful, though. More broadly, it'll increase science understanding among the non-scientist/non-technical public, at least on this topic, and good does tend to come out of that.

Linear regression is everywhere in science and that can be classified as machine learning artificial intelligence.

Still, it's cool that science is using more data and more intricate algorithms to produce fits.

That doesn't sound like luck.