Live data from Hacker News

Scientists discover new antibiotics using AI

euronews.com

31–40 of 100 posts

Re: Scientists discover new antibiotics using AI

#31

The headline is sensationalized. They did a virtual screen of a large compound library. QSAR / QSPR / Virtual Screening has been around since the late 1950s. The secret sauce here was the large experimental dataset - on the order of 10^5 compounds - they generated to train the model. Maybe the explainability part is kind of novel for a neural network based approach; but not clear that you couldn’t identify substructu…

The OP says something different:

"The insight here was that we could see what was being learned by the models to make their predictions that certain molecules would make for good antibiotics," James Collins, professor of Medical Engineering and Science at the Massachusetts Institute of Technology (MIT) and one of the study’s authors, said in a statement.

...

"What we set out to do in this study was to open the black box. These models consist of very large numbers of calculations that mimic neural connections, and no one really knows what's going on underneath the hood," said Felix Wong, a postdoc at MIT and Harvard and one of the study’s lead authors.

> not clear that you couldn’t identify substructure classes better with a pure bioinformatic approach.

Lots of things aren't clear, but what supports your particular claim? Has it ever been done? And is it addressed in the article?

Re: Scientists discover new antibiotics using AI

#32

Earlier quoted context omitted.

I think the above commenter is just pointing out how the fundamental conflict between these two things results in significantly lessened incentive for pharmaceutical companies to put money into researching new antibiotics

I extremely know nothing about this field. Would a naive approach would to have a coordinated “crop rotation” type tactic where all hospitals switched to a primary antibiotic every C years/months do anything?

Empirically, many bacteria seem to be able to acquire resistance in a way that doesn't significantly impact their fitness, meaning they can basically get new resistances and keep old ones for almost arbitrarily long, so the crop rotation idea would fail massively.

https://academic.oup.com/femsre/article/35/5/901/2680377

Re: Scientists discover new antibiotics using AI

#33

Earlier quoted context omitted.

It requires a socialized solution: to fund it for future needs rather than for profits.

A government which can't regulate effectively can't be trusted with a monopoly. Anyway, how does holding antibiotics in reserve help anything? Why let the bugs evolve resistance to one antibiotic at a time, rather than hitting them them with multiple antibiotics and thus raising the evolutionary hurdle to resistance? Was this strategy designed by the bad guys in a Jacky Chan movie?

Whatever the theory, the government achieves quite a bit. Look at NASA, as one example, not to mention nuclear energy in all its applications, etc.

Re: Scientists discover new antibiotics using AI

#34
post #4

I've been under the impression that we don't have new antibiotics because it is not economically viable. When you invent new weight loss drug you can sell millions of pills to anyone. If you invent new antibiotic it is immediately classified as "reserve antibiotic" and the sale is restricted.

This is good example of the limits of capitalism.

Re: Scientists discover new antibiotics using AI

#35

Earlier quoted context omitted.

It requires a socialized solution: to fund it for future needs rather than for profits.

A government which can't regulate effectively can't be trusted with a monopoly. Anyway, how does holding antibiotics in reserve help anything? Why let the bugs evolve resistance to one antibiotic at a time, rather than hitting them them with multiple antibiotics and thus raising the evolutionary hurdle to resistance? Was this strategy designed by the bad guys in a Jacky Chan movie?

How would you ensure things like industrial farms use a more expensive multi-antibiotic approach instead of a cheaper single-antibiotic one without effective regulation?

Re: Scientists discover new antibiotics using AI

#36

Earlier quoted context omitted.

It requires a socialized solution: to fund it for future needs rather than for profits.

A government which can't regulate effectively can't be trusted with a monopoly. Anyway, how does holding antibiotics in reserve help anything? Why let the bugs evolve resistance to one antibiotic at a time, rather than hitting them them with multiple antibiotics and thus raising the evolutionary hurdle to resistance? Was this strategy designed by the bad guys in a Jacky Chan movie?

A government which can't regulate effectively can't be trusted with a monopoly.

If only the world were as simple. But it isn't, and everyone knows that those with power (in general, governments) will never be regulated effectively enough for everyone - but that doesn't make them never to be trusted with monopoly, nor does it mean that the government's monopoly is bad.

Sorry, I don't really want private militaries nor private tax collection. I'm happy the government runs things like IDs and drivers licenses. In fact, various department of motor vehicles (or whatever your local thing is called) is an excellent example of how a monopoly can be a good or bad experience. I'm originally from Indiana and the motor vehicle folks are great there and the service is easy to use - by design - but it isn't like that everywhere in the US. This has nothing really to do with how "effective" their regulation is.

I'm not sure actual monopolies are better - are you really satisfied with your electricity provider or ISP?

Re: Scientists discover new antibiotics using AI

#37

The headline is sensationalized. They did a virtual screen of a large compound library. QSAR / QSPR / Virtual Screening has been around since the late 1950s. The secret sauce here was the large experimental dataset - on the order of 10^5 compounds - they generated to train the model. Maybe the explainability part is kind of novel for a neural network based approach; but not clear that you couldn’t identify substructu…

I would recommend reading the actual paper, and not the press release. The main novelty here and what the paper is about is their method, not the discovery of the antibiotic.

Re: Scientists discover new antibiotics using AI

#38

Tigecycline https://www.ncbi.nlm.nih.gov/pmc/articles/PMC1426172/ is a new class of antibiotics discovered around 2005 that also works against resistant bacteria such as MRSA and VRE. So while it is great they are coming up with new antibiotics, it is by no means the first in 60 years.

Ceftaroline

https://pubmed.ncbi.nlm.nih.gov/20334458/

Discovered about at the same time or later. Also works against MRSA.

Re: Scientists discover new antibiotics using AI

#39

Earlier quoted context omitted.

It requires a socialized solution: to fund it for future needs rather than for profits.

A government which can't regulate effectively can't be trusted with a monopoly. Anyway, how does holding antibiotics in reserve help anything? Why let the bugs evolve resistance to one antibiotic at a time, rather than hitting them them with multiple antibiotics and thus raising the evolutionary hurdle to resistance? Was this strategy designed by the bad guys in a Jacky Chan movie?

Anyway what? You don't win an internet argument by dumping some random quote.

If you have some ideas, do share them.

Re: Scientists discover new antibiotics using AI

#40
post #15

What is AI? I've only heard of LLM.

"AI" is what we used to call algorithms, macros, and applications not too long ago. Marketing.

Amazon goes as far as to call my heating fan’s temperature control ai. Probably why it doesn’t work and it randomly turns on and off.
Post reply on HN