Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

AlphaFold-Powered Drug Discovery of a Novel CDK20 Inhibitor

arxiv.org

Post reply on HN
Print view View original

21–30 of 72 posts

Re: AlphaFold-Powered Drug Discovery of a Novel CDK20 Inhibitor

#21

Post by cracrecry »

mikkelam wrote: post #16

Offtopic: More and more I'm noticing the ever-increasing amount of chinese names in machine learning papers. Can anyone explain that? Are these researchers mainly choosing this field out of their own interest, or is China somehow pushing/sponsoring a lot researchers to pursue this field? I realise that China is pursusing AI dominance, is that just what we're seeing? Note this is purely curiosity, I have no problems w…

>Can anyone explain that?

It is very simple to understand: There are more than 1.200 million Chinese people just in China, and a couple hundred million more outside.

AI is also growing and creating new opportunities, most of them work in Universities on the West.

The same happens in other fields like piano playing, there are so many exceptional players because there are so many Chinese.

Re: AlphaFold-Powered Drug Discovery of a Novel CDK20 Inhibitor

#22

Post by epistasis »

jimmySixDOF wrote: post #14

Interesting to consider this in light of yesterday's news about the lack of success for IBM Watson in Healthcare. https://news.ycombinator.com/item?id=30046432 IBM’s Watson Health is sold off in parts

Alphafold has a clear, easily stated application and problem it solves.

Watson, like the AI craze in general, was mostly buzzwords and hype covering the fact that it was actually three application specialists in a trench coat trying to pass themselves off as machine intelligence.

Re: AlphaFold-Powered Drug Discovery of a Novel CDK20 Inhibitor

#23

Post by ramraj07 »

fnands wrote: post #20
jimmySixDOF wrote: post #14

Interesting to consider this in light of yesterday's news about the lack of success for IBM Watson in Healthcare. https://news.ycombinator.com/item?id=30046432 IBM’s Watson Health is sold off in parts

Eh, I would argue there is a massive difference between drug discovery and patient care, which was what Watson was aiming for. Filtering out useful molecules from useless (or dangerous) ones is a nicely contained (if difficult) problem that ML is pretty good at solving.

To say Watson was aiming for anything is an injustice to the word Aim.

Re: AlphaFold-Powered Drug Discovery of a Novel CDK20 Inhibitor

#24

Post by jio_as »

mikkelam wrote: post #16

Offtopic: More and more I'm noticing the ever-increasing amount of chinese names in machine learning papers. Can anyone explain that? Are these researchers mainly choosing this field out of their own interest, or is China somehow pushing/sponsoring a lot researchers to pursue this field? I realise that China is pursusing AI dominance, is that just what we're seeing? Note this is purely curiosity, I have no problems w…

No post body was provided.

Re: AlphaFold-Powered Drug Discovery of a Novel CDK20 Inhibitor

#26

Post by alpineidyll3 »

bawolff wrote: post #10

For people who know about this area: How far away is something like this from an actual treatment? I assume its pretty far, but is it the sort of thing where you basically have to test to see if it works and is safe-ish? Or are a lot more steps involved? What does promising in this context mean? Like is it the sort of thing that has a 50% chance of eventually being useful, or is it more like 1% chance? Regardless exc…

Very far away, and there are competing experimental technologies which could have yielded the same result in less time. A twist on the same experiment used to do the binding assay called DNA encoded libraries (DEL) can screen millions of molecules against a target. In these screens it's routine to find hundreds of micromolar binders. It's not routine to publish micromolar binders.

This paper isn't really even quantitative scientific evidence that the methodology of the paper is a good hit filtering method. The authors don't say much about the ranking of the non-hits.

It's a valuation booster moreso than a scientific milestone.

Re: AlphaFold-Powered Drug Discovery of a Novel CDK20 Inhibitor

#27

Post by bayesian_horse »

fnands wrote: post #20
jimmySixDOF wrote: post #14

Interesting to consider this in light of yesterday's news about the lack of success for IBM Watson in Healthcare. https://news.ycombinator.com/item?id=30046432 IBM’s Watson Health is sold off in parts

Eh, I would argue there is a massive difference between drug discovery and patient care, which was what Watson was aiming for. Filtering out useful molecules from useless (or dangerous) ones is a nicely contained (if difficult) problem that ML is pretty good at solving.

AlphaFold doesn't sort out molecules. This paper took the 3D model of a protein predicted by the original AlphaFold paper and used that to test random small molecules against it, first virtually then physically.

Re: AlphaFold-Powered Drug Discovery of a Novel CDK20 Inhibitor

#28

Post by bayesian_horse »

rguiscard wrote: post #11

Several authors are in Insilico Medicine[1], which uses AI for drug discovery and has one product in clinical trials if I remember correctly. [1] https://insilico.com/

This paper doesn't use Machine Learning at all, as far as I understand it.

Re: AlphaFold-Powered Drug Discovery of a Novel CDK20 Inhibitor

#29

Post by TaylorAlexander »

ramraj07 wrote: post #23
fnands wrote: post #20

Earlier quoted context omitted.

Eh, I would argue there is a massive difference between drug discovery and patient care, which was what Watson was aiming for. Filtering out useful molecules from useless (or dangerous) ones is a nicely contained (if difficult) problem that ML is pretty good at solving.

To say Watson was aiming for anything is an injustice to the word Aim.

Aiming to market IBM as cool.
Post reply on HN