News for hackers. Stuff that matters.

A comment on I got fooled by AI-for-science hype–here's what it taught me. Parent comment

Re:I got fooled by AI-for-science hype–here's what it taught me by boxed on Tuesday May 20, 2025 @09:03AM (#44041114)
I'm personally waiting for the other shoe to drop here. I suspect that, since nature begins with an existing protein and modifies it slightly, AlphaFold is crazy overfitted to the training data. Furthermore, the enormous success of AlphaFold means that the number of people doing protein structure solving has likely crashed.

So not only are we using an overfitting model that probably can't handle truly novel proteins, we have stopped actually doing the research to notice when this happens. Pretty bad.

[ Parent | on HN ]
Re:I got fooled by AI-for-science hype–here's what it taught me by pixl97 on Tuesday May 20, 2025 @12:59PM (#44043645)
Why do you expect this, or is this just a "I need to find a reason to hate AI" thing?
[ Parent | on HN ]
Re:I got fooled by AI-for-science hype–here's what it taught me by boxed on Thursday May 22, 2025 @09:15AM (#44061747)
It's like every time AI "can code" and then falls on its face when presented with super basic problems that are outside its training data. Why would protein folding be different?
[ Parent | on HN ]
Re:I got fooled by AI-for-science hype–here's what it taught me by flobosg on Tuesday May 20, 2025 @04:54PM (#44045826)
> that probably can't handle truly novel proteins

AlphaFold is able to predict novel folds, see https://www.nature.com/articles/s42003-022-03357-1

[ Parent | on HN ]
Re:I got fooled by AI-for-science hype–here's what it taught me by boxed on Thursday May 22, 2025 @09:13AM (#44061731)
Could once is not the same as can predictably first of all.

Second, how can they possibly know this fold isn't actually in the ENTIRE PDB? I doubt very much that the can. The PDB is enormous.

[ Parent | on HN ]
Re:I got fooled by AI-for-science hype–here's what it taught me by flobosg on Friday May 23, 2025 @05:14AM (#44071255)
> Could once is not the same as can predictably first of all

I was merely addressing your claim in the previous post.

> Second, how can they possibly know this fold isn't actually in the ENTIRE PDB? I doubt very much that the can. The PDB is enormous.

There are well-established fold classification databases (such as SCOP and CATH) where you can query newly solved structures using several structural comparison algorithms (DALI, TM-align, etc).

The Protein Data Bank might be enormous, but there is an enormous amount of structural redundancy as well, from which reduced datasets can be (and are) derived. Protein structure is, after all, much more conserved than sequence, mainly due to the physicochemical principles that govern folding and stability.

[ Parent | on HN ]