These threads are always the same: lots of comments about protein folding, how amazing DeepMind is, how AlphaFold is a success story, how it has flipped an entire field on it's head, etc. The language from Google is so deceptive about what they've actually done, I think it's actually intentionally disingenuous.
At the end of the day, AlphaFold is amazing homology modeling. I love it, I think it's an awesome application of machine learning, and I use it frequently. But it's doing the same thing we've been doing for 2 decades: pattern matching sequences of proteins with unknown structure to sequences of proteins with known structure, and about 2x as well as we used to be able to.
That's extremely useful, but it's not knowledge of protein folding. It can't predict a fold de novo, it can't predict folds that haven't been seen (EDIT: this is maybe not strictly true, depending on how you slice it), it fails in a number of edge cases (remember, in biology, edge cases are everything) and again, I can't stress this enough, we have no new information on how proteins fold. We know all the information (most of at least) for a proteins final fold is in the sequence. But we don't know much about the in-between.
I like AlphaFold, it's convenient and I use it (although for anything serious or anything interacting with anything else, I still need a real structure), but I feel as though it has been intentionally and deceptively oversold. There are 3-4 other deep learning projects I think have had a much greater impact on my field.
EDIT: See below: https://news.ycombinator.com/item?id=32265662 for information on predicting new folds.
I would like to correct somethign here- it does predict structures de novo and predict folds that haven't been seen before. That's because of the design of the NN- it uses sequence information to create structural constraints. If those constraints push the modeller in the direction of a novel fold, it will predict that.
To me what's important about this is that it demonstrated the obvious (I predicted this would happen eventually, shortly after losing CASP in 2000).
Could you expand on this? Basically it looks at the data, and figures out what's an acceptable position in 3D space for residues to occupy, based on what's known about other structure?
I will update my original post to point out I may be not entirely correct there.
The distinction I'm trying to make is that there's a difference between looking at pre-existing data and modeling (ultimately homology modeling, but maybe slightly different) and understanding how protein folding works, being able to predict de novo how an amino acid sequence will become a 3D structure.
Also thank you for contacting CASP about this.
Your objection is that alphafold is a chinese room?
What does that matter? Either it generates useful results or it doesn't. That is the metric we should evaluate it on.
It's a really good, fancy model completely reliant on data we already have empirically (and therefore subject to all the same biases as well).
i really don't think anyone is presenting alphafold as if its a physics simulator operating from first principles.
Like obviously alphafold does not "understand". Maybe i have blinders on for being in the computer field, but i would assume that it goes without saying that a statistical deep learning AI model does not tell us how to solve the problem from first principles.
Like yes, alphafold isn't the final chapter in protein folding and that is obvious. But it seems a stretch to dismiss it on those grounds. If that's the metric we're going with then we can dismiss pretty much everything that has happened in science for the past thousand years.
> re self driving car metaphor
I think this is a bad metaphor for your purposes, because self-driving cars aren't de novo understanding, and arguably do have some carry over from things like adaptive cruise control.