> There are few approaches that will accelerate the field of drug development and chemistry as a whole in a way that the works of these three people will.

As the author of one such approach, I'm skeptical.

AlphaFold 2 just predicts protein structures. The thing about proteins is that they are often related to each other. If you are trying to predict the structure of a naturally occurring protein, chances are that there are related ones in the dataset of known 3D structures. This makes it much easier for ML. You are (roughly speaking) training on the test set.

However, for drug design, which is what AlphaFold 3 targets, you need to do well on actually novel inputs. It's a completely different use case.

More here: https://olegtrott.substack.com/p/are-alphafolds-new-results-...

Protein structures are similar to each other because of evolution (protein families exist because of shared ancestry of protein coding genes). It's not a weird coincidence that helps ML; it's inherent in the problem. Same with drug design -- very, very, few drugs are "novel" as opposed to being analogues of something naturally in the body.

They're referring to the structure of the protein when a drug is bound, that's what's novel. Novel as in, you can't think of it as "just" interpolation between known structures of evolutionarily related proteins.

That said I'm not sure that's entirely fair, since Alphafold does, as far as I know, work for predicting structures that are far away from structures that have previously been measured.

You're quite wrong about small molecule drug structures. Historically that has been the case but these days many lead structures are made by combinatorial chemistry and are not derived from natural products.

But even drugs made by combinatorial chemistry still generally end up being analogues of natural products even if they aren't derived from them. As Leslie Orgel said "Evolution is cleverer than you are"; chemists are unlikely to discover a mechanism of action that millions of years of evolution hasn't already found.

I... Don't think that's right? Although I would appreciate being corrected with some good sources on this. It's a fast moving field and combinatorial chemistry is still new enough that many recently published structures wouldn't have used it.

I'm well aware of the impact of natural products and particularly plant secondary metabolites in drug discovery. I'm also aware of combinatorial synthesis occasionally hitting structures that are close to natural products.

But from first principles, why would you need to limit yourself to that subset of molecular space?

Obviously, your structure will need to look vaguely biochemical to be compatible with the bodies chemical environment, but natural products are limited to biochemically feasible syntheses, and are therefore dominated by structures derived from natural amino acids and similar basic biochemical building blocks.

For a concrete example off the top of my head, I'm not aware of any natural diazepines - the structure looks "organic" but biochemistry doesn't often make 7-rings, and those were made long before combinatorial chemistry. Might be wrong on this one, since there's so much out there, but I think it holds.

Perhaps we are using "structure" in different senses. Yes, it is possible to generate a molecule with a chemical structure unlike any biological molecule and have it bind to a protein, but it can only do so if its 3D structure is analogous to what naturally binds there. Natural products are a source of drugs because evolution has already done this work for us.

https://en.wikipedia.org/wiki/Functional_analog_(chemistry) explains the difference between structural and functional analogs: fentanyl is quite dissimilar from morphine, but binds the same targets.

Yes, the chemical structures can look very different when drawn in the 2D manner, but that's why 2D structures aren't very useful for understanding binding, much as primary sequences of proteins aren't that useful. Morphine and fentanyl bind to μ-opioid receptors, just like what naturally binds there (endorphins and enkephalin). But if they are binding to the same receptor, they have to have similar structures in the biologically meaningful 3D sense (at least where they bind).

You originally wrote:

> very, very, few drugs are "novel" as opposed to being analogues of something naturally in the body

But "analog" means "structural analog" in this context (see https://en.wikipedia.org/wiki/Structural_analog ), which is why people disagreed with you, presumably.

It appears that you were merely saying that ligands must adopt a 3D conformation that's complementary to the receptor. Sure. That's the entire premise of molecular docking software.

But there can be very dissimilar ligands (like morphine and fentanyl) binding the same receptors. A major goal of drug discovery is to find such novel binders, not to regurgitate known ones.

> Alphafold does, as far as I know, work for predicting structures that are far away from structures that have previously been measured.

It did very poorly at this last time I checked. Maybe AlphaFold3 is better?

> It's not a weird coincidence that helps ML; it's inherent in the problem.

This depends on the application. If you are trying to design new proteins for something, unconstrained by evolution, you may want a method that does well on novel inputs.

> Same with drug design

Not by a long shot. There are maybe on the order of 10,000 known 3D protein-ligand structures. Meanwhile, when doing drug discovery, people scan drug libraries with millions to billions of molecules (using my software, oftentimes). These molecules will be very poorly represented in the training data.

The theoretical chemical space of interest to drug discovery is bigger still, with on the order of 1e60 molecules in it: https://en.wikipedia.org/wiki/Chemical_space

I was just wondering when they were going to award the alphafold2 guys the nobel after after seeing Hinton win the physics one. 100% agree, all three of them totally deserve this one. Baker's lab is pretty much keeping Deepmind in check at this point and ensuring open source research is keeping up. Hats off

Baker has been in the protein folding game for a long time and was the leader before Alphafold came in... His generative paper came out what last year (2023)?

I mean this is a fast award cycle.

David Baker’s RoseTTAFold was first released in 2021.

[1]: https://www.science.org/doi/10.1126/science.abj8754

[2]: https://cen.acs.org/analytical-chemistry/structural-biology/...

Both Rosetta and DeepMind have made contributions outside of protein structure prediction that are far more important for drug discovery.

Are they? What did Demis do?

didn't he lead early successes in RL which popularized it and culminated in protein prediction?

He's founder and CEO of the AI lab that build Alphafold?

Then maybe Sergey and Larry should also get the prize since they founded Google, which owns Deepmind?

They were not equal contributors to the seminal paper that got the prize. From another post in this thread:

"These authors contributed equally: John Jumper, Richard Evans, Alexander Pritzel, Tim Green, Michael Figurnov, Olaf Ronneberger, Kathryn Tunyasuvunakool, Russ Bates, Augustin Žídek, Anna Potapenko, Alex Bridgland, Clemens Meyer, Simon A. A. Kohl, Andrew J. Ballard, Andrew Cowie, Bernardino Romera-Paredes, Stanislav Nikolov, Rishub Jain, Demis Hassabis"

They bought it and it runs autonomously (or did mostly)

He writes software in different areas, so he has the potential to get a Nobel prize in any area soon.

The physics price should have went to Elon Musk!

Also I really hope the Nobel Prize of Economics goes to Bill Gates! He facilitated sooo much advances by releasing Excel that this must be recognized!

And based on this year's announcements so far I am not sure that my sarcastic comments should be taken as a joke!

Except Excel has introduced way to many bugs and how many people has it killed?

As someone in the drug discovery business I’m skeptical as I’ve seen many such “advances” flop.

I remember when computer aided drug design first came out (and several “quantum jumps” along the way). While useful they failed often at the most important cases.

New drugs tend to be developed in spaces we know very little about. Thus there is nothing useful for AI to be trained on.

Nothing quite like hearing from the computational scientist “if you make this one change it will improve binding by 1000x”. Then spending 3 weeks making it to find out it actually binds worse.

Well deserved! My only qualm is it should've been awarded to the team, vs individuals

It needed Oriol as well doing IC work