If we can accurately predict protein structures (particularly multiple structures, or structures reflecting what the conformation is in cells), then we can do a couple things:
- better predict drug binding to proteins (massive benefits if accurate)
- better understand the functional outcomes of missense mutations on proteins
- study protein-protein interactions
- and in general, just gain a better understanding of biology (which is driven by proteins and their reactions/interactions)
While the article is correct that knowing the protein structures in itself is not that interesting, it's a prerequisite step to predicting interactions between proteins, which is super interesting for drug discovery.
What's encouraging is the rate of progress, not what has already been done.
Think of it as an engineering problem rather than a science problem.
In much of drug discovery/development (and disease research), being able to predict protein structure would be very valuable. Being able to quickly find candidate structures (that can then be searched for in the lab) speeds things up immensely. Reducing false positives (or just coming up with possibilities at all) is a huge win.
But you’re right that this probably doesn’t help the protein theoretician much if at all. We already “know” how it works (it’s just thermodynamics and quantum mechanics) and of course have no idea how it works (“well they wiggle around until they find a low energy state” doesn’t really tell you anything). But that doesn’t keep this from being exciting.
(a) the structure of every protein (what DeepMind is doing here)
(b) how different protein structures interact (i.e. protein complexes - DeepMind is working on this but not there yet)
Then we could use those two building blocks to design new proteins (drugs) that do what we want. If we solve those two problems with very high accuracy, we can also reduce the time it takes to go from starting a drug discovery programme to approved medicine.
Obtaining all protein structures and determining how they interact is a key step towards making biology more predictable. Previously, solving the structure of a protein was very time consuming. As a result, we didn’t know the structure for a majority of proteins. Now that it’s much faster, downstream research can move faster.
Caveat: we should remember that these are all computational predictions. AlphaFold’s predictions can be wrong and protein structures will still need to be validated. Having said that, lots of validation has already occurred and confidence in the predictions grows with every new iteration of AlphaFold.
This is a really good solution. Of course, there's still room for more research and better methods in the future, but now computational protein structure prediction can compete with experiments actually measuring the structure.
A known 3D structure for your target protein is very useful to improve molecules that bind to it, but we can't yet determine which molecules bind to a target without actually trying it experimentally. Of course there are methods to predict binding, but they not reliable enough and in the end the drug candidates are discovered by throwing a lot of molecules at a specific target or assay.
Once you have a candidate, it is very useful to determine the structure of the protein together with the drug candidate. There you can see how it binds, and can make some educated guesses on how to change the molecule to make it bind better, or to improve other aspects without making it bind worse.
Determing the protein fold from scratch without experimental data is impressive, but it doesn't have an immediate use for drug development. But a few steps further and it could certainly help if you can also predict which molecules bind to the protein structure.
I would strongly recommend the following blog post from Derek Lowe to put the importance of this into context for drug development:
You can assume that any known drug target has experimentally determined structures available, once you spend the enormous amounts of effort necessary to put a drug through real clinical trials the effort to determine the target structure is pretty much irrelevant.
Of course there are plenty of drugs where we either don't know where they bind or we're probably wrong about where we think they bind. Or they bind at multiple places and some desirable or non-desirable effect are due to binding at places we don't know yet.
There are real uses to having lots of high-quality structure predictions for proteins. Drug development is something that only get limited benefits here. If you want to know how drugs or drug candidates bind to proteins you first create a protein structure with X-ray crystallography. Then you soak your crystals with your drugs or drug candidates and determine even more structures. The interesting part here is not necessarily the overall fold of the protein (which is mostly what AlphaFold gives you) but e.g. a single hydrogen bond to the drug in the active pocket of the target protein. You need really high-quality data if you want to do any kind of rational drug design, most of the time we still just semi-randomly vary structures until they bind better as far as I understand.
Protein structure prediction, at the current levels of precision (and I include AlphaFold here), is not useful for drug discovery.
It’s the sort of thing researchers say to get grants, but as a distant goal, not a practical reality.
For structure-based drug discovery (which isn’t even the majority of drug discovery), the details are what matter (e.g. “does this water molecule mediate a binding interaction, or do the sidechains shuffle a bit, and kick the water out?”), and these methods don’t even come close to predicting detailed interactions.
Metrics in this space are focused on “general correctness” of protein backbone conformation. Success is to achieve a kind of blurry view of the overall shape of the molecule, and drug design is trying to predict specific atomic interactions. They’re two wildly different problems.
About the best you can say is that if we had a generalizable model of physics that could predict protein structure, it might also be able to do a good job of evaluating how a small molecule binds to a protein target. But even that is a huge leap, and when you start using black-box methods like AlphaFold to specifically solve the problem of structure prediction, it’s not really clear that generalization is even possible.
There are potential practical uses in drug discovery for a method that can design a protein which takes a particular shape, but even that is pretty different from
what AlphaFold actually does.
Improved structure prediction is mainly useful in hypothesis generation when doing hypothesis-driven science (IE, you want to confirm that a specific part of a protein plays a functional role in a disease). Its also a nice way to think creatively about your protein of interest.
THe problem is those distilled soundbites get learned by the next generation and they try to apply it. At least I will give AlphaFold/DM credit for correcting their language - originally they claimed AF solved protein folding, but really, it's just a structure predictor, which is an entirely different area. Unfortunately, people basically taught computer scientists that the Anfinsen Dogma was truth. I fell for this for many years.
It can be an aid in drug development, and can perhaps assist a bit in tuning small molecule drugs for more stable binding.
Though I think the major impacts will be two-fold:
(1) The field of structural biology is going to see a change, with much more data available. Some structures of difficult to crystallize proteins will be solved, which may lead to much greater biological understanding. We may enter a time, where once you have a primary sequence, you also have a likely 3d-structure, which will probably change the daily work of quite a few biologists a bit.
(2) Industrial protein design. A tool such as this can potentially have great utility in optimizing proteins as chemical catalysts for various processes in different industries. This includes expanding the conditions under which a protein is active and also making their conformation more stable and so the protein more long-lived in solution.
There's lots of structural information such as conserved folds that can be gleaned from Cryo and X-ray structures. Protein dynamics is an important part but structures published with these mechanisms have been proven biologically relevant by site directed mutagenesis an almost infinite number of times now.
Scientists can verify that an AlphaFold-predicted structure is correct, or at least useful, without being able to get the structure experimentally. For instance, we could use the AlphaFold-predicted structure to do protein-ligand binding calculations for a bunch of known molecules. If these calculations agree with experimental protein-ligand binding (which they generally do for proteins with known structures), then we can say with high confidence that we've got a good structure.
Correct. Protein structures often adopt multiple conformations influenced by the factors you listed. There are things you can do - like molecular dynamics simulations - to study / predict protein conformations in silico. But you can’t do that without a structure.
I don't think it's super valuable to spend time thinking about the computational class protein folding (or structure prediction) is in. It's clear now that approaches that approximate the expensive physics and extended sampling using every bit of additional information available are going to be much more successful in providing data that people need from structures.
As an example, the majority of current drug targets are membrane proteins, of which most are multimers, which makes stuff like this a key part of predicting important protein complexes. Membrane proteins are also notoriously difficult to get structures of which makes it even more interesting.
BTW, I'm not sure how well AlphaFold predicts structures that are part of multimers in the first place? But since they have to be (relatively) stable as a monomer before locking in place, I guess they can be predicted without considering their final part of a complex. Still, feels like some kind of symbiosis between this and the structure prediction itself could exist.
There are many uses for structure. Personally, I find the 3d structures to be useful as a mental guide for picturing things, and certainly people do try to "dock" proteins that have complementary structures, but unfortunately, the biophysics of protein complexes suggests that the conformation change on binding is so large that the predicted structures aren't super-helpful.
Certainly, in a corpo like mine (Genentech/Roche) protein structures have a long history of being used in drug discovery- not typically a simple "dock a ligand to a protein" but more for constructing lab experiments that help elucidate the actual mechanistic biology going on. That is only a tiny part of a much larger process to work on disease targets to come up with effective treatments. Genentech is different from most pharma in that their treatments are themselves typically proteins, rather than small molecules.
reply