X-ray people might be impacted more than NMR and cryo-EM people by AF2. It may replace all biophysical techniques for structural determination someday, IMHO, they advertise much better than academic groups for the things they've achieved and still a long way to go (like when Rosetta first introduced). Not to mention the missing pieces like non-natural amino acids, binding partners, dynamics, different circumstances in the cell, more or less scientists would like to validate the prediction experimentally. However, it is hard to argue with its valuable inputs and insights before wet bench works that cost a lot.

Hey John,

Great insight. In my opinion with this big achievement in the field, we're enable to not only better understand the function of proteins, but also able to address some follow up questions which have direct implications on the drug development such as effect of point mutations on the function/structure of the proteins.

The next interesting field which will be impacted substantially is micro biology, where we have a lot of sequencing data without any structures.

Further, I assume with current attention on targeting RNA directly, there is a need to develop similar method which can predict the structure of RNA.

X-ray people might be impacted more than NMR and cryo-EM people by AF2. It may replace all biophysical techniques for structural determination someday, IMHO, they advertise much better than academic groups for the things they've achieved and still a long way to go (like when Rosetta first introduced). Not to mention the missing pieces like non-natural amino acids, binding partners, dynamics, different circumstances in the cell, more or less scientists would like to validate the prediction experimentally. However, it is hard to argue with its valuable inputs and insights before wet bench works that cost a lot.

It will be useful, but lets remember back when "lock and key" structural studies were supposed to drive all small molecule drug development. That never happened as screening is still the preferred method, although structural data can help to fine tune drug candidates found in screens. Traditional structural studies will still be needed to score the AI accuracy, but its not going to be leading the parade anymore. Progress is grand; its best to focus on big questions and don't get wedded to any one technique IME!

John,

I do not exactly understand why you asked a very similar question twice. In both cases the question introduces more confusion then the answers. Let me reiterate what I stated in the latest post. So in summary the impact will be much much smaller than you suggest.

You have asked an interesting question. For a senior member of structural biology community it shows the yearning for practical solutions as well as naivety of the real difficulties in even defining the problem. The protein folding problem is an ill-defined and most likely unsolvable problem in its classic sense of axiomatic reductionist sciences. If the old Anfinsen view was true about the minimum of global free energy there never would be life on Earth or anywhere else. The new paradigm that I partially formulated is that every protein (as a matter of fact every macromolecule of life) has its own specific recipe how to combine the structural with dynamical features to accomplish the desired function (PNAS 106(2009)10505). It means that there is a unique proportion of conditionally stable structure to conditionally unstable elements to perform given function. This ill defined condition is not solvable by classic axioms but it just might be partially solvable by fuzzy methods such as AI. Why AI is so good? Because the protein folding problem is a practical not a theoretical problem. Depending on conditions and their possible changes the protein suppose to perform a certain function. This is what physics call "self organized criticality". This is far from equivalency of having a certain structure nor a possible unique binding site nor anything that remotely can be called a solution. AI just simply captures better the set of heuristic rules than other methods particularly dynamical coupling with solvent. There are millions of examples to support this view. If anybody wants to engage I will be happy to, but not now. There is no place here to mention even a single one. So the only hope is that we found an effective heuristic tool that gives us better approximation to reality. To be properly tested the method needs to be exposed to finding bordering cases when it breaks down. What conditions produce divergencies. What percentages of certain structures are folded and are not. For instance only around 30% of genomes of higher eukaryotes are properly folded. Around 30% is conditionally folded (on the target, in the particular compartment) since the misfolding diseases. And finally around 30% is almost never folded with residual presence of folding nuclei that precipitate the function. So all these classes of proteins must be tested against this new AI approach to see when the rules break down and how to enhance them. Therefore, it is not a breakthrough that John is so excited about. But it is definitely progress. But, I would not see anytime in the future, abolishing or significant diminished importance of any particular field of science, in exactly the same way as radio did not get extinct by TV. Bog