Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

Alphafold

github.com

Post reply on HN
Print view View original

31–40 of 170 posts

Re: Alphafold

#31

Post by dekhn »

rllearneratwork wrote: post #27
COGlory wrote: post #24

I am a structural biologist. This is one of the handful of topics that overlaps with my field here. I'm very excited to play with this, although it might eventually put me out of a job.

why would it put you out of job? Wouldn't it just become one of the tools you use?

It would both become a tool he used (to produce initial structures to fit in density maps) and a tool that used his or her output (because alphafold requires known protein structures that are homologous to the one you're predicting).

Re: Alphafold

#32

Post by Cas9 »

Honest question: since AlphaFold doesn't really _solve_ the protein folding problem (it's NP-complete after all), but only _approximates_ solutions very well, what are the real impacts of this? Isn't a good approximation of a protein enough to cause unexpected problems? How do we know that an approximate structure will perform the same as the correct solution?

Re: Alphafold

#33

Post by dekhn »

aantix wrote: post #25
dekhn wrote: post #21

Earlier quoted context omitted.

Yes, all science should be communicated in the form of an academic paper wiht a supporting git repo and quickly downloadable dataset and a fast path to reproducing the work. That would be a huge change from the establishment. It's quite unclear what value this will have to pharma; personally I doubt this has any direct applications (and I'm one of the few people in the world that can say that with deep authority).

Who benefits from this work?

Primarily the community that previously depended on homology models.

Re: Alphafold

#34

Post by dekhn »

timr wrote: post #26
gonehome wrote: post #17

Does anyone on HN work in bio or drug discovery? Could you give an overview of how people can leverage this (or how you might?). From reading around about it, it sounds like there's often a need to find a certain type of molecule to activate/inhibit another based on shape and the ability to programmatically solve for this makes the searching way easier. Is this too oversimplified/wrong? How will this be used in pract…

> Could you give an overview of how people can leverage this (or how you might?). Short answer: nobody knows. Traditionally, protein folding is a solution in search of a problem, but that's largely because the predictions were...unusably bad. This was always more of a super-difficult validation problem for the force fields and simulation methods, which could then be used for other problems of greater value (such as r…

Also I would say that really they just made improvements to protein structure prediction, not protein folding which is the dynamic process by which proteins reach their equilibrium fold.

Re: Alphafold

#35

Post by dekhn »

nextos wrote: post #16

Alphafold 2 is very very cool, but we need a little dose of reality. It's still a bit away from really solving protein folding as it was marketed. For example, multi-complex proteins are not well predicted yet and these are really important in many biological processes and drug design: https://occamstypewriter.org/scurry/2020/12/02/no-deepmind-h... A disturbing thing is that the architecture is much less novel than I…

many of these resources are available, it's mostly that academic scientists don't have the time, money, or expertise to manage large datasets. However, the community has maintained high quality MSA database for decades and that's exactly the work that DM drafted off.

Re: Alphafold

#36

Post by nick238 »

gonehome wrote: post #17

Does anyone on HN work in bio or drug discovery? Could you give an overview of how people can leverage this (or how you might?). From reading around about it, it sounds like there's often a need to find a certain type of molecule to activate/inhibit another based on shape and the ability to programmatically solve for this makes the searching way easier. Is this too oversimplified/wrong? How will this be used in pract…

I haven't worked on the drug-side of things, but here my bio perspective: It's kind of out-of-vogue, but consider the "lock and key" model of proteins and small molecules (drugs). For drug design, what you want to do is get a key that fits just one lock (to pull whatever lever) and not others (to avoid side-effects). It's relatively easy to find a molecule that fits a protein, because that protein is what you might spend years researching and probing, but it's tricky to check if it does anything against ~100,000 others in humans. If you could do an in silico computational survey to be like, oh, maybe it'll target this accidentally, you could spot-check those in vitro, and/or stick on some other atoms to your small-molecule to make it not fit that off-target.

Holy grail, IMO, though is being able to design de novo protein sequences (to make "biologics", aka engineered protein drugs) that can a) target (bind/block/enhance) or do (chemical reactions) what you want and only that, b) are easily synthesizeable by bacteria/yeast (cheap to make), and c) are stable (easy to transport/store).

Re: Alphafold

#37

Post by whimsicalism »

Cas9 wrote: post #32

Honest question: since AlphaFold doesn't really _solve_ the protein folding problem (it's NP-complete after all), but only _approximates_ solutions very well, what are the real impacts of this? Isn't a good approximation of a protein enough to cause unexpected problems? How do we know that an approximate structure will perform the same as the correct solution?

You want to find a protein that has X structure (since structure determines function to a degree).

If AlphaFold is substantially more accurate at solving proteins, it can mean that drug discovery is faster, assays are faster, etc. etc.

The "unexpected problems" would be caught in the assay stage.

Re: Alphafold

#38

Post by Cas9 »

Honest question: since AlphaFold doesn't really _solve_ the protein folding problem (it's NP-complete after all), but only _approximates_ solutions very well, what are the real impacts of this? Isn't a good approximation of a protein enough to cause unexpected problems? How do we know that an approximate structure will perform the same as the correct solution?

Re: Alphafold

#39

Post by dekhn »

Cas9 wrote: post #32

Honest question: since AlphaFold doesn't really _solve_ the protein folding problem (it's NP-complete after all), but only _approximates_ solutions very well, what are the real impacts of this? Isn't a good approximation of a protein enough to cause unexpected problems? How do we know that an approximate structure will perform the same as the correct solution?

The protein folding problem is not NP complete. The "formal" protein folding problem, as posed (find the set of dihedral angles whose resulting structure has the lowest energy) might be, but that bears only a distant resemblance to how people "solve" the problem today. At the very least, the statement is incorrect because many proteins don't actually fold to their energy minimum, they get stuck in kinetic traps, and the formal PF defintion never accomodated that idea.

Re: Alphafold

#40

Post by bawolff »

Cas9 wrote: post #32

Honest question: since AlphaFold doesn't really _solve_ the protein folding problem (it's NP-complete after all), but only _approximates_ solutions very well, what are the real impacts of this? Isn't a good approximation of a protein enough to cause unexpected problems? How do we know that an approximate structure will perform the same as the correct solution?

I dont know much about protein folding, but for most things in life,exact solutions to NPC problems usually aren't needed for non-contrived problems. In many cases, approximations are good enough.

Besides, this is real life - if predictions and real life match, that's great. If they don't, well you know you went wrong somewhere.

Post reply on HN