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

51–60 of 170 posts

Re: Alphafold

#51

Post by dumb1224 »

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 work in cancer research with a drug discovery focus in a lab with some structure biologists. My understanding is that if we identified proteins targets suitable for therapeutics then understand its structure to identify secondary binding sites could be crucial for drug discovery. Drugs can then be designed to modulate its biological functions.

Re: Alphafold

#52

Post by nmca »

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?

NP completeness tells you about the hardest cases, not the most useful cases.

Re: Alphafold

#53

Post by miltondts »

dekhn wrote: post #30
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've worked in bio and drug discovery for some 25 years. That includes building classifiers using gradient descent in the 90s (when algorithms, computers and data were all much worse). I ported DOCK to Linux in ~96 or 97. Since then I built an academic and then industrial career with some emphasis on using computing to solve problems in drug discovery, but I don't play that role any more. It doesn't look like the mod…

> ... but I don't play that role any more.

I was thinking of going into that field. Can you expand a bit on why you left?

Re: Alphafold

#55

Post by timr »

dekhn wrote: post #34
timr wrote: post #26

Earlier quoted context omitted.

> 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.

Most definitely.

Re: Alphafold

#56

Post by dekhn »

miltondts wrote: post #53
dekhn wrote: post #30

Earlier quoted context omitted.

I've worked in bio and drug discovery for some 25 years. That includes building classifiers using gradient descent in the 90s (when algorithms, computers and data were all much worse). I ported DOCK to Linux in ~96 or 97. Since then I built an academic and then industrial career with some emphasis on using computing to solve problems in drug discovery, but I don't play that role any more. It doesn't look like the mod…

> ... but I don't play that role any more. I was thinking of going into that field. Can you expand a bit on why you left?

Because programming computers is far more lucrative, and I'm better at it. However, if I had an unlimited budget I would return to biology.

I spent 15 years trying to be a professor and failed miserably. I was bad at it and didn't like what professors have to do.

I then moved to industry to be a random engineer and thrived doing things entirely unrelated to drug discovery. Eventually, I convinced my company to invest heavily in life sciences. This was successful and I was on track to be a powerful player (a "research engineer", just like the DM folks who are building these things) in this space, when the project got very popular and I was elbowed aside by others who are more aggressive. So I went back to being a programmer again, it's much less stressful, pays better, and realistically, much of my time is just telling scientists what I would do if I was in their place anyway.

"Don't swim with the sharks if you don't like being bitten"

Re: Alphafold

#57

Post by hobofan »

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 would expect that once AlphaFold has helped you identify a potential protein (e.g. as a drug) out of a bigger set of potential proteins, there will still be a manual step of traditional cryoEM, NMR, etc. to get an accurate high-resolution structure.

Re: Alphafold

#58

Post by t_serpico »

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?

To me, the interesting thing is not the specific results but rather that you can accurately predict crystal structures from sequence alone. This begets the question: what other physical biological properties can we predict?

Re: Alphafold

#59

Post by MrsPeaches »

timr wrote: post #23
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…

> A disturbing thing is that the architecture is much less novel than I originally thought it would be, so this shows perhaps one of the major difficulties was having the resources to try different things on a massive set of multiple alignments. This is something an industrial lab like DeepMind excels at. Whereas universities tend to suck at anything that requires a directed effort of more than a handful of people. Y…

> high heat-to-light ratio

Sorry for the ignorance but what does this mean?

Re: Alphafold

#60

Post by Cas9 »

ashtonbaker wrote: post #44
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?

Not really an answer to your question, but is the problem really NP-complete, or just combinatorially difficult? For example how is this condition of NP-completeness satisfied? > it is a problem for which the correctness of each solution can be verified quickly [0] [0] https://en.wikipedia.org/wiki/NP-completeness

According to this answer[0] it seems it's actually NP-Hard, my bad. Haven't seen the proof though, and I'm not an expert.

[0] https://cs.stackexchange.com/questions/128493/is-protein-fol...

Post reply on HN