Hacker News Reader

Comment by 41b696ef1113 | Hacker News Reader

I work in pharma, though not related to modelling.

Completely agree with the stance. Protein modelling is one part of the enormous jigsaw that is drug development. Structural biology is already a computational savvy discipline that is accustomed to using available tooling/predictions to enable better decisions with spare/minimal data. Sometimes the predictions are good, sometimes bad, but they are always being reviewed by a human expert. Maybe alpha fold is significantly better than the competition -then it is likely to make solving structures faster.

Hypothetical: the protein structures of all human proteins were solved tomorrow -is human disease cured? No, far from it, there is so much development work that goes beyond knowing the accessible pockets on a protein.

View on HN

Could you elaborate on this a little please? Let's say a computer program was created that could model any protein and any disease perfectly and you could, in an hour or two, take any virus, or disease or whatever, and design a drug that was guaranteed to disrupt it -- or do whatever it is medicines do (I don't know how it all works honestly). Given this, wouldn't it make creating drugs a breeze? Wouldn't that cut down billions on research and testing into drugs that turn out to be failures? If not, what other obstacles does pharma face in creating these drugs?

>that could model any protein

Sure.

>and any disease

Impossible. Modeling a drug's effect on mental illness would require... fully simulating a human brain. Modeling the effect of thalidomide on fetuses would require fully simulating fetal development. That's not happening any time soon.

Doing this would (probably) create a drug which would work well in theory - and possibly in a test tube - but there's no guarantee that it would continue to work when put into the incredibly, vastly more complex environment of the human body.

> design a drug that was guaranteed to disrupt it

If that drug then also kills the patient, it's not much of a medicine.

Sure you can direct an algorithm to optimize for a metric (like curing a disease), but it will be completely ignorant to all other aspects of being (like not having harmful side-effects).

sending drug into cell and let it work is a very different task

The recent porcine kidney transplant, in which a hog did all the computations for you, was done on a patient in a coma. Vascular endothelial growth factor is being tested with CABG procedures. Find someone who needs a hail Mary, and do your best. That will always be faster.

Genes are not the end all be all to medicine let alone biology. There are places where medicine won't go, such as the delicate structures of the brain. Much too unethical. Neurotransmitters fire across synapses. You will always be uncertain of what temperature or charge you need. No way of telling what's really on the inside. And that's with an incomplete model.

You also can't just zap or plunge in medicine. If you are going gene by gene or protein by protein, yet alone cell by cell, how long is that going to take?

Reply on news.ycombinator.com