vhiremath4

Finding and designing new drugs is a long process, but it is the least cumbersome and expensive part of the process (as opposed to human trials which run on average upwards of 4x as long and cost 10-50x as much as preclinical).

And what we need is not simply more biological phenotypical data (such as genomics, biomarkers, etc.) that we can plug into a model. We actually need that AND labeled trial outcomes, which is a challenge in and of itself because pharma companies will often hide negative trial results (which are advantageous for training the model layer) in order to exacerbate the perception of drugs that make it to market (search for "missing data phenomenon pharma"). The clinical trials are an extremely costly (and necessary) market inefficiency that leads to a bunch of bad behavior that is unfortunately self-reinforcing. I spoke on the phone with a biotech entrepreneur who told me to think of the Gavin Belson (from Silicon Valley the TV show) quote where he says "I don't know about you, but I don't want to live in a world where someone other than me makes the world a better place better than me", and to just remember that's how many people think in pharma and biotech + pharma.

Augmenting how pharma companies work is a great first step. Augmenting how candidate drugs are engineered is a good first step. But that does not change the fact that we simply do not have deterministic governing laws (as we do in physics) to understand the complete pharmacokinetics/dynamics of a drug across a large patient population. You just have to run the test. It is true that AI will help, but only as much as we have a reasonable way to predict that candidate drugs will lead to positive trial outcomes and a large market.

Note that I am not a doomer here. I think AI will have a profoundly disruptive and positive impact on the pharma industry. I'm just not sure starting with drug design alone leads to hope unless there are things happening in the background between pharma + the labs (very possible) that could lead to better trial outcomes.

I have been reading through pharma textbooks written before AI and realized it's so relieving to follow language that has been crafted over multiple editions by humans. When I started to realize how much easier it was for me to read textbooks than the average AI-assisted text, that's when I realized we are truly cooked (at least for this chapter of AI + writing).

Oh damn - really good catch. Thank you. Updated my comment.

There are three mentions of “open source” and none of them mention open source models as a fundamental risk to their business. Interesting.

UPDATE: seems like it is under "open-source" and "open-weight". Woops. Will keep this up simply because I do think the OS (and infra-managed OS services) provided by Chinese labs is a considerable risk to the underlying business, at least with enterprise R&D.

Interesting. Honestly I think about this much more in a cohort way. There’s some cohort of students who are extremely self motivated and mature and understand the way you do one thing is kinda the way you do all things. There’s another cohort that is completely checked out or whose priorities are not grades at all. For these cohorts I don’t think it makes a big different.

But it’s hard for me to imagine that for the cohorts in between (who definitely want to be motivated) having some forcing function is just an easier guiding hand to helping them become responsible vs. completely bombing a class and then potentially losing hope or self identifying as lazy/helpless - which I had seen all too often to some of my smartest classmates.

Regardless not saying this to invalidate your experience. Just hasn’t lined up with mine.

This is quite sad. Even if students would cheat off each other, someone had to do the homework. And even the collaboration of cheating on homework always served as a forcing function for me or others to think about the material. If not actively, at least in the form of a quasi background radiation. With AI that is completely gone, and without reward loops for incremental work, the truth is there is a large number of people (especially 18-20 year olds) who will not do well on the exams because they need a bit of a stick.

I am not saying this as a black and white statement. I just think there are different cohorts of students based on maturity and self motivation and we might be losing out on one cohort that is at neither extreme.

Extremely helpful and thank you for relaying back here!

Thank you! Also, OpenADMET is sick

Is it fair to say the source of the failures is we simply do not understand the complex relationship between the drug design (chemistry, cell therapy, etc.) and the biology (the complete system of the living thing). If we could understand that relationship, we could design better drugs? I know this is very hand-wavy. Probably so much so as to not be a useful thing to say, but I'm just trying to understand.

Can someone explain whether design of protein binders is an important rate-limiting step in drug creation (of which antivenom is a very small market)? Or AI-driven drug discovery in general? It feels like something that will definitely help the drug market but is nowhere near the rate-limiting step, but that's from my own researcher as someone without a background in it.

My understanding is that FDA trials (specifically phase 2 + 3) are the death valley for most drugs and finding a biomarker is something mostly done through a mix of gene bank scraping + looking at old biomarker databanks. The majority of the cost and time is in failed drugs that do not pass FDA trials (which average 6-7 years end-to-end).

Note: I am asking this in earnest. I am not trying to ask a leading question and saying it is not important at all.

Is it explained why, in this drawing, the right catalyst forms at a higher rate than the left? Or put another way why left/right catalyst gets formed at a higher rate than right? I’m trying to understand the why behind the amplification effect.

AI Slop. Will not read.

Reading Psycho-cybernetics to understand teleological goal-oriented mindsets. Reading The Rise of Theodore Roosevelt to remember what America used to stand for.

As someone who has no understanding of how the grid works, this was surprisingly a great first read that sent me down a ton of rabbit holes which have somehow together given me a much better overall idea of how this all works. Love seeing stuff like this on HN!