Claude designed protein binders against scorpion neurotoxins

There’s certainly value in using LLM to search unknown spaces for research of knowledge captured in human text forms, but having done a lot of modeling and simulation in applied sciences over my career, I often wonder for some of these cases how much is just having people interested in various computational sciences, modeling and simulation, and a massive pool of compute to deploy things and approaches to rapidly wire things together on the cheap, sort of like this case.

Claude will just choose similar toolings as everyone. Orchestration is a really nice tool to have and this can definitely empower non-technical bench biologists. But the bottleneck isn't using the tools or even intelligence in this field. It's data generation and ontology. There needs to be more hardware automation and good data/record keeping in biology. With the exception of high-throughput sequencing and some other more niche quantitative methods, I feel like molecular biology is still at similar data throughput of Mendel's pea experiments.

I guess if you want good health care at an affordable cost you should have gone to Mexico where the anti-venom that is $10,000 a vial in the US is sold (by the same company) for $100 a vial.

> but apparently now it is so expensive

They saw Shkreli hike prices 100x and decided that was the business model for them. Same thing has happened with rabies.

Vision involvement should have qualified your son for antivenom. Sounds like good ol' US healthcare fuck up, again. Every time.

Unfortunately, available does not mean cheap these days. Parents (good ones anyway) would go into a decade of debt to prevent their child from having an experience like you just described. Drug giants see that as a business opportunity.

This might be a job for fentanyl. Carefully monitored in a hospital setting of course.

My understanding is it is not - this is something we have models for, and there was a flurry of machine learning based drug discovery companies about 8-10 years ago. But they ran into the testing bottleneck real fast because they would spit out thousands of candidates for binders and so on that all needed to be tested in vitro before they could even start the real drug dev circuit. Furthermore the drugs need to be manufacturable and that's not a trivial problem.

It's nice to (as the blog post suggests) give the opportunity to non medical experts, say in this case a snake/venom research center, to pursue a problem and produce some realistic candidates that they could pay to test. I do think it's good to democratize what parts of the process can be, but it's more of a resource prioritization problem than a molecular design one.

Have a comment below on this, but generally things don't work out in the clinic because we didn't understand the biology adequately, and not because we didn't have a molecule.

A better binder only helps if you know what to bind to and that if you bind to it, you'll have the desired effect.

This is why the industry has crowded around a very limited set of "validated" targets. It's because we know if we do something with them, they will work. Obviously we're likely missing a lot of great ideas though.

AI might help find some of those ideas, but we won't know until someone tests them in a human. Essentially, without more extremely expensive and difficult data to acquire, it's not likely to be that much better at picking winners.

I'm in the sector and I believe strongly in AI helping (I've bet my entire career on it). It will get there eventually, but it will take much longer than people seem to think at the big labs.

On crowding in big pharma: https://www.lek.com/insights/life-sciences-pharma/biopharma-...

While Clinical Trials are the most expensive step and have a 90% failure rate, it is not the *source* of the failures, it's just where failures are revealed.

Much of whether or not a candidate drug will succeed was determined all the way back in the design/discovery stage. If we can design better drugs, then we would enjoy a higher probability of success in the later clinical trials.

The single biggest improvement to pharma drug development would be from increasing the probability of success in clinical trials.

Disclaimer: I did not work in protein design but in biophysics. However some of my collaborators did.

It definitely is a small help. Although the lab I was working with had supercalculators to generate microtubule-binding proteins, They were kind of limited in how many they could simulate and try, so being able to go through 318K molecules is useful. Our lab was then tasked with doing the testing (I designed the automated assay) and this part is going on right now, I expect it to last around a year (small lab, many tests to run).

Once potential medical targets have been found, the actual work takes several years as you have mentionned as you would switch to cell cultures, then animal models, then human trials. That matches the 6-7 years timeline you mentionned.

So overall, you can crunch a ~6-months period into 1 month, which is definitely a time saver.

The impression I have, which admittedly is purely as a layman reading articles, is that by far the rate-limiting factor in all drug creation is the cost of doing clinical trials in humans.

Protein binders (as in, small proteins like the one in the article that themselves bind other proteins) aren't a rate-limiting step, but also are fairly restricted in their applications as therapeutics. Designing small-molecule ligands is much more challenging, and AI/ML design tools for small molecules are much less effective for a number of reasons, including 1) existing training data are sparse the search space for small molecules is arguably much larger and more complex than for proteins 2) the evolutionary data that powers protein structure prediction and design don't exist for small molecules. So it is still non-trivial to design a small-molecule binder for a protein.

It's true that clinical trials are a big cost center for drug development, but there is an argument for mitigating failure here earlier in the process through better technology development. Some of this will come from AI and some of it from better experimental methods for probing biology. One of my favorite efforts in this area is OpenADMET, which combines ML and experimental methods for addressing tox-related issues in drug discovery, which are common causes for failure in the later (more expensive) clinical trial stages:

https://www.nature.com/articles/s41467-026-73410-8 https://openadmet.org

Your impression is correct. Clinical trials are the rate limiting step and the primary source of cost and risk.

There would be less failures if problematic therapies were filtered out before the clinical stage.

Both "yes" and "no". AI has been doing great in protein structure prediction.

It's a task that is well suited for the current generation of AIs, (most) proteins consist of a constrained "alphabet" of components, and the alphabet then forms recognizable shapes ("motifs"). So working backwards and generating a protein that binds with another protein is the logical next step.

The problem is in the efficacy. Monoclonal antibodies work surprisingly poorly as antivenoms. They are too specific, and real venom is a mix of multiple kinds of proteins with a lot of variation. Which makes sense, as venoms are under high selective pressure, so there's going to be a lot of genetic variability within a single species (never mind _across_ species).

Snake antivenoms are a major underserved area with a decent amount of research. But so far the century-old method of producing antivenoms (injecting horses and then collecting their blood plasma) is the best one.

my general question with any drug isn't its effectiveness. It is what are the side effects? Unless somehow AI is solving this without clinical trials, there isn't much of note here

it is a rate-limiting step.

previously you'd inject a rabbit or other small mammal with what wanted antibodies to bind against, plus an adjuvant compound

then you'd need to screen the antibodies and figure out what they do. some antibodies will bind to your target but not neutralize it, so have to rule those out.

then I think you'd have to do amino acid sequencing on it I think and then clone the sequence in some B-cells to produce it.

there's probably a way better approach than what I just said but it's usually still going to start with stabbing an animal with your target.

They're trying to catch up to OpenAI which has been doing these a lot, but I agree, can we actually get them peer reviewed as a hard requirement? I think OpenAI would have some looked over by experts before posting their blog posts.

[dead]

It doesn't take a genius to realize that you should let anonymous randoms do bio "research" on your API. I'm glad they prevent this unless you are partnered with a university, tbh.

Yes, they _hope_ they can verify that the outcome of giving someone they trust a gun will not end in the end of the world.

I wouldn't trust you with a gun of mine... I don't know you.

it's just you, it looks good on my computer, next time check on internet archive instead of asking DIY