Using AI to improve a challenging reaction in medicinal chemistry

Posted by ilreb 7 hours ago

Counter50Comment17OpenOriginal

Comments

Comment by refurb 6 hours ago

As a former chemist, what's old is new again!

It's basically high through put screening plus an AI engine to map out the "variable space".

Back in 1990 when robotics became more reliable we did the same thing. The only difference is a trained chemist would determine what variables would be altered.

It's not that hard to do, it doesn't take that much brain power, just an understanding of what variables may impact the yield. Claiming AI can now do this isn't all that impressive.

Comment by AnodicElegy 4 hours ago

Yeah, it's hard to see exactly what was gained here versus standard, machine-learning-based high-throughput experimentation.

Comment by readthenotes1 5 hours ago

Without knowing the comparative cost is hard to know how impressive it is.

It could be as unimpressive as motorcycling across the USA in 33 hours vs 7 days

Comment by malchow 7 hours ago

Well-run autolabs recursively training discipline-specific models are becoming very valuable assets. I write more about this here:

https://x.com/jmalchow/status/2067298271647904061

Comment by wasabi991011 7 hours ago

Is there a way to read this without a Twitter account?

Comment by malchow 6 hours ago

https://www.linkedin.com/pulse/bicycle-joseph-malchow-liv9c/

Comment by wasabi991011 4 hours ago

Thanks

Comment by WithinReason 6 hours ago

https://xcancel.com/OpenAI/status/2067293746556027376

GPT-5.4 reviewed scientific literature, generated and ranked research proposals, helped design experiments, analyzed results, and proposed follow-up studies.

Human chemists steered the work, selected proposals for testing, and validated the final result.

Maria [AI] tested the idea across 10,080 reactions, and human chemists later validated representative results by hand.

Under the optimized conditions, yields improved for 88% of the boronic acids and 83% of the sulfonamides tested.

Human chemists then repeated 14 representative reactions by hand: 11 showed higher yields, including 8 with a more than twofold improvement.

The full process took about 2.5 months, plus another half month for human chemists to write up the results.

Comment by wasabi991011 4 hours ago

Thanks, but this wasn't the link I was referring to

Comment by 6 hours ago

Comment by CamperBob2 3 hours ago

It kills me how many scientific researchers in various fields still rely on X. Every time they post or read a tweet, they are subsidizing the guy who wants more than anything else -- having already gained everything else -- to put them out of a job.

Comment by FigurativeVoid 6 hours ago

It looks like xcancel doesn't support articles yet. There may be another service?

Comment by 5 hours ago

Comment by gnabgib 6 hours ago

No such thing as an AI chemist (a chemist being someone who has a degree in chemistry or related), oh that's not even the title. Near-autonomous AI chemist improves challenging reaction in medicinal chemistry

Comment by cml123 6 hours ago

I also had a strong reaction to the title from their research blog; too anthropomorphic. Model, agent, or system don't have the same personification.

Comment by AnodicElegy 4 hours ago

Anthropic did the same thing recently:

https://www.anthropic.com/research/making-claude-a-chemist

I don't know why they think this is okay, any more than it would be to call their models "AI doctors" or "AI lawyers".

Ironically, where I live, most actual medicinal chemists are not allowed to call themselves chemists since you have to pay dues to a professional association to use that title.

Comment by readthenotes1 6 hours ago

I noticed the Wikipedia article so that it was a "graduated scientist" (outside of UK).

It made me wonder what other professions require an associate's degree or better to be able to claim the profession without some sort of modifier, such as licensed physician, or Master plumber...

Comment by Xmd5a 6 hours ago

are you a chemist?

Comment by IAmBroom 6 hours ago

That has no bearing. I am not a Medical Doctor, but I know that AI cannot be an MD.

Comment by ath3nd 4 hours ago

[dead]