[HN Gopher] An AI that learns about chemical reactions and desig...
___________________________________________________________________
An AI that learns about chemical reactions and designs a procedure
to make them
Author : geox
Score : 109 points
Date : 2023-12-20 17:32 UTC (5 hours ago)
(HTM) web link (new.nsf.gov)
(TXT) w3m dump (new.nsf.gov)
| 6stringmerc wrote:
| Wait, it works cheaper than Post Docs? I am somewhat serious
| because I am a musician. In Dallas my view is Bench Science is
| woefully underpaid and over performs at an unsustainable dynamic.
| postpawl wrote:
| > I am somewhat serious because I am a musician.
|
| ?
| hiddencost wrote:
| Saying the post docs might have it worse than musicians.
| tejtm wrote:
| musicians/artists are the archetypal poster children for
| intense training with underpaid work. That a musician is
| calling out science work as the same, is notable as the
| musician would have the experience to know.
| ska wrote:
| Typical post-docs may be the worst systemic ratio of pay to
| skills and experience anywhere. Probably related: it's
| otherwise often a pretty amazing gig. Not universal obviously.
| JonChesterfield wrote:
| Copied text from Wikipedia somehow seems different from deriving
| the nobel prize winning process from a dataset that didn't have
| the answer in it.
|
| And downvotes. The article presents this as a magic box capable
| of novel work, and some distance down says it found the answers
| on Wikipedia. Those are different things, whether you're excited
| about LLMs or not.
| Obscurity4340 wrote:
| Can you clarify what you're trying to say, I'm a little slow
| today hehe
| devmor wrote:
| Definitely different things but I suppose "machine that finds
| related prior research for me effortlessly" is still quite
| useful.
| obmelvin wrote:
| Yes, missing prior work at best can impact your review, and
| at worst can mean you waste a significant amount of research
| time
| striking wrote:
| > In less than four minutes, Coscientist had designed an
| accurate procedure for producing the required reactions using
| chemicals provided by the team. When it sought to carry out its
| procedure in the physical world with robots, it made a mistake
| in the code it wrote to control a device that heats and shakes
| liquid samples. Without prompting from humans, Coscientist
| spotted the problem, referred back to the technical manual for
| the device, corrected its code and tried again.
|
| What does it matter that it looked up the reactions on
| Wikipedia? They're building a "coscientist", not an AI-based
| Nobel prize winning researcher.
| Filligree wrote:
| > What does it matter that it looked up the reactions on
| Wikipedia? They're building a "coscientist", not an AI-based
| Nobel prize winning researcher.
|
| Well, quite. This is attempting to automate the boring, time-
| consuming _and dangerous_ part of chemical research.
|
| We should be applauding.
| exit wrote:
| "a magic box capable of novel work"
|
| or a box whose content can be cleanly swapped out with future
| iterations which already demonstrate the potential for novel
| discovery:
|
| https://thenextweb.com/news/deepminds-ai-finds-solution-to-d...
|
| "Researchers claim it is the first time an LLM has made a novel
| scientific discovery"
| riku_iki wrote:
| > "Researchers claim it is the first time an LLM has made a
| novel scientific discovery"
|
| LLM didn't make discovery on its own in that work, it played
| role in one step of unknown importance, other steps were lots
| of manual coding and lots of CPUs to brute force solution.
| teepo wrote:
| I think the point was that the application includes the source
| attribute of the data.
| dylan604 wrote:
| so crediting prior work is the novel thing done by the AI?
| bglazer wrote:
| You should read the actual paper before dismissing it. Fig 6
| and the surrounding discussion shows that their system is able
| to iteratively optimize a reaction by adding steps and changing
| reaction conditions. Based on how poorly the model does on its
| first try, it seems unlikely that it had already just memorized
| the best reaction. So, they show that the model can try things,
| observe results, and try again.
|
| Also their model converts the "wikipedia answer" into steps
| that they run on a robot, which hasn't been done before for
| this specific reaction.
| mym1990 wrote:
| Novel work can often be accomplished by taking two existing
| methods and implementing parts of both, it doesn't have to be a
| eureka moment that stems from nothing. In this case, seeing
| what went wrong in one experiment, seeing what went right in
| another, combining the best of both, and re-implementing...is
| novel work.
| thenerdhead wrote:
| "Consider a future device ... in which an individual stores all
| his books, records, and communications, and which is mechanized
| so that it may be consulted with exceeding speed and flexibility.
| It is an enlarged intimate supplement to his memory."
|
| By Vannevar Bush
| Obscurity4340 wrote:
| The Memex
| KRAKRISMOTT wrote:
| A great idea until Big Brother subpoenas you and decides that
| pleading the fifth does not apply for electronic devices.
| jahewson wrote:
| It doesn't apply to paper documents either. Though it does
| apply to your passcode :)
| mistermann wrote:
| "Say, that's a nice 'democratic' governmental organization
| you have there....would be a real shame if something was to
| happen to it."
| meesles wrote:
| I would assume a device that records data is already fair
| game for evidence by legal means. If you want to get
| technocratic about it, you'd need to start arguing that
| this kind of tool is an extension of your
| mind/consciousness of which you are currently entitled
| privacy to (probably more due to lack of tech than strong
| ethics). But there's no tech the government does not want
| to regulate, so your version is probably right.
| Obscurity4340 wrote:
| Smartphones are basically already "The Memex", didnt really
| expect this would start te current thread aha
| obmelvin wrote:
| Read/discussed "As We May Think" in a grad school HCI class -
| highly recommend it to anyone interested in the history of
| computing.
|
| It is available behind a paywall on The Atlantic website, but
| you can see the original magazine layout here (which is even
| cooler IMO) - https://archive.org/details/as-we-may-think
| mensetmanusman wrote:
| Building 13 @ MIT is named after him.
|
| Cool to think this tech will be there soon :)
| ithkuil wrote:
| I thought we already had that. We humans are never happy with
| the current stuff
| figassis wrote:
| Looking forward to having my own personal Jarvis
| teeray wrote:
| Yeah science! Yeah Mr. GPT!
| mcphage wrote:
| It seems... unlikely, that a LLM built from scraped webpages,
| would be able to predict the results of novel chemical reactions.
| I don't really understand what information in the model's source
| would lead to new insights into chemistry.
| calebkaiser wrote:
| For anyone interested in the applications of ML to chemistry,
| PostEra has been doing some pretty cool stuff in medicinal
| chemistry for the last several years: https://postera.ai/
| mahastore wrote:
| This framework of retrieving information , analyzing it with
| program code as an output , programming machines to do something
| , retrieve information about the output of the machines ,
| analyzing it to see if it matches the expectations and if not
| repeat and rinse until you get the perfect outcome ....
|
| seems useful in general for all kind of AI agents. Is this
| framework open source yet?
| joshuamcginnis wrote:
| This is identical to what I've been building and using my own gpt
| (via ChatGPT) with API integration to automate full genome base-
| calling, assembly, annotation and prediction pipelines. Using
| this approach, me and my team can use it to debug pipeline
| failures, interpret the results, draw inferences and create
| context-dependent experiments. There's no leap in the tech beyond
| GPT facilitating the interaction with APIs, but it is a
| completely new way of working. This is what I can currently do:
|
| User: Show me my genomes
|
| ChatGPT: Here's a list of your genomes ... [API call to GET
| /genomes]
|
| User: Annotate genome #nnnn
|
| ChatGPT: Kicking off annotation [API call to POST /annotate]
|
| User: Show me what genes are related to growth regulation for the
| genome
|
| ChatGPT: The genome appears to have several genes related to
| growth regulation. Here's a list [API call to GET
| /genome/X/annotations] ...
|
| User: Design an experiment to knock-out this gene using CRISPR in
| Aspergillus niger, include the guideRNA specific to this gene.
|
| ChatGPT: Here you go...
| Nesco wrote:
| Really interesting, what would be your real-world use cases?
| joshuamcginnis wrote:
| This is the real-world use-case! We're using to accelerate
| the discovery and elucidation of novel or unknown gene
| function in previously unstudied fungal strains.
| Nesco wrote:
| I should have meant, have you already found customers? I am
| also working on a project on genomics, which is very
| orthogonal to yours, and finding customers in this field
| the difficult part
| joshuamcginnis wrote:
| We're pursuing grant-funded research at the moment. We
| have some hunches on some specific fungal genetic
| functions but they need to be better characterized before
| we think about commercialization.
| ck_one wrote:
| Why do you need ChatGPT for the API calls?
| joshuamcginnis wrote:
| As an example, asking questions like "show me which genes
| from my genome are related to growth regulation" requires an
| API call to give ChatGPT a list of annotated genes from the
| genome we're studying so it can then filter them into growth
| regulation related genes. Leveraging ChatGPT's extensive
| knowledge of genes lets us find new insights into our newly
| assembled genomes much faster.
| candiddevmike wrote:
| Is this doing anything more than using ChatGPT as a frontend? I
| thought based on your comment ChatGPT would run all of that,
| not just call an API that does the actual work.
| joshuamcginnis wrote:
| The parent article isn't doing anything more than using
| ChatGPT as a frontend either. The API does all the _work_
| (pipeline running, robot control, etc) while ChatGPT uses
| it's vast knowledge to interpret, analyze and iterate on
| future commands sent to the API.
| throwawaymaths wrote:
| Oh God this is going to be really bad, there are so so so many
| misannotated genes, even well known ones that have more or less
| "wrong names"[0], that a lot of lazy scientists are going to
| either be led astray or totally miss targets as a result from
| an uncritically science-believing LLM
|
| [0] do you really really think ferritin is _best_ described as
| an "iron carrier"?
| gigel82 wrote:
| I have a friend that works on Azure Quantum Elements and they
| said the Copilot integration is pretty impressive. I imagine
| that's a very specific niche though so likely not interesting if
| you're not into material science or computational chemistry.
| babyshake wrote:
| Is there something along these lines for physics experiments?
___________________________________________________________________
(page generated 2023-12-20 23:01 UTC)