• xkforce@lemmy.world
    link
    fedilink
    English
    arrow-up
    85
    ·
    10 months ago

    The article (and what I can access of the paper it is based on) doesn’t really give any details as to what this class is, how it works etc. All the interesting parts about this aren’t mentioned.

    • krellor@kbin.social
      link
      fedilink
      arrow-up
      41
      ·
      10 months ago

      It sounds like they trained a classification model using 39,000 molecules with known reactivity to MRSA. The molecules are vectorized text representations of the structures. Once trained, they can run arbitrary molecules through the model and see which ones are predicted to have antibiotic properties, or at least MRSA reactivity.

      They likely fed in molecules from families of structures that seem likely to contain an antibiotic but are too numerous to manually test them all. They get a prediction of which ones are likely to have the properties they want, and then start the slow process of creating and testing the molecules in the lab.

      • xkforce@lemmy.world
        link
        fedilink
        English
        arrow-up
        16
        ·
        10 months ago

        I get what they did (its been something a lot of groups have been wanting to do for years) but I am curious what molecule specifically they found that worked especially well. i.e What does this thing look like? What is the new antibiotic’s mechanism of action? None of those latter details are discussed. Its something we can only guess at.

        • krellor@kbin.social
          link
          fedilink
          arrow-up
          10
          ·
          10 months ago

          It sounds like they are moving forward with clinical testing in partnership with a bio company, so I’m sure they withheld the information anticipating a patent. The results of this paper was the validation of the explainable AI model which identified candidate classes of compounds.

    • deweydecibel@lemmy.world
      link
      fedilink
      English
      arrow-up
      8
      ·
      10 months ago

      But it’s going to be. Until we do something to stop them, it’s absolutely going to be that way. There’s no serious view of human history that will tell you anything different.

      We can’t just sit here and marvel at technology without acknowledging who controls it, who uses it, and what they’re going to use it for. Without people, AI is just a bunch of code sitting there waiting for input.

      • AllonzeeLV@lemmy.world
        link
        fedilink
        English
        arrow-up
        9
        arrow-down
        2
        ·
        edit-2
        10 months ago

        You’re right, but We’ll get what we deserve when it comes to that.

        The one thing the greedy tech bastardizers have never been able to do is shut down, not for lack of trying, the benevolent open source and human knowledge belongs to the world movements. The seven seas are still free and the most motivated thinkers are still the open source ones, matey.

        They have nothing that isn’t already being extrapolated and tinkered with on private servers. If they use the soon to come AGI to make the peasant’s lives even more bleak, they might not like the damage in kind that can be done with some militant engineer’s homebrew anti-cap AGI. What could that do? Engineer a plague? Mass delete banking records? Who knows but it’s increasingly likely we’ll find out!

        If wealthy “winner” humans continue to insist on making most humans live’s increasingly desperate, solely because they are never getting richer fast enough and without regard to the concept of Mutually assured destruction, then our species will have to experience the inevitable consequences of that choice. They have the capital, so its on them.

        • lad@programming.dev
          link
          fedilink
          English
          arrow-up
          2
          ·
          9 months ago

          We’ll get what we deserve when it comes to that.

          What’s even worse, a lot of people are going to get what just a handful deserve

    • money_loo@lemmy.world
      link
      fedilink
      English
      arrow-up
      19
      arrow-down
      4
      ·
      10 months ago

      It’s just a movie, relax.

      Staphylococcus kills thousands of people every year, this is a good thing.

      We have PLENTY of negative places you could go here on Lemmy that really really hate all things futurism and technology, please try to save your dooomerism for those places, we just literally don’t have many positive spaces left and it’s so frustrating to come from the good news of the article only to see silly comments like yours that make it seem like we are all going to die because AI found a way to help us.

      • thefartographer@lemm.ee
        link
        fedilink
        English
        arrow-up
        6
        arrow-down
        5
        ·
        10 months ago

        Sorry, you seem to have lost the thread. We’re talking about scary things that happen movies, not current daily real-world issues which could really use our focus but we’re to involved in the media.

        Focus on the media, join our ignorant dance.

        • SCB@lemmy.world
          link
          fedilink
          English
          arrow-up
          4
          arrow-down
          1
          ·
          edit-2
          9 months ago

          There is a massively conservative movement lurking in the left, which opposes any new advances and wants people to return to subsistence farming and shit. Same kind of people that argue against having kids to gut the population worldwide

          Those people aren’t even worth arguing with. They’re not the people that will show up to do any work to accomplish policy objectives. They aren’t serious, their objections will never be listened to, and they don’t actually want to make anything better.

          It’s just tradwife-homesteader fantasizing, just with a different economic view and less (but not 0) racism.

    • EdibleFriend@lemmy.world
      link
      fedilink
      English
      arrow-up
      14
      arrow-down
      2
      ·
      10 months ago

      Maybe things will work out for the better. Maybe they take over. Worst case scenario I blow my fucking brains out so i don’t have to live though the apocalypse.

      I’ll roll those dice.

      • AllonzeeLV@lemmy.world
        link
        fedilink
        English
        arrow-up
        8
        arrow-down
        2
        ·
        10 months ago

        Same!

        Either way, It’s main event time and we’re both fortunate enough to have tickets! I’ll even stay for the apocalypse and see how I do, to a point.

      • Dienervent@kbin.social
        link
        fedilink
        arrow-up
        3
        arrow-down
        1
        ·
        10 months ago

        I look at it as the AI we build is humanity’s child. It will outgrow us. And we will age out and die.

        On a cosmic scale, an AI can operate in ways humans never could.

        Even if you use the augmented humans path, eventually, all the human will be augmented out of existence until only the AI is left.

      • AllonzeeLV@lemmy.world
        link
        fedilink
        English
        arrow-up
        8
        ·
        edit-2
        10 months ago

        In this case I’m glad. We are close to achieving the technology to let technology self-iterate and propagate.

        The direction our species chooses to apply this technology will be a reflection and measure of who we are with commensurate rewards and/or consequences.

        Will some voices of sanity let us harness the power of this atom to enlighten the world? Or will we follow tradition and use our newfound power to make big boomie boom rival tribe over there, yet again?

  • KISSmyOS@lemmy.world
    link
    fedilink
    English
    arrow-up
    17
    ·
    9 months ago

    Quick! Produce tons of it and inject them into factory-farm livestock, like we did with all other antibiotics.

  • ChicoSuave@lemmy.world
    link
    fedilink
    English
    arrow-up
    7
    arrow-down
    4
    ·
    10 months ago

    Does this AI use the same process for piecing together things as LLMs do for art and writing? Is this a drug we have known about but not yet applied as an antibiotic or a whole new compound?

    • krellor@kbin.social
      link
      fedilink
      arrow-up
      12
      ·
      10 months ago

      It doesn’t sound like it but they don’t have enough detail in the article to say.

      It sounds likey they are using a classification model that takes a vectorized text representation of molecules and classifies or scores them by their expected properties/reactivity. They took 39,000 molecules with known reactivity to MRSA to train the model, I assume to classify the structures. Once trained they can feed in arbitrary molecules into the trained model and see which ones are predicted to have antibiotic properties, which they can verify with bench work.

      They likely fed in molecules from classes of likely candidate structures, and the model helped focus and direct the wet work.

      I’m not up on the latest, but years ago I helped a similar project using FPGAs running statistical models to direct lab work.

      • Jerkface@lemmy.world
        link
        fedilink
        English
        arrow-up
        4
        ·
        10 months ago

        I’d be interested to know why FPGAs were selected for this application. I’m not especially familiar with their use cases.

        • krellor@kbin.social
          link
          fedilink
          arrow-up
          6
          ·
          10 months ago

          This was years ago before GPU processing really took off, and we wanted the performance, but also, wanted to see if we could develop an affordable discrete lab device that could be placed in labs to aid in computationally directed bench work. So effectively, testing the efficacy of the models and designing ASICs to perform lab tests.

        • 1rre@discuss.tchncs.de
          link
          fedilink
          English
          arrow-up
          1
          ·
          edit-2
          10 months ago

          With a CPU or even a GPU, there is a bunch of inefficiencies for every task as they’re designed to be able to do pretty much anything - your H265 media decoder isn’t going to be doing much when you’re keeping a running sum of the number of a certain type of bond in a list of chemicals

          With ASICs and a lesser extent FPGAs, you can make it so every single transistor is being used at every moment which makes them wildly efficient for doing a single repetitive task, such as running statistical analysis on a huge dataset. This is because rather than being limited by the multiprocessing ability of the CPU or GPU, you can design the “program” to run with as much multiprocessing ability as is possible based on the program, meaning if you stream one input per clock cycle, after a delay you will get one input per clock cycle out, including your update function so long as it’s simple enough (eg moving average, running sum or even just writing to memory)

          This is one specific application of FPGAs (static streaming) but it’s the one that’s relevant here

    • Willy@sh.itjust.works
      link
      fedilink
      English
      arrow-up
      6
      arrow-down
      3
      ·
      10 months ago

      llms have progressed beyond cut and paste way more than a year ago. they have shown understanding of what items are and how they behave and interact. I know it’s popular here to call it a parrot or whatever but most people don’t have access to the high level stuff and most seem afraid/snobby/parroting things themselves.