Want to read Slashdot from your mobile device? Point it at m.slashdot.org and keep reading!

 



Forgot your password?
typodupeerror
×
AI Biotech

Generative AI Arrives In the Gene Editing World of CRISPR (nytimes.com) 22

An anonymous reader quotes a report from the New York Times: Generative A.I. technologies can write poetry and computer programs or create images of teddy bears and videos of cartoon characters that look like something from a Hollywood movie. Now, new A.I. technology is generating blueprints for microscopic biological mechanisms that can edit your DNA, pointing to a future when scientists can battle illness and diseases with even greater precision and speed than they can today. Described in a research paper published on Monday by a Berkeley, Calif., startup called Profluent, the technology is based on the same methods that drive ChatGPT, the online chatbot that launched the A.I. boom after its release in 2022. The company is expected to present the paper next month at the annual meeting of the American Society of Gene and Cell Therapy. "Its OpenCRISPR-1 protein is built on a similar structure as the fabled CRISPR-Cas9 DNA snipper, but with hundreds of mutations that help reduce its off-target effects by 95%," reports Fierce Biotech, citing the company's preprint manuscript published on BioRxiv. "Profluent said it can be employed as a 'drop-in replacement' in any experiment calling for a Cas9-like molecule."

While Profluent will keep its LLM generators private, the startup says it will open-source the products of this initiative. "Attempting to edit human DNA with an AI-designed biological system was a scientific moonshot," Profluent co-founder and CEO Ali Madani, Ph.D., said in a statement. "Our success points to a future where AI precisely designs what is needed to create a range of bespoke cures for disease. To spur innovation and democratization in gene editing, with the goal of pulling this future forward, we are open-sourcing the products of this initiative."
This discussion has been archived. No new comments can be posted.

Generative AI Arrives In the Gene Editing World of CRISPR

Comments Filter:
  • I've seen some good headlines (CRISPR helping cure Sickle Cell Anemia, I think) and some bad ones implying it'll cause cancer some significant portion of the times it's used. I'm still waiting for the "turn your eyes violet" kinda CRISPR mods we were "promised".
    • I'm not *too* worried about the cancer thing. By huge margin, the majority of gene errors either do nothing or worst case kill the cell (Cells have some fairly robust mechanisms to detect errors and suicide the cell if it detects them to protect the organism). Thats not to say its impossible, and some mechanisms are more dangerous to tamper with than others (especially around ageing. Ageing is in some respect a function of the body protecting our genes from cancers. google "hayflick limit".) but I suspect a

      • The threat of any of an offtarget gene edit causing cancer is highly unlikely, but possible. The FDA in Dec.2023, for the first time, approved infusion with CRISPR edited cells as a treatment for sickle cell anemia. The way that works is .. they take some of your blood .. select certain type of stem cells, modify them, and then put them back in you. The reason that approach is safer is because we can check copies of the edited cells to make sure they haven't gotten potentially cancerous mutations. However,

    • Would be nice to ride around with violet eyes in my fusion powered flying car.

    • by gweihir ( 88907 )

      Oh, definitely. CRISPR is not safe to use until we have mastered cancer treatment. The only applications now are really bad medical problems, were the cancer risk is acceptable.

      • So you're an expert in genetics, oncology AND artificial intelligence!

        We /. luddites bask in the glory of your continuous stream of insightful comments backed by thorough reasoning!

        --
        The internet reveals stupidity in people.

        • by gweihir ( 88907 )

          No, but I can read. You should try it some time. It is not even that hard, to you may be able to master that skill!

          • No, but I can read

            Then once in a while read the comment you're responding to. Try to write something that makes sense. You sound like a regurgitating parrot!

    • I've seen some good headlines (CRISPR helping cure Sickle Cell Anemia, I think) and some bad ones implying it'll cause cancer some significant portion of the times it's used.

      To be clear, this is FUD.

      No matter what your cousin's friend overheard somebody in the know talking about down at the bar.... It is a theoretical possibility, but it is not a practical concern.

      • P53, called the guardian of the genome, is activated upon CRISPR-Cas9 edits. This causes DNA damage response genes to be activated and cell to either fix the damage or apoptosis. Cells remaining are ones with dysfunctional P53, which could lead to cancer as mutated P53 is found in approximately half of cancers. Authors are even hypothesizing that CRISPR-Cas9 method of action may be silencing of genes due to p53 activation.

        CRISPR-Edited Cells Linked to Cancer Risk in 2 Studies

        June 12, 2018 - Editing cells’ genomes with CRISPR-Cas9 might increase the risk that the altered cells, intended to treat disease, will trigger cancer, two studies published on Monday warn—a potential game-changer for the companies developing CRISPR-based therapies.

        In the studies, published in Nature Medicine, scientists found that cells whose genomes are successfully edited by CRISPR-Cas9 have the potential to seed tumors inside a patient. That could make some CRISPR’d cells ticking time bombs, according to researchers from Sweden’s Karolinska Institute and, separately, Novartis.

        CRISPR has already dodged two potentially fatal bullets—a 2017 claim that it causes sky-high numbers of off-target effects was retracted in March, and a report of human immunity to Cas9 was largely shrugged off as solvable. But experts are taking the cancer-risk finding seriously. On supporting science journalism

        If you're enjoying this article, consider supporting our award-winning journalism by subscribing. By purchasing a subscription you are helping to ensure the future of impactful stories about the discoveries and ideas shaping our world today.

        The CEO of CRISPR Therapeutics, Sam Kulkarni, told STAT the results are “plausible.” Although they likely apply to only one of the ways that CRISPR edits genomes (replacing disease-causing DNA with healthy versions) and not the other (just excising DNA), he said, “it’s something we need to pay attention to, especially as CRISPR expands to more diseases. We need to do the work and make sure edited cells returned to patients don’t become cancerous.”

        Another leading CRISPR scientist, who asked not to be named because of involvement with genome-editing companies, called the new data “pretty striking,” and raised concerns that a potential fatal flaw in some uses of CRISPR had “been missed.”

        On the other hand, the Novartis paper has been available in preliminary form since last summer, and CRISPR experts “haven’t freaked out,” said Erik Sontheimer of the University of Massachusetts Medical School, whose CRISPR research centers on novel enzymes and off-target effects. “This is something that bears paying attention to, but I don’t think it’s a deal-breaker” for CRISPR therapies.

        The Karolinska and Novartis groups tested CRISPR on different kinds of human cells—retinal cells and pluripotent stem cells, respectively. But they found essentially the same phenomenon. Standard CRISPR-Cas9 works by cutting both strands of the DNA double helix. That injury causes a cell to activate a biochemical first-aid kit orchestrated by a gene called p53, which either mends the DNA break or makes the cell self-destruct.

        Whichever action p53 takes, the consequence is the same: CRISPR doesn’t work, either because the genome edit is stitched up or the cell is dead. (The Novartis team calculated that p53 reduces CRISPR efficiency in pluripotent stem cells seventeenfold.) That might explain something found over and over: CRISPR is woefully inefficient, with only a small minority of cells into which CRISPR is introduced, usually by a virus, actually having their genomes edited as intended.

        “We found that cutting the genome with CRISPR-Cas9 induced the activation of p53,” said Emma Haapaniemi, the lead author of the Karolinska study. That “makes editing much more difficult.”

        The flip side of p53 repairing CRISPR edits, or killing cells that accept the edits, is that cells that survive with the edits do so precisely because they have a dysfunctional p53 and therefore lack this fix-it-or-kill-it mechanism.

        CRISPR edits genomes in either of two ways. It slices out a chunk of disease-causing DNA, in a process called non-homologous end joining (NHEJ), or gene disruption. That’s how CRISPR Therapeutics is going after sickle cell disease. Alternatively, CRISPR both cuts out a disease-causing stretch of DNA and replaces it with healthy nucleotides, in homology-directed repair (HDR), or gene correction. Several university labs are investigating HDR to treat Duchenne muscular dystrophy, among many other diseases.

        In the normal, mature cells she and her team studied, Haapaniemi said, gene disruption “can happen even when p53 is activated.”

        https://www.scientificamerican... [scientificamerican.com]

  • by dpille ( 547949 ) on Wednesday April 24, 2024 @02:54AM (#64420120)
    To spur innovation and democratization in gene editing, with the goal of pulling this future forward, we are open-sourcing the products of this initiative.

    Because the products of this initiative cannot be covered by any patent, by virtue of their "invention" by an AI, we're going to use the phrase "open source" a lot to try to fool you into thinking we've done something deliberately altruistic.
  • by Big Boss ( 7354 )

    Now we can make actual people with screwed up hands and other appendages! Maybe make an AI that can make real looking photos before we mess with genetic data.

    To be fair, there are a lot of possible good applications, and this seems to at least partly be about finding sequences to attach to, which could be very useful for research. From a layman perspective anyway. I am not a genetic scientist.

  • "videos of cartoon characters that look like something from a Hollywood movie. "

    Now they can produce humans that look like something from a Hollywood movie.

Hackers are just a migratory lifeform with a tropism for computers.

Working...