What happens when you take two things people are skeptical about – human gene editing and artificial intelligence – and put them together?
A whole lot of concern, for one thing.
A team of researchers at a startup called Profluent says they’ve done just that – used generative AI to edit human DNA.
They claim to have fed huge amounts of biological data into a large language model called OpenCRISPR-1 and come up with new editors based on the gene-editing technique CRISPR.
Their goal with this project is to produce gene editors that are more efficient than even biological mechanisms in allowing organisms to ward off pathogens.
“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.”
The research has not yet been subjected to peer review, but they’ve open-sourced it for others to use.
They also don’t address the fact that gene editing hasn’t moved forward because we currently don’t know whether or not it’s safe and effective. Scientists are concerned about potential side effects, like edited genes triggering instead of fighting cancer.
Profluent VP of gene editing Peter Cameron is plowing ahead, though.
“A watershed moment and the beginning of what we hope will be an iterative process as we embark on this next generation of building genetic medicines.”
They are hoping that, by open-sourcing the editor, other researchers will help them improve the model.
“We encourage the gene editing community to pressure test OpenCRISPR-1. If there are particular features that could be improved for a specific application, we’d like to know and can collaborate to optimize those properties.”
Only time will tell whether this gene editors or others will be the answer to some of humanity’s woes.
This does seem to point to the vast potential, however.
If you enjoyed that story, check out what happened when a guy gave ChatGPT $100 to make as money as possible, and it turned out exactly how you would expect.