Today in @NatureNano, we report an all-RNA lipid nanoparticle (LNP) system for efficient in vivo prime editing (PE). We identify bottlenecks in transient prime editor delivery, develop a workflow for LNP optimization, and use it to rescue a mouse model of phenylketonuria. drive.google.com/file/d/1-rP… 1/12

Check out this new @Nature_NPJ study looking at AI-powered and manual assessment of #TumorInfiltratingLymphocytes in early HER2-positive #BreastCancer in NSABP B-41. 🔓pubmed.ncbi.nlm.nih.gov/4213… @IlanaSchlam @khalidated #TILs

Just published @NEJM Marked and durable reduction of LDL cholesterol with one shot PCSK9 gene base editing @skathire nejm.org/doi/full/10.1056/NE…

No Fraser, DeepMind was a total and utter failure at a structural level They sold for $600m to the first US company that asked They should have been the UKs first $1tn company But the follow on investment wasn’t there and the yanks snapped it up for cheap

if you’re an ai researcher you should really consider working on bio pretraining is great: data sets are big enough for interesting stuff but not so big you’re spending all your time on weird cluster optimization post training is in the age of research: the lab is the only true validation, but it’s expensive so figuring out the limits of what we can do for evals in silico is still very open question existing stuff kind of works: we have proof of life for the ability of ai to accelerate bio but there is a long way to go it feels a lot like computer vision after imagenet or nlp after the first transformers started really working if your idea works, you might get to help improve the human condition. way cooler to talk about at parties than “we pushed benchmark X for chat model Y up by 3 point”

yes, and clinical is the bottleneck keytruda only works in 12% of lung cancer, without the biomarker would be toast

Amplify continues to build! We're looking for 1 amazing person to drive our Bio platform effort. Reach out if you: - Are unreasonably excited about AI x Bio - Would build relationships with brilliant scientists, developers, and execs - even if it wasn't your job - Have a talent for building community, content, and connection

You only need to define revenue when you’ve been faking it.

First it was "UK wage growth is too low" 😭 Now "Rich American AI companies are paying our engineers too much and UK unicorns can no longer compete" 😭

110-year-old Turkish grandma shares her secret to a long life: "i never once used Microsoft Teams"

It's now possible to walk from Westminster to the Tower entirely along the north riverbank (only straying a few metres to go beneath bridges). First time in London's history this has been possible. Details on link londonist.substack.com/p/an-…

ImmunoScape is pioneering innovative cancer therapies, and its upcoming clinical trials targeting pancreatic, ovarian, and mesothelioma cancers are highly encouraging. As an investor in @ImmunoScape, I hope to play a small role in helping accelerate their development. #ImmunoScapePartner