My goodness, this is a TERRIFIC piece of writing. The coming epidemics, by Ed Yong is not here in the The Atlantic theatlantic.com/magazine/archi…

Frontiers in Medicine, a new monthly review series authored by leading experts, highlights technological advances at the intersection of science and medicine. The first in the series reviews CAR T-cell therapy. Read now: nej.md/2tPkmBW

Sharing our "Year In Review": Annual Talk On Macro, Biotech, and Atlas. A data-rich, whirlwind tour thru a bunch of pharma and biotech topics over about 45 min. Cheat sheet with timestamps included. lifescivc.com/2019/02/our-ye…

We trained a genomic language model on all observed evolution, which we are calling Evo 2. The model achieves an unprecedented breadth in capabilities, enabling prediction and design tasks from molecular to genome scale and across all three domains of life.

Incredible engineering work to design a polymerase that handles X-NTPs 50X the size of regular nucleotides. Curious if/how the polymerase might be tweaked to accommodate a 5th X-NTP for capturing methylation data.

Awesome! Can lab-in-the-loop also accelerate small molecule design or will players like Isomorphic Labs have the edge in that space? endpts.com/isomorphic-lab…

Just finished module 1 on AI-assisted data analysis and was amazed by rolv.io. Made it incredibly easy to visualize gene expression heatmaps and apply ML to methylation data. Thanks Altuna Akalin and team!

Will we see large-scale DNA synthesis automation with models like Evo2 as one design step in an elaborate DBTL cycle? Can the build/test steps be fast enough and cheap enough for whole genome applications?

Thanks for sharing. It’s nice to see this being covered for a broader audience. For anyone interested in learning more, I highly recommend The Code Breaker by Walter Isaacson.

1/🚨WOW! Beam Therapeutics presented promising data from its Phase 1/2 trial of $BEAM-302 in Alpha-1 Antitrypsin Deficiency-AATD, demonstrating the first ever effective clinical genetic correction of a disease-causing mutation & clinical proof-of-concept for in vivo Base Editing $XBI 🧵👇

The paradigm shift from "cancer as a disease of the genome” to “cancer as a disease of the multi-ome” is clearly underway. Thanks again bora Altuna Akalin for the great crash course on using #DeepLearning techniques to integrate multi-omics data with flexynesis.

Great educational and entertaining conversation on the classic trio of tariffs, the Democratic Party, and AI.

Thirteen years ago, my administration acted to protect young people who were American in every single way but one: on paper.  DACA was an example of how we can be a nation of immigrants and a nation of laws. And it’s an example worth remembering today, when families with similar

It is no secret that I have profound disagreements with Zohran Mamdani. But every Democrat — and every decent person — should speak out with moral clarity against the despicable Islamophobic attacks that have been directed at him. Demanding the deportation of an American citizen

Wild that we have elected public officials who are this openly racist.

Nice to see one of my favorite Paul Graham essays referenced while reading “Range” by David Epstein: “…don't commit to anything in the future, but just look at the options available now, and choose those that will give you the most promising range of options afterward.”

If you have been following the GPT-5 rollout, one thing you might be noticing is how much of an attachment some people have to specific AI models. It feels different and stronger than the kinds of attachment people have had to previous kinds of technology (and so suddenly

My second "On Medicine" column for the New York Times (might be a tough read for some) mobile.nytimes.com/2017/10/24/mag…

Today on NPR. "Certain And Confident: Predicting The Future In A Climate-Changing World." I read the big climate report so you don't have to! And you know what? It's an awesome lesson in how science works! npr.org/sections/13.7/…