ICYMI, @ImranSHaque just finished up a tweetorial on our recent work @RecursionPharma investigating a widespread source of systematic #confounding in #CRISPR-Cas9 screens we dub "proximity bias." Digging in w/ my colleagues has been an awesome experience + opportunity!

Viral persistence is one of the leading hypotheses on what causes #LongCovid. Over the years we've done a lot of work to highlight, support, & grow this line of research. Some of this work: 1/

Get an early look at the power of our groundbreaking #phenomics foundation model! With results up to 28% better than prior models, our work demonstrates scaling properties apply in biology: larger models & more training data = superior performance. Stay tuned for future papers

I am so excited to partner with the team @nvidia to further accelerate our pioneering work in AI leveraging their DGX Platform for drug discovery. This partnership, alongside our other partnerships with @Roche /@genentech and @Bayer makes it clear that the transition from

EXCESS DEATHS… a thread🧵 There have been 25,700 excess deaths in the UK so far this year (source: CMI). That averages out at OVER 1,000 excess deaths a week. Now I hope you’re sitting comfortably because I’ve been doing some digging & there’s a lot more to this story…

Love how people wanna talk at me about merit. Like anything in this country is actually ever based off merit.

My ability to tweet long research webinars has diminished, but I'm going to try here bc it's an important & under-researched area of #LongCovid! It's on venous congestion disorders in the brain & neck & features amazing folks like @RuhoyMD & @ar_pnw. 1/ https://t.co/Q1wFqggC7y

So delighted that our paper, which uses comparative CRISPR screening to identify species differences in human and chimpanzee stem cells, is being published today!

My @pycon talk is up!! This may be my favorite talk I've given to-date; the audience was SO KIND. If you want to see, starting with my personal story: https://t.co/G4wKxDPbtK If you want to skip all that and get to "AI", start here: https://t.co/c7XPkSVYJc

We are incredibly excited to integrate our powerful chemistry engine into @RecursionPharma’s OS to enable the future of AI-first drug discovery! We’ll be expanding our ML research team at @Mila_Quebec with the aim of solving the hardest problems in drug discovery Stay tuned!

Jordan Neely was murdered. But bc Jordan was houseless and crying for food in a time when the city is raising rents and stripping services to militarize itself while many in power demonize the poor, the murderer gets protected w/ passive headlines + no charges. It’s disgusting.

I'm hopeful that recognizing the existence of and addressing proximity bias (whether through the approach we share or ones developed in the future) will lead to more effective #drugdiscovery and ultimately have a positive impact on patient lives.

I'm thankful for @RecursionPharma's openness in sharing these results with the scientific community; we believe that this confounding has implications for CRISPR-based discovery and may have implications for therapy.

Is it time to rethink how we perform system evaluations in AI? In our new @ScienceMagazine paper, we show that over-reliance on aggregate metrics and a lack of transparency in reporting threatens public understanding and hinders progress in the field. 1/8

In a dialogue in Gödel, Escher, Bach (1979), the Crab describes "a new...very flexible kind of computer": "they are called 'smart-stupids', since they are so flexible, and have the potential to be either smart or stupid, depending on how skillfully they are instructed." (1/2)

3 years of work... the JUMP-Cell Painting Consortium has now released the world's largest public Cell Painting dataset! 117,000 compounds, 13,000 overexpressed genes, 8,000 gene knockdowns, w/images and extracted profiles 🤯 Data @ Cell Painting Gallery:

📢 MosaicML Cloud is now available for early access! Create advanced AI models faster and cheaper than you thought possible.

Captcha

I want to talk about burnout. A brief 🧵... I was well aware I was burnt out in the fall, but it's hard to fully appreciate the impact of burnout in the moment. After 2 weeks of vacation and a month of aggressively blocking daily focus time, the impact has become more clear: