My prior post below re China x US biotech has caught the attention of a few of you Why am I well positioned to comment on the situation? A short backstory: In 2021 I co-founded precision oncology biotech, @melioratx, based in Boston and SF. We work on covalent allosteric

Long term outcomes from #KATHERINE out in NEJM. Post-neoadjuvant escalation of therapy with a HER2 ADC (T-DM1) in patients with HER2+ breast cancer and residual disease meaningfully improves 7-year iDFS (Δ 13.7%) and OS (Δ 4.7%). Congrats to the authors! nejm.org/doi/full/10.10…

Yikes!

It’s been a tough few weeks. My 10yo daughter was diagnosed with a very rare, aggressive cancer called interdigitating dendritic cell sarcoma (IDCS). I’m reaching out to identify clinicians/patients who have encountered pediatric IDCS, indeterminate dendritic cell histiocytosis

Today, we are announcing a new pre-seed venture fund – Altitude Lab Fund – to support early-stage biotech startups facing the loss of SBIR grants due to recent federal funding policy shifts which have left many biotech founders in limbo. I wrote about why these funds are so

The Recursion $RXRX Pi3k preclinical molecule REC-7735 just revealed - as good, if not better, than the Scorpion molecule STX-478 that received so much attention recently when it was acquired by Lilly for up to $2.5Bn.

Come visit with Recursion at AACR!

NEW: Google’s bet on AI in drug discovery just got a lot bigger. My latest with Kyle LaHucik on Isomorphic's $600 million round — the largest in biotech so far in 2025: endpts.com/isomorphic-lab…

What if we could map the surface features that make a protein degradable? At Monte Rosa, we’re doing just that – creating ‘glueprints’ to rationally design molecular glue degraders for previously undruggable targets. Our latest preprint explains how: bit.ly/4d3vxex

Excited to unveil Boltz-2, our new model capable not only of predicting structures but also binding affinities! Boltz-2 is the first AI model to approach the performance of FEP simulations while being more than 1000x faster! All open-sourced under MIT license! A thread… 🤗🚀

Today, we’re announcing an important step forward in modeling binding affinity alongside Massachusetts Institute of Technology (MIT) and a research team led by Regina Barzilay. Boltz-2 is the first open-source co-folding model to combine protein structure and binding affinity predictions – measuring how strongly a

Learn more about Boltz-2, the new open source AI model from MIT and Recursion capable of predicting protein binding affinity with unprecedented speed, scale and accuracy. ▪️ Boltz-2 is the first model to combine structure and binding affinity prediction, approaching the accuracy

Strong work! One of my most favorite auxotrophic papers was from Javier Garcia-Bermudez and Kivanc Birsoy, can't wait to read this one.

AHH!! My primary thesis work is finally out! Tweetorial to come...

🚨Postdoctoral position available now! 🚨We have an immediate fully funded position available in cardiac metabolism. We are looking for a highly motivated person to lead our animal model work in oxidative metabolism in heart! Pay is competitive with benefits offered. 1/2

Phenomenal lab looking for a postdoc in Salt Lake!

I talk a lot about the incredible platform we’re building at Recursion, but nothing beats hearing from the brilliant scientists who use it every day. That’s why I love this video with Chase Neumann. Chase is part of the team that uncovered the initial insight for our