Great drug hunters develop a "sixth sense" for identifying and advancing promising targets before others. Sometimes connecting the dots on target validation is clearer. Take Deucravacitinib (oral Tyk2i). The ID of psoriasis as an IL-17 and IL-23 dependent disease and

Thoughtful alert on CMC issues for protein, mab, & gene/cell therapies. Don’t underestimate cost & complexity of bridging studies and impact of small changes on regulatory review.

Pharmas typically acquire drugs they know how to commercialize. This means assets that are trickier to commercialize, e.g. drug+device combos, can be overlooked due to low M&A interest. What are other therapeutics classes with similar dynamics, but nonetheless promising?

Rate of pharma M&A has remained strikingly consistent over the years. Much of the biotech game is finding a way to get on this shopping list.

Directed evolution is key for unlocking new protein function But is difficult and time consuming So how can we accelerate protein design by 10-100x? With AI! Now introducing EVOLVEpro, an LLM-based model for evolving proteins rapidly and efficiently biorxiv.org/content/10.110…

Directed evolution won a Nobel prize by unlocking new protein functions How can we augment evolution to engineer proteins 10-100 times better? By using large language models! Here we present EVOLVEpro, an LLM for accelerated protein evolution biorxiv.org/content/10.110… 1/

Appreciated this article from LEK on first- vs. best-in-class drugs Unlike most academic work on this topic, LEK acknowledges the empirical reality that a majority of drugs fail to achieve commercial success, and strives to bridge that incongruity in their analysis (1/4)

TP53: - Discovered 45 years ago, most cited gene all time - No therapies - 500 million people currently living will die of TP53 mutant cancers without new therapies Our Preprint: - A general strategy for TP53 missense mutant cancers (majority) with prototype small molecules

Huge congratulations to the newly minted Dr. Kunes (Russell Zhang Kunes). It was a real pleasure and honor to have him in my lab, one of the most gifted people I have met in his dual ability to see the structure and understand both data and statistics, and how to connect the two

Vault complex: - Massive 13 mDa protein complexes; - Widely conserved and expressed in eukaryotic cells; - Vault knockout mice had no phenotypic differences from wild type; - Nobody knows what they do; - BIG MYSTERY en.wikipedia.org/wiki/Vault_(or…

PHARMA HISTORY: Top 10 BY MARKET CAP 2004: Pfizer “King of Lipids - Lipitor” 2005-11: JNJ “TNF Time - Remicade” 2012: Roche “HER Too - Herceptin” 2013-21: JNJ “Bloody Blockbuster - Imbruvica” 2022-23: Lilly “The Obesity Show - Mounjaro” Source: Joana Sadowska on the HR APP

Impressive to see Twist continue scaling revenue, while cutting back on both R&D and SG&A expense last year. Currently trading 8x EV/Rev, highest among specialty tool companies

i teared up at the Z machine firing at Sandia National Labs. thirty years of relentless work by engineers in Albuquerque, for the pursuit of fusion and material science. a rare, haunting dedication.

reasoning ✅ I joined the 🍓 team because I believed in making the reasoning dream—thinking hard on hard problems—a reality. With collaborators I feel lucky every day to work with, we made this dream come true. Proud to finally be able to share o1 with the world!

Evaluating o1 on the International Olympiad of Informatics was very personally meaningful to me. When I competed nine years ago, I never thought I'd be back—so soon—competing with an AI. To highlight how amazing this model is, we shared on Codeforces its best IOI submissions ⬇️