sent some thoughts to a founder on balancing partnerships vs internal therapeutic programs as a platform biotech

the term “foundation model” for bio leads to confusion. FM is simply a new term for large pre-trained models trained via self-supervision, and then fine-tuned (or applied in zero-shot setting) on downstream tasks. it’s not clear that something “foundational” about biology is

in 1966, an MIT professor recruited summer interns to build a “significant” portion of a computer vision system. almost 60 years later, computer vision is not solved. never underestimate the complexity of a problem and the timeline required to solve it.

will be at the ASGCT conference next week in Baltimore, reach out if you're around! #ASGCT2024

Not exactly.. Putting a device in the bone is easily the safest place to implant something and quite scalable. It’s when you start going into the soft tissue that risks increase and scaling becomes challenging.

A primer on molecular dynamics (MD) abhishaike.com/p/a-primer-on-… this covers a lot of the absolute basics of MD in a way that is (hopefully) easy to read. at around 7.6k words, this is the longest post ive made click to see the table of contents in the replies 🧵🧵🧵

the 2024 edition of the Decoding Bio report is live! we analyzed many of the most impactful recent papers in AI, biosecurity, cell-based medicines, immunology, and biotech software. from the jump, a core goal of Decoding Bio has been to clearly communicate why these

if you can compress biology, you can predict biology one way to think about the power of LLMs is as extremely efficient data compression algorithms. at their core, LLMs learn to map high-dimensional input data (e.g., a biological sequence such as a protein) to lower-dimensional

NVentures backed Terray Therapeutics, has unveiled COATI-LDM—a groundbreaking #genAI model for designing small molecules with precision. This innovative example of inverse design has potential to greatly accelerate #drugdiscovery. Check out the arXiv preprint nvda.ws/3MhwqDF

Recursion's clinical trial readouts are not a referendum on the value of AI in drug discovery. some thoughts...