serial co-founder building AI in biotech @FlagshipPioneer ๐งฌ | Previously ML @Amgen, omics @decodegenetics | @ETH_en & @MIT | 2:58 marathon ๐โโ๏ธ-er
Itโs getting hard to keep track of all the new open-source cofolding models coming out. To help everyone stay up to date, I'm excited to share https://t.co/Gc9PaF6GoY, a PDB-synced leaderboard of open models, updated weekly. All predictions are available to view & download! (1/4)
was talking to some frontier lab people about this today
think the realistic path to AI "solving" disease would be AI making fundamental discoveries in physics, which lets us make applied discoveries in sensor/assay design, which lets us probe biological systems at microscopic resolutions non-invasively at 1/1000th the current cost
Our @AsimovPress book on the history of the molecular biology lab is nearly finished. It's currently 455 pages, with 100+ images. Some previews below.
We've spent the last 6+ months making this book as beautiful, and detailed, as possible. And we're excited for you to hold it.
I recently finished @_brianpotter's book The Origins of Efficiency. I loved it! It got me thinking - where are we waiting in the life sciences? How can we improve our efficiency towards getting from early stage research to an actual drug for patients.
https://t.co/nPkDw9Uxt2
The dream is where you can industrialize the entire cycle of creating a drug - from industrialized data creation at scale to potentially models that reason at scale about what to do next towards a clinical asset.
You can now give your agent deep knowledge of millions of papers in one line with #paperclip!๐
>8 million papers natively indexed for agents.
Much more thorough + often 10x faster than standard deep research.
Just add the paperclip mcp (instruction below).
I'm also excited about the impact @adaptyvbio, @btnaughton via biomodals, and @tamarind.bio are having on making computational pipelines, and the protein design field in general, reproducible + scalable
Inspired by this post on agent-led growth from @sonyatweetybird, I wrote about how we need to rethink how we record, structure, and share data from the lab to unlock agent-led labs.
Post: https://t.co/pxXL4c7ySJ
I believe we need to make papers more reproducible, perhaps through "machine readable formats," so that we can actually reproduce results from literature (inspiration from https://t.co/Aw1Ju7CrDD)