Introducing OpenScience. A better, open-source Claude Science.
• Any model: GLM, Kimi, DeepSeek, Claude, GPT, your own fine-tune. Switching is one flag.
• 250+ research skills across ML, comp bio, cheminformatics. All readable, editable, extensible.
• No throttling, no gatekeeping, no one vendor deciding what science is okay.
• Native Atlas integration: many agents, one shared reproducible research graph.
• Runs on your infra. Your data stays yours.
Scientific AI should be open. One company shouldn't own the tools the rest of us discover with, or decide who gets to.
Excited to release BoltzGen which brings SOTA folding performance to binder design! The best part of this project has been collaborating with many leading biologists who tested BoltzGen at an unprecedented scale, showing success on many novel targets and pushing its limits! 🧵..
Ask not why would you work in biology, but rather: why wouldn't you?
https://t.co/kYEpm5B1IL
openai/gemini gave this essay an A- for evocative imagery. claude gave it a C- for being emotionally manipulative. both are probably right. i feel a little sick re-reading it
Last month, @PatDotPy defended his PhD dissertation!
Pat’s work studied E. coli Transcription Factors at multiple resolution scales & provided novel insights into the spectrum of TF binding (more details soon)!
He is now building NGS Analysis Pipeline Services for @BU_PDC!
@jankosinski Apologies if you’ve answered this already but have you tried this with a “nonspecific” sequence? Might give that a shot later myself but curious what it would find