GENERATIVE AI

Going from a beautiful idea to successful wet lab experiments is the dream cycle of every scientist.

This is exactly what DISCO does but at insane, inhuman scale. Given numerous chemical constraints including binding targets and off-targets, it generates proposals for wet-lab… https://t.co/c7TbU3xUhp

— Kirill Neklyudov (@k_neklyudov) 8 avril 2026

Going from a beautiful idea to successful wet lab experiments is the dream cycle of every scientist. This is exactly what DISCO does but at insane, inhuman scale. Given numerous chemical constraints including binding targets and off-targets, it generates proposals for wet-lab testing at unprecedented throughput. For @martoskreto, @AlexanderTong7, and me, it also means bringing Feynman-Kac Correctors from idea stage to a successful practical technique! Jarrid Rector-Brooks (@jarridrb) What if AI could invent enzymes that nature hasn’t seen? 👩‍🔬🧑‍🔬 Introducing 🪩 DISCO: Diffusion for Sequence-structure CO-design 14 rounds of directed evolution and over a year of wet lab work. That's what it took to engineer an enzyme for selective C(sp³)–H insertion, one of the most challenging transformations in organic chemistry. DISCO surpasses this with a single plate. No pre-specified catalytic residues, no template, no theozyme, no inverse folding, just joint diffusion over protein sequence and structure. 📝 Blog: disco-design.github.io/ 📄 Paper: arxiv.org/abs/2604.05181 💻 Code: github.com/DISCO-design/DISC… — https://nitter.net/jarridrb/status/2041893841301860542#m

→ View original post on X — @ceobillionaire