iiinova — where your digital self keeps evolving

Marta Skreta @martaowesyou.bsky.social · 08/04/2026

So grateful for this incredible collaboration with @jarridrb.bsky.social, @tlambert99.bsky.social @daro9000.bsky.social ky.social, Yueming Long, Zi-Qi Li, Xi Zhang, @mirunacretu.bsky.social, @francescazfl.bsky.social, Tanvi Ganapathy, Emily Jin, @joeybose.bsky.social, Jason Yang, ...

ky.social

110

Marta Skreta @martaowesyou.bsky.social · 08/04/2026

Not only are the enzymes functional, they're also evolvable starting points. One round of mutagenesis on dCT-H11 yielded a 4x activity increase for spirocyclopropanation and even inverted stereoselectivity. The chemistry nature never explored is now within reach! 🌍

100

Marta Skreta @martaowesyou.bsky.social · 08/04/2026

Take the top design, dCT-H11. Its closest structural match (PDB 3CRJ) is a non-enzymatic transcription factor from a Dead Sea extremophile. DISCO completely repurposed this fold for carbene chemistry with a novel active-site geometry and very low sequence identity. 🦠🔬

110

Marta Skreta @martaowesyou.bsky.social · 08/04/2026

Perhaps the most interesting property? These active sites don't exist in nature. When searched against 200M+ structures in the AlphaFold Database, the majority of DISCO's generated binding motifs have no close natural homologs.

110

Marta Skreta @martaowesyou.bsky.social · 08/04/2026

The success continued with B–H insertion. A single DISCO design achieved 5,170 TTN, outperforming three rounds of laboratory directed evolution by over 2x. 🤯

110

Marta Skreta @martaowesyou.bsky.social · 08/04/2026

It mastered selective C(sp³)–H insertion, one of the most challenging transformations in organic chemistry. A single computational step reached 2,360 TTN, exceeding the endpoint of a previous 14-round directed evolution campaign. 🎯

110

Marta Skreta @martaowesyou.bsky.social · 08/04/2026

The ultimate test is the wet lab. 🧪 DISCO was challenged to design enzymes for carbene-transfer reactions—chemistry alien to the natural world.

110

Marta Skreta @martaowesyou.bsky.social · 08/04/2026

Because DISCO generates sequence & structure together, it unlocks multimodal inference-time steering. 🧭 Deriving multimodal Feynman-Kac Correctors, DISCO steers generation on the fly—like forcing the creation of dense disulfide bonds (FKC-MM) or binding a target while avoiding a decoy (FKC-SG). 🎯🚫

120

Marta Skreta @martaowesyou.bsky.social · 08/04/2026

How does it work? DISCO aligns sequence & structure bidirectionally via cross-modal recycling, self-correction, and noisy guidance. It also introduces an entropy-adaptive sequence temperature to properly balance information across modalities during generation! ⚖️

120

Marta Skreta @martaowesyou.bsky.social · 08/04/2026

Introducing the 💃🕺Studio-179 benchmark 🕺 💃: DISCO outperforms baselines on 178/179 targets, along with sequence-specific DNA and RNA binders! 📈 It also shines in unconditional design, generating highly diverse, novel, and co-designable proteins.

110

Marta Skreta @martaowesyou.bsky.social · 08/04/2026

Evolution is an amazing chemist, but the reactions it has explored represent a remarkably narrow slice of what is possible. Existing AI models require predefined theozymes & generate backbones before sequences. DISCO generates both sequence & structure simultaneously without the need for theozymes.

110

Marta Skreta @martaowesyou.bsky.social · 08/04/2026

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.

110

Marta Skreta @martaowesyou.bsky.social · 08/04/2026

What if AI could invent enzymes that nature hasn’t seen? 👩‍🔬🧑‍🔬 Introducing 🪩 DISCO: Diffusion for Sequence-structure CO-design 📝 Blog: disco-design.github.io 📄 Paper: arxiv.org/abs/2604.05181 💻 Code: github.com/DISCO-design...

15918

Reposted by Marta Skreta

Rocío Mercado Oropeza @rociomer.bsky.social · 05/08/2025

📄📄📄 The AI4Mat-NeurIPS-2025 workshop is now open for submissions until August 22, 2025 (AOE)! Consider submitting full-length papers or shorter-length findings. We also have a special track for papers on benchmarking AI for materials design. sites.google.com/view/ai4mat/...

273

Reposted by Marta Skreta

Rocío Mercado Oropeza @rociomer.bsky.social · 28/04/2025

Thanks to all the speakers and participants for the engaging discussions today, and for making the AI4Mat@ICLR 2025 workshop a great success! Thanks also to Santiago, @martaowesyou.bsky.social, and the rest of the co-organizing team for the effort putting this together. Great to be a part of it!

Singapore EXPO sign outside of the convention center where ICLR was held.

Co-organizer photo with Santiago, myself, and Marta at the end of the workshop.

0111

Reposted by Marta Skreta

Alán Aspuru-Guzik @aspuru.bsky.social · 24/01/2025

We at @digital-discovery.bsky.social are very happy to announce a new paper type called "Commit". Inspired by version control systems such as git, the idea is that if you have an update on a short and pointed publication, you can send it as a commit. We envision commits to be co-cited with the

88515

Reposted by Marta Skreta

lebellig @lebellig.bsky.social · 05/01/2025

"The Superposition of Diffusion Models using the Îto Density Estimator" (@martaowesyou.bsky.social, @lazaratan.bsky.social et al.) It's nice to see an easy-to-compute log-likelihood estimator for SDE sampling of diffusion models (not just ODE) 📄 arxiv.org/abs/2412.17762 🐍 github.com/necludov/sup...

0224

Reposted by Marta Skreta

Joey Bose @joeybose.bsky.social · 28/12/2024

New paper just dropped! How do you combine pre-trained diffusion models without having to train a new one 🤓? Turns out you can use our all new Ito density estimator 🔥 to compute densities under a diffusion model efficiently 🚀!

0205

Marta Skreta @martaowesyou.bsky.social · 28/12/2024

Super super excited to share our work SuperDiff 🦹‍♀️ for superimposing pretrained diffusion models at inference time 💪 Check out the 🧵 to see how we superimposed proteins as well as images, all thanks to a fast new density estimator. Curious to see what 🍩 & 🗺️ would produce?

1243

Marta Skreta @martaowesyou.bsky.social · 18/12/2024

exciting new workshop announcement!! join us in Singapore for Frontiers in Probabilistic Inference: Learning Meets Sampling 🌏⚡️😃 details below 👇 #ICLR2025

092

Marta Skreta @martaowesyou.bsky.social · 09/12/2024

3/3 🧵Work with my fellow Matter Lab quantum tunnelers: Philipp Schleich, Lasse B. Kristensen, @rovargash.bsky.social, @aspuru.bsky.social 📜 buff.ly/4iu8w6M 💻 buff.ly/3D9HaD2 See you at NeurIPS!

011

Marta Skreta @martaowesyou.bsky.social · 09/12/2024

2/3 🧵Here, we enter the quantumverse with deep equilibrium networks, where we demonstrate that a single layer of a quantum circuit can perform as well or better than multiple independent layers when trained like a DEQ.

100

Marta Skreta @martaowesyou.bsky.social · 09/12/2024

1/3 🧵Quantum conundrum: we want expressive circuits, but current hardware only allows short coherence times, and so more parameters = more problems. Check out our #NeurIPS2024 paper “Quantum Deep Equilibrium Models”.

1136