Protein FID: Improved Evaluation of Protein Structure Generative Models １．This paper proposes Protein FID, a new evaluation metric for generative protein structure models, addressing key limitations of current metrics like designability, diversity, and novelty, which often

Nature Methods PNASNews 38/ Next paper in this series is #Boltz2 paper that described an open-source AI model that predicts both 3D protein structures and binding affinities — approaching the gold-standard FEP simulations, but 1000x faster ⚡ Why does this matter? Binding affinity = how tightly a

One thing that really bothers me with the new "virtual cell" terminology is that is currently largely focused on a very narrow definition of models that can predict effects of trans perturbations (gene dosage, drugs etc) on gene expression. 1/

Instead, we represent proteins as 3D densities sampled on a discrete grid. Like image pixels, we're calling this representation *proxels* 🙃 (3/8)

Very happy about our new ProxelGen piece! We explore generating proteins represented as densities instead of the standard 3D point clouds. I am excited to see what this can enable in terms of training on broader density data in the future 👌

📌Notes on Boltz-2 Just watched the video talk led by Gabriele Corso Jeremy Wohlwend, and Saro Passaro that introduced Boltz-2, a structural biology foundation models. I summarized some learning notes below 🧵

Couldn't summarize the affinity prediction part yet, saving for later. Boltz-2 Paper: biorxiv.org/content/10.110… Code: github.com/jwohlwend/boltz Talk: youtube.com/watch?v=iHDauM…

Starkly Speaking tomorrow: Brandon Wood will present "UMA: A Family of Universal Models for Atoms" ai.meta.com/research/publi… Join us on Zoom 12pm ET / 6pm CEST: portal.valencelabs.com/starklyspeaking

Announcing Ambient Protein Diffusion, a state-of-the-art 17M-params generative model for protein structures. Diversity improves by 91% and designability by 26% over previous 200M SOTA model for long proteins. The trick? Treat low pLDDT AlphaFold predictions as low-quality data

Had a lot of fun learning diffusion and addressing key issues in protein diffusion with Giannis Daras Jeffrey Ouyang-Zhang TLDR: a few protein structure insights inspired us to design a new diffusion loss, training regime and dataset, resulting in significant performance improvements

🚧 Important warning about novelty computation in prior work 🚧 While working on the paper, we realized that a FoldSeek bug has affected novelty numbers in prior works. If you are using FoldSeek to report novelty, we strongly recommend using FoldSeek 10 onwards.

Unfortunately, not able to attend #ICML2025 this year, but happy to share our accepted paper: 𝐒𝐏𝐇𝐈𝐍𝐗: 𝐒𝐭𝐫𝐮𝐜𝐭𝐮𝐫𝐚𝐥 𝐏𝐫𝐞𝐝𝐢𝐜𝐭𝐢𝐨𝐧 𝐮𝐬𝐢𝐧𝐠 𝐇𝐲𝐩𝐞𝐫𝐠𝐫𝐚𝐩𝐡 𝐈𝐧𝐟𝐞𝐫𝐞𝐧𝐜𝐞 𝐍𝐞𝐭𝐰𝐨𝐫𝐤 w/ Pietro Lio' arxiv.org/pdf/2410.03208 1/2

My labmate, officemate, and co-author Felix Faltings will be at #ICML2025 presenting ProxelGen in the GenBio Workshop @ ICML25 ! Anyone interested in discussing ProxelGen, ProtFID, or our current biomolecular design work? (ProxelGen link arxiv.org/pdf/2506.19820)

We also presented this work in Hannes Stärk's reading group. Go check it out if interested! (youtu.be/0r25eXy-Bgc?si…) Code coming soon! (12/12)

Presenting La-Proteina! A new model for scalable, all-atom protein design 🧬 Backbone + sequence + side-chains, indexed and unindexed atomistic motif scaffolding, scalable up to 800 residues, and more… A thread 🧵

📢📢 "La-Proteina: Atomistic Protein Generation via Partially Latent Flow Matching" Fully atomistic. Partially latent. Structurally precise. Entirely generative. w/ Tomas Geffner*, Kieran Didi @ICLR*, et al. 📜 Project page & paper: research.nvidia.com/labs/genair/la… 🧵 Thread below... (1/n)

Excited to share: “Learning Diffusion Models with Flexible Representation Guidance” With my amazing coauthors Cai Zhou, Sharut Gupta, Johnson Lin, Stefanie Jegelka, Stephen Bates, Tommi Jaakkola Paper: arxiv.org/pdf/2507.08980 Code: github.com/ChenyuWang-Mon…

Tomorrow we discuss diffusion models for sampling unnormalized densities "Adjoint Sampling: Highly Scalable Diffusion Samplers via Adjoint Matching" arxiv.org/abs/2504.11713 Join us on zoom at 9am PT / 12pm ET / 6pm CEST: portal.valencelabs.com/starklyspeaking