We present an end-to-end differentiable Bayesian framework for learning the latent parameters of coarse-grained potentials for IDPs. By optimizing a likelihood objective via importance-weighted gradients, we align generative protein ensembles with experimental observables doi.org/10.1529/biop...

Show Post

Looking for an awesome PhD in Germany at the interface of AI, small molecule design, and health? Go work with the awesome Andrea Volkamer on AI-driven discovery of safer new organic materials that avoid human toxicity! Volkamer group: volkamerlab.org position: www.uni-saarland.de/fileadmin/up...

Show Post

Can we learn protein biology from a language model? In new work led by @liambai.bsky.social and me, we explore how sparse autoencoders can help us understand biology—going from mechanistic interpretability to mechanistic biology.

Show Post

"Adapting ProteinMPNN for antibody design without retraining" Our several-years-old fix to ProteinMPNN's tendency to make weird antibody CDR sequences is finally preprinted

Show Post

Two more🙃: 1) arxiv.org/abs/2412.12979 2) arxiv.org/abs/2505.15093

Show Post