Reproduce “ProTEUS: A mutation-resolved world model for closed-loop protein evolution” on OpenResearch
Turn your favorite coding agents into research agents that review literature, develop hypotheses, and run experiments.
Universal app for Apple silicon and Intel. Requires macOS 11 or later.
About this paper
Yikun Zhang, Minghao Guo, Guangxue Xu, Peter Yichen Chen, Wojciech Matusik, Wengong Jin, Jingjing Chai, Kaiyi Jiang
ProTEUS uses a model-guided loop to improve protein variants: it ranks mutations, tests manageable batches, and uses measurements to guide later choices. Its MutationFormer combines sequence, evolutionary, and structural context while focusing attention on changed positions. Across three rounds, SacB reached 14.03-fold wild-type screening activity after 90 variants; ALDH reached 6.85-fold screening and 7.90-fold abundance-normalized catalytic-rate improvement, in preliminary campaigns.
Summary by alphaXiv.
Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.