HIGHLIGHTS
- who: ETH Library and collaborators from the Department of Biosystems Science and Engineering, Zuu0308rich, Basel, Switzerland, Visium, Lausanne, Switzerland and have published the article: Conditional generative modeling for de novo protein design with hierarchical functions, in the Journal: (JOURNAL)
- what: The authors propose a general-purpose model for protein design that only requires specifying the desired functional properties for generation. The authors propose to use MMD (Gretton et_al, 2012), a test statistic that compares mean embeddings in a Reproducing Kernel Hilbert Space (RKHS). The authors explore several conditioning mechanisms, label embeddings and model architectures to . . .
If you want to have access to all the content you need to log in!
Thanks :)
If you don't have an account, you can create one here.