Robust deep learning based protein sequence design using ProteinMPNN
J. Dauparas, I. Anishchenko, N. Bennett et al. · 2022
Read Robust deep learning based protein sequence design using ProteinMPNN by J. Dauparas, I. Anishchenko, N. Bennett et al. (2022) in the Tower of Babel, a free online library of public-domain works preserved in clean, searchable text. No sign-up. The full text is served as a plain-text file at a predictable URL, where text is present: https://antarctic-labs.com/tower-of-babel/pmc-9997061.txt.
Description
Justas Dauparas and co-authors described ProteinMPNN in 2022, a deep learning method that designs protein sequences to fold into a chosen shape. Predicting structure from sequence had just been transformed by deep learning. Designing the reverse, a sequence for a desired structure, still relied mostly on physics based tools such as Rosetta, which produced nearly all proven experimental designs.
ProteinMPNN takes the backbone shape as input and proposes sequences likely to fold into it. The authors show its designs solving in the laboratory at strong rates. A fast, reliable design method widens the door to custom proteins built for medicine, materials, and research, rather than only borrowed from nature.
Catalog record
| CREATOR | J. Dauparas, I. Anishchenko, N. Bennett et al. |
|---|---|
| YEAR | 2022 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 26 KB |
| LICENSE | Creative Commons Attribution License |
| RIGHTS | CC BY |
| SOURCE | PubMed Central |