Titlebar

Export bibliographic data
Literature by the same author
plus on the publication server
plus at Google Scholar

 

ProtGPT2 is a deep unsupervised language model for protein design

Title data

Ferruz, Noelia ; Schmidt, Steffen ; Höcker, Birte:
ProtGPT2 is a deep unsupervised language model for protein design.
In: Nature Communications. Vol. 13 (2022) Issue 1 . - No. 4348.
ISSN 2041-1723
DOI: https://doi.org/10.1038/s41467-022-32007-7

Abstract in another language

Protein design aims to build novel proteins customized for specific purposes, thereby holding the potential to tackle many environmental and biomedical problems. Recent progress in Transformer-based architectures has enabled the implementation of language models capable of generating text with human-like capabilities. Here, motivated by this success, we describe ProtGPT2, a language model trained on the protein space that generates de novo protein sequences following the principles of natural ones. The generated proteins display natural amino acid propensities, while disorder predictions indicate that 88% of ProtGPT2-generated proteins are globular, in line with natural sequences. Sensitive sequence searches in protein databases show that ProtGPT2 sequences are distantly related to natural ones, and similarity networks further demonstrate that ProtGPT2 is sampling unexplored regions of protein space. AlphaFold prediction of ProtGPT2-sequences yields well-folded non-idealized structures with embodiments and large loops and reveals topologies not captured in current structure databases. ProtGPT2 generates sequences in a matter of seconds and is freely available.

Further data

Item Type: Article in a journal
Refereed: Yes
Institutions of the University: Faculties
Faculties > Faculty of Biology, Chemistry and Earth Sciences
Faculties > Faculty of Biology, Chemistry and Earth Sciences > Department of Chemistry
Faculties > Faculty of Biology, Chemistry and Earth Sciences > Department of Chemistry > Chair Biochemistry > Chair Biochemistry - Univ.-Prof. Dr. Birte Höcker
Faculties > Faculty of Biology, Chemistry and Earth Sciences > Department of Chemistry > Professorship Biochemistry
Result of work at the UBT: Yes
DDC Subjects: 500 Science > 500 Natural sciences
500 Science > 540 Chemistry
500 Science > 570 Life sciences, biology
Date Deposited: 18 Nov 2022 07:19
Last Modified: 18 Nov 2022 07:19
URI: https://eref.uni-bayreuth.de/id/eprint/72825