Expanding functional protein sequence spaces using generative adversarial networks
Journal article, 2021
De novo protein design for catalysis of any desired chemical reaction is a long-standing goal in protein engineering because of the broad spectrum of technological, scientific and medical applications. However, mapping protein sequence to protein function is currently neither computationally nor experimentally tangible. Here, we develop ProteinGAN, a self-attention-based variant of the generative adversarial network that is able to ‘learn’ natural protein sequence diversity and enables the generation of functional protein sequences. ProteinGAN learns the evolutionary relationships of protein sequences directly from the complex multidimensional amino-acid sequence space and creates new, highly diverse sequence variants with natural-like physical properties. Using malate dehydrogenase (MDH) as a template enzyme, we show that 24% (13 out of 55 tested) of the ProteinGAN-generated and experimentally tested sequences are soluble and display MDH catalytic activity in the tested conditions in vitro, including a highly mutated variant of 106 amino-acid substitutions. ProteinGAN therefore demonstrates the potential of artificial intelligence to rapidly generate highly diverse functional proteins within the allowed biological constraints of the sequence space.
Author
Donatas Repecka
Biomatter Designs, UAB
Vykintas Jauniskis
Chalmers, Biology and Biological Engineering, Systems and Synthetic Biology
Biomatter Designs, UAB
Laurynas Karpus
Biomatter Designs, UAB
Elzbieta Rembeza
Chalmers, Biology and Biological Engineering, Systems and Synthetic Biology
Irmantas Rokaitis
Biomatter Designs, UAB
Jan Zrimec
Chalmers, Biology and Biological Engineering, Systems and Synthetic Biology
Simona Poviloniene
Vilnius University
Audrius Laurynenas
Vilnius University
Biomatter Designs, UAB
Sandra Viknander
Chalmers, Biology and Biological Engineering, Systems and Synthetic Biology
Wissam Abuajwa
Chalmers, Biology and Biological Engineering, Systems and Synthetic Biology
Otto Savolainen
Chalmers, Biology and Biological Engineering, Systems and Synthetic Biology
Rolandas Meskys
Vilnius University
Martin Engqvist
Chalmers, Biology and Biological Engineering, Systems and Synthetic Biology
Aleksej Zelezniak
Science for Life Laboratory (SciLifeLab)
Chalmers, Biology and Biological Engineering, Systems and Synthetic Biology
Nature Machine Intelligence
25225839 (eISSN)
Vol. 3 4 324-333Subject Categories (SSIF 2011)
Biochemistry and Molecular Biology
Bioinformatics and Systems Biology
Other Industrial Biotechnology
DOI
10.1038/s42256-021-00310-5