| Title |
Computational scoring and experimental evaluation of enzymes generated by neural networks / |
| Authors |
Johnson, Sean R ; Fu, Xiaozhi ; Viknander, Sandra ; Goldin, Clara ; Monaco, Sarah ; Železniak, Aleksej ; Yang, Kevin K |
| DOI |
10.1038/s41587-024-02214-2 |
| Full Text |
|
| Is Part of |
Nature biotechnology.. Berlin : Springer Nature. 2024, Early Access, p. [1-17].. ISSN 1087-0156. eISSN 1546-1696 |
| Abstract [eng] |
In recent years, generative protein sequence models have been developed to sample novel sequences. However, predicting whether generated proteins will fold and function remains challenging. We evaluate a set of 20 diverse computational metrics to assess the quality of enzyme sequences produced by three contrasting generative models: ancestral sequence reconstruction, a generative adversarial network and a protein language model. Focusing on two enzyme families, we expressed and purified over 500 natural and generated sequences with 70–90% identity to the most similar natural sequences to benchmark computational metrics for predicting in vitro enzyme activity. Over three rounds of experiments, we developed a computational filter that improved the rate of experimental success by 50–150%. The proposed metrics and models will drive protein engineering research by serving as a benchmark for generative protein sequence models and helping to select active variants for experimental testing. |
| Published |
Berlin : Springer Nature |
| Type |
Journal article |
| Language |
English |
| Publication date |
2024 |
| CC license |
|
