Assessing the laboratory performance of AI-generated enzymes

Assessing the laboratory performance of AI-generated enzymes

A set of 20 computational metrics was evaluated to determine whether they could predict the functionality of synthetic enzyme sequences produced by generative protein models, resulting in the development of a computational filter, COMPSS, that increased experimental success rates by 50–150%, tested in over 500 natural and AI-generated enzymes.

Access options

Access Nature and 54 other Nature Portfolio journals

Get Nature+, our best-value online-access subscription

24,99 € / 30 days

cancel any time

Subscribe to this journal

Receive 12 print issues and online access

209,00 € per year

only 17,42 € per issue

Buy this article

Purchase on Springer LinkInstant access to full article PDF

Prices may be subject to local taxes which are calculated during checkout

Additional access options:

Log in

Learn about institutional subscriptions

Read our FAQs

Contact customer support

Fig. 1: Benchmarking in silico metrics for prediction of enzyme functionality.

References

Repecka, D. et al. Expanding functional protein sequence spaces using generative adversarial networks. Nat. Mach. Intell. 3, 324–333 (2021). Among the first experimentally validated generative models of protein sequences demonstrating that AI can generate diverse functional enzymes.

Meier, J. et al. Language models enable zero-shot prediction of the effects of mutations on protein function. Preprint at bioRxiv https://doi.org/10.1101/2021.07.09.450648 (2021). The paper presents one of the top-performing models that ended up in the COMPSS filter.

Dauparas, J. et al. Robust deep learning-based protein sequence design using ProteinMPNN. Science378, 49–56 (2022). The paper presents one of the top-performing models that ended up in the COMPSS filter.

Article 
CAS 
PubMed 
PubMed Central 

Google Scholar 

Madani, A. et al. Large language models generate functional protein sequences across diverse families. Nat. Biotechnol.41, 1099–1106 (2023). A recent generative sequence model example that is based on a large protein language transformer.

Article 
CAS 
PubMed 
PubMed Central 

Google Scholar 

Ingraham, J. B. et al. Illuminating protein space with a programmable generative model. Nature623, 1070–1078 (2023). A paper showing the successful application of generative diffusion models conditioned on geometrical protein properties.

Article 
CAS 
PubMed 
PubMed Central 

Google Scholar 

Download references

Additional information

Publisher’s note Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

This is a summary of: Johnson, S. R. et al. Computational scoring and experimental evaluation of enzymes generated by neural networks. Nat. Biotechnol. https://doi.org/10.1038/s41587-024-02214-2 (2024).

About this article

Cite this article

Assessing the laboratory performance of AI-generated enzymes.
Nat Biotechnol (2024). https://doi.org/10.1038/s41587-024-02239-7

Download citation

Published: 23 April 2024

DOI: https://doi.org/10.1038/s41587-024-02239-7

>>> Read full article>>>
Copyright for syndicated content belongs to the linked Source : Nature.com – https://www.nature.com/articles/s41587-024-02239-7

Exit mobile version