Signal Peptides Generated by Attention-Based Neural Networks | Zendy

Zachary Wu | Zendy; Kevin Yang | Zendy; Michael J. Liszka | Zendy; Alycia Lee | Zendy; Alina Batzilla | Zendy; David G. Wernick | Zendy; David P. Weiner | Zendy; Frances H. Arnold | Zendy

AI Assistant Blog Pricing

Home ZAIA Blog

Open Access

Signal Peptides Generated by Attention-Based Neural Networks

Author(s) -

Zachary Wu,

Kevin Yang,

Michael J. Liszka,

Alycia Lee,

Alina Batzilla,

David G. Wernick,

David P. Weiner,

Frances H. Arnold

Publication year - 2020

Publication title -

acs synthetic biology

Language(s) - Uncategorized

Resource type - Journals

SCImago Journal Rank - 2.156

H-Index - 66

ISSN - 2161-5063

DOI - 10.1021/acssynbio.0c00219

Subject(s) - signal peptide , bacillus subtilis , amino acid , computational biology , artificial neural network , peptide , biochemistry , peptide sequence , protein sequencing , secretion , biology , chemistry , computer science , artificial intelligence , genetics , gene , bacteria

Short (15-30 residue) chains of amino acids at the amino termini of expressed proteins known as signal peptides (SPs) specify secretion in living cells. We trained an attention-based neural network, the Transformer model, on data from all available organisms in Swiss-Prot to generate SP sequences. Experimental testing demonstrates that the model-generated SPs are functional: when appended to enzymes expressed in an industrial Bacillus subtilis strain, the SPs lead to secreted activity that is competitive with industrially used SPs. Additionally, the model-generated SPs are diverse in sequence, sharing as little as 58% sequence identity to the closest known native signal peptide and 73% ± 9% on average.

The content you want is available to Zendy users.

Already have an account? Click here to sign in.

Having issues? You can contact us here

Accelerating Research