Signal Peptides Generated by Attention-Based Neural Networks

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. E...

Full description

Saved in:
Bibliographic Details
Published in:ACS synthetic biology 2020-08, Vol.9 (8), p.2154-2161
Main Authors: Wu, Zachary, Yang, Kevin K, Liszka, Michael J, Lee, Alycia, Batzilla, Alina, Wernick, David, Weiner, David P, Arnold, Frances H
Format: Article
Language:English
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary: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.
ISSN:2161-5063
2161-5063
DOI:10.1021/acssynbio.0c00219