Cargando…

IUP-BERT: Identification of Umami Peptides Based on BERT Features

Umami is an important widely-used taste component of food seasoning. Umami peptides are specific structural peptides endowing foods with a favorable umami taste. Laboratory approaches used to identify umami peptides are time-consuming and labor-intensive, which are not feasible for rapid screening....

Descripción completa

Detalles Bibliográficos
Autores principales: Jiang, Liangzhen, Jiang, Jici, Wang, Xiao, Zhang, Yin, Zheng, Bowen, Liu, Shuqi, Zhang, Yiting, Liu, Changying, Wan, Yan, Xiang, Dabing, Lv, Zhibin
Formato: Online Artículo Texto
Lenguaje:English
Publicado: MDPI 2022
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9689418/
https://www.ncbi.nlm.nih.gov/pubmed/36429332
http://dx.doi.org/10.3390/foods11223742
_version_ 1784836529262166016
author Jiang, Liangzhen
Jiang, Jici
Wang, Xiao
Zhang, Yin
Zheng, Bowen
Liu, Shuqi
Zhang, Yiting
Liu, Changying
Wan, Yan
Xiang, Dabing
Lv, Zhibin
author_facet Jiang, Liangzhen
Jiang, Jici
Wang, Xiao
Zhang, Yin
Zheng, Bowen
Liu, Shuqi
Zhang, Yiting
Liu, Changying
Wan, Yan
Xiang, Dabing
Lv, Zhibin
author_sort Jiang, Liangzhen
collection PubMed
description Umami is an important widely-used taste component of food seasoning. Umami peptides are specific structural peptides endowing foods with a favorable umami taste. Laboratory approaches used to identify umami peptides are time-consuming and labor-intensive, which are not feasible for rapid screening. Here, we developed a novel peptide sequence-based umami peptide predictor, namely iUP-BERT, which was based on the deep learning pretrained neural network feature extraction method. After optimization, a single deep representation learning feature encoding method (BERT: bidirectional encoder representations from transformer) in conjugation with the synthetic minority over-sampling technique (SMOTE) and support vector machine (SVM) methods was adopted for model creation to generate predicted probabilistic scores of potential umami peptides. Further extensive empirical experiments on cross-validation and an independent test showed that iUP-BERT outperformed the existing methods with improvements, highlighting its effectiveness and robustness. Finally, an open-access iUP-BERT web server was built. To our knowledge, this is the first efficient sequence-based umami predictor created based on a single deep-learning pretrained neural network feature extraction method. By predicting umami peptides, iUP-BERT can help in further research to improve the palatability of dietary supplements in the future.
format Online
Article
Text
id pubmed-9689418
institution National Center for Biotechnology Information
language English
publishDate 2022
publisher MDPI
record_format MEDLINE/PubMed
spelling pubmed-96894182022-11-25 IUP-BERT: Identification of Umami Peptides Based on BERT Features Jiang, Liangzhen Jiang, Jici Wang, Xiao Zhang, Yin Zheng, Bowen Liu, Shuqi Zhang, Yiting Liu, Changying Wan, Yan Xiang, Dabing Lv, Zhibin Foods Article Umami is an important widely-used taste component of food seasoning. Umami peptides are specific structural peptides endowing foods with a favorable umami taste. Laboratory approaches used to identify umami peptides are time-consuming and labor-intensive, which are not feasible for rapid screening. Here, we developed a novel peptide sequence-based umami peptide predictor, namely iUP-BERT, which was based on the deep learning pretrained neural network feature extraction method. After optimization, a single deep representation learning feature encoding method (BERT: bidirectional encoder representations from transformer) in conjugation with the synthetic minority over-sampling technique (SMOTE) and support vector machine (SVM) methods was adopted for model creation to generate predicted probabilistic scores of potential umami peptides. Further extensive empirical experiments on cross-validation and an independent test showed that iUP-BERT outperformed the existing methods with improvements, highlighting its effectiveness and robustness. Finally, an open-access iUP-BERT web server was built. To our knowledge, this is the first efficient sequence-based umami predictor created based on a single deep-learning pretrained neural network feature extraction method. By predicting umami peptides, iUP-BERT can help in further research to improve the palatability of dietary supplements in the future. MDPI 2022-11-21 /pmc/articles/PMC9689418/ /pubmed/36429332 http://dx.doi.org/10.3390/foods11223742 Text en © 2022 by the authors. https://creativecommons.org/licenses/by/4.0/Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/)
spellingShingle Article
Jiang, Liangzhen
Jiang, Jici
Wang, Xiao
Zhang, Yin
Zheng, Bowen
Liu, Shuqi
Zhang, Yiting
Liu, Changying
Wan, Yan
Xiang, Dabing
Lv, Zhibin
IUP-BERT: Identification of Umami Peptides Based on BERT Features
title IUP-BERT: Identification of Umami Peptides Based on BERT Features
title_full IUP-BERT: Identification of Umami Peptides Based on BERT Features
title_fullStr IUP-BERT: Identification of Umami Peptides Based on BERT Features
title_full_unstemmed IUP-BERT: Identification of Umami Peptides Based on BERT Features
title_short IUP-BERT: Identification of Umami Peptides Based on BERT Features
title_sort iup-bert: identification of umami peptides based on bert features
topic Article
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9689418/
https://www.ncbi.nlm.nih.gov/pubmed/36429332
http://dx.doi.org/10.3390/foods11223742
work_keys_str_mv AT jiangliangzhen iupbertidentificationofumamipeptidesbasedonbertfeatures
AT jiangjici iupbertidentificationofumamipeptidesbasedonbertfeatures
AT wangxiao iupbertidentificationofumamipeptidesbasedonbertfeatures
AT zhangyin iupbertidentificationofumamipeptidesbasedonbertfeatures
AT zhengbowen iupbertidentificationofumamipeptidesbasedonbertfeatures
AT liushuqi iupbertidentificationofumamipeptidesbasedonbertfeatures
AT zhangyiting iupbertidentificationofumamipeptidesbasedonbertfeatures
AT liuchangying iupbertidentificationofumamipeptidesbasedonbertfeatures
AT wanyan iupbertidentificationofumamipeptidesbasedonbertfeatures
AT xiangdabing iupbertidentificationofumamipeptidesbasedonbertfeatures
AT lvzhibin iupbertidentificationofumamipeptidesbasedonbertfeatures