This site needs JavaScript to work properly. Please enable it to take advantage of the complete set of features!
Skip to main page content
U.S. flag

An official website of the United States government

Dot gov

The .gov means it’s official.
Federal government websites often end in .gov or .mil. Before sharing sensitive information, make sure you’re on a federal government site.

Https

The site is secure.
The https:// ensures that you are connecting to the official website and that any information you provide is encrypted and transmitted securely.

NIH NLM Logo
Log in
Access keys NCBI Homepage MyNCBI Homepage Main Content Main Navigation
. 2022 Nov 21;11(22):3742.
doi: 10.3390/foods11223742.

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

Affiliations

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

Liangzhen Jiang et al. Foods. .

Abstract

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.

Keywords: BERT; SMOTE; deep learning; prediction; umami peptide.

PubMed Disclaimer

Conflict of interest statement

The authors declare no conflict of interest.

Figures

Figure 1
Figure 1
Overview of iUP-BERT development. The illustration depicts the 6 main steps for model development. (1) The peptide sequence was included as text and feature-extracted by the BERT model and SSA method. (2) The 788D BERT extracted feature was fused with the 121D SSA extracted features to make an 889D fusion feature vector, with individual feature vectors as comparison. (3) The SMOTE method was used to overcome the data imbalance. (4) The LGBM feature selection method was used to attain the best feature combinations. (5) Five different ML algorithms (KNN, LR, SVM, RF, and LGBM) were combined with the above techniques to build several models. (6) The final iUP-BERT predictor was established by combining the optimized feature representations. Here, BERT is for Bidirectional Encoder Representations from Transformers; SSA is for Soft Sequence Alignment; SMOTE: Synthetic Minority Oversampling Technique; LGBM is for Lighting Gradient Boosting Machine; D is for Dimension; KNN is for K-Nearest Neighbors; LR is for Logistic Regression; SVM is for Support Vector Machine; RF is for Random Forest.
Figure 2
Figure 2
The performance of 10-fold cross-validation metrics of SSA and BERT features using different algorithms pretrained with or without SMOTE. (A) KNN; (B) LR; (C) SVM; (D) RF; (E) LGBM.
Figure 3
Figure 3
The performance metrics of individual and fused features with SMOTE, according to the machine learning methods used. (A) Ten-fold cross-validation results. (B) Independent test results.
Figure 4
Figure 4
The performance metrics of individual and fusion features using selected features and different algorithms. (A) Ten-fold cross-validation results. (B) Independent test results.
Figure 5
Figure 5
Dimension reduction visualization of umami peptide BERT features and decision function boundary analysis of the SVM model. The red dots are umami peptides and the blue dots are non-umami peptides. The sub-figure (A,B) show the use of principal components analysis (PCA) and uniform manifold approximation and projection (UMAP) respectively for reducing 139 dimensional selected BERT features to 2 dimensions for visual analysis. Additionally, the decision function boundary lines of support vector machine (SVM) are drawn in both. The yellow section represents the positive sample area and the purple section represents the negative sample area.

References

    1. Liang L., Zhou C., Zhang J., Huang Y., Zhao J., Sun B., Zhang Y. Characteristics of umami peptides identified from porcine bone soup and molecular docking to the taste receptor T1R1/T1R3. Food Chem. 2022;387:132870. doi: 10.1016/j.foodchem.2022.132870. - DOI - PubMed
    1. Liang L., Duan W., Zhang J., Huang Y., Zhang Y., Sun B. Characterization and molecular docking study of taste peptides from chicken soup by sensory analysis combined with nano-LC-Q-TOF-MS/MS. Food Chem. 2022;383:132455. doi: 10.1016/j.foodchem.2022.132455. - DOI - PubMed
    1. Kong Y., Zhang L.L., Zhao J., Zhang Y.Y., Sun B.G., Chen H.T. Isolation and identification of the umami peptides from shiitake mushroom by consecutive chromatography and LC-Q-TOF-MS. Food Res. Int. 2019;121:463–470. doi: 10.1016/j.foodres.2018年11月06日0. - DOI - PubMed
    1. Lioe H.N., Selamat J., Yasuda M. Soy sauce and its umami taste: A link from the past to current situation. J. Food Sci. 2010;75:R71–R76. doi: 10.1111/j.1750-3841.2010.01529.x. - DOI - PubMed
    1. Shiyan R., Liping S., Xiaodong S., Jinlun H., Yongliang Z. Novel umami peptides from tilapia lower jaw and molecular docking to the taste receptor T1R1/T1R3. Food Chem. 2021;362:130249. doi: 10.1016/j.foodchem.2021.130249. - DOI - PubMed

LinkOut - more resources

Full text links
MDPI full text link MDPI Free PMC article
Cite

AltStyle によって変換されたページ (->オリジナル) /