In Silico Discovery and Sensory Validation of Umami Peptides in Fermented Sausages: A Study Integrating Deep Learning and Molecular Modeling

Deep learning has great potential in the field of functional peptide prediction. This study combines metagenomics and deep learning to efficiently discover potential umami peptides in fermented sausages. A candidate peptide library was generated using metagenomic data from fermented sausages, an int...

Full description

Saved in:
Bibliographic Details
Main Authors: Haochen Geng, Chunming Xu, Huijun Ma, Youxu Dai, Ziyou Jiang, Mingyue Yang, Danyang Zhu
Format: Article
Language:English
Published: MDPI AG 2025-07-01
Series:Foods
Subjects:
Online Access:https://www.mdpi.com/2304-8158/14/14/2422
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850077667488956416
author Haochen Geng
Chunming Xu
Huijun Ma
Youxu Dai
Ziyou Jiang
Mingyue Yang
Danyang Zhu
author_facet Haochen Geng
Chunming Xu
Huijun Ma
Youxu Dai
Ziyou Jiang
Mingyue Yang
Danyang Zhu
author_sort Haochen Geng
collection DOAJ
description Deep learning has great potential in the field of functional peptide prediction. This study combines metagenomics and deep learning to efficiently discover potential umami peptides in fermented sausages. A candidate peptide library was generated using metagenomic data from fermented sausages, an integrated deep learning model was constructed for prediction, and SHAP (SHapley Additive exPlanations) interpretability analysis was performed to elucidate the key amino acid features and contributions of the model in predicting umami peptides, screening the top ten peptides with the highest predicted probability. Subsequently, molecular docking was performed to assess the binding stability of these peptides with the umami receptor T1R1/T1R3, selecting the three peptides DDSMAATGL, DGEEDASM, and DEEEVDI with the most stable binding for further study. Docking analysis revealed the important roles of the key receptor residues Glu301, Arg277, Lys328, and His71 in hydrogen bond formation. Molecular dynamics simulations validated the robust integrity of the peptide–receptor associations. Finally, sensory evaluation demonstrated that these three peptides possessed significant umami characteristics, with low umami thresholds (0.11, 0.37, and 0.44 mg/mL, respectively). This study, based on metagenomics and deep learning, provides a high-throughput strategy for the discovery and validation of functional peptides.
format Article
id doaj-art-1e490f3692ec4ed6ab4bf44112ecb296
institution DOAJ
issn 2304-8158
language English
publishDate 2025-07-01
publisher MDPI AG
record_format Article
series Foods
spelling doaj-art-1e490f3692ec4ed6ab4bf44112ecb2962025-08-20T02:45:45ZengMDPI AGFoods2304-81582025-07-011414242210.3390/foods14142422In Silico Discovery and Sensory Validation of Umami Peptides in Fermented Sausages: A Study Integrating Deep Learning and Molecular ModelingHaochen Geng0Chunming Xu1Huijun Ma2Youxu Dai3Ziyou Jiang4Mingyue Yang5Danyang Zhu6School of Computer and Artificial Intelligence, Beijing Technology and Business University, Beijing 100048, ChinaSchool of Light Industry Science and Engineering, Beijing Technology and Business University, Beijing 100048, ChinaSchool of Computer and Artificial Intelligence, Beijing Technology and Business University, Beijing 100048, ChinaSchool of Light Industry Science and Engineering, Beijing Technology and Business University, Beijing 100048, ChinaSchool of Computer and Artificial Intelligence, Beijing Technology and Business University, Beijing 100048, ChinaSchool of Computer and Artificial Intelligence, Beijing Technology and Business University, Beijing 100048, ChinaSchool of Languages and Communication, Beijing Technology and Business University, Beijing 100048, ChinaDeep learning has great potential in the field of functional peptide prediction. This study combines metagenomics and deep learning to efficiently discover potential umami peptides in fermented sausages. A candidate peptide library was generated using metagenomic data from fermented sausages, an integrated deep learning model was constructed for prediction, and SHAP (SHapley Additive exPlanations) interpretability analysis was performed to elucidate the key amino acid features and contributions of the model in predicting umami peptides, screening the top ten peptides with the highest predicted probability. Subsequently, molecular docking was performed to assess the binding stability of these peptides with the umami receptor T1R1/T1R3, selecting the three peptides DDSMAATGL, DGEEDASM, and DEEEVDI with the most stable binding for further study. Docking analysis revealed the important roles of the key receptor residues Glu301, Arg277, Lys328, and His71 in hydrogen bond formation. Molecular dynamics simulations validated the robust integrity of the peptide–receptor associations. Finally, sensory evaluation demonstrated that these three peptides possessed significant umami characteristics, with low umami thresholds (0.11, 0.37, and 0.44 mg/mL, respectively). This study, based on metagenomics and deep learning, provides a high-throughput strategy for the discovery and validation of functional peptides.https://www.mdpi.com/2304-8158/14/14/2422deep learningmolecular dockingumami peptidespeptide prediction
spellingShingle Haochen Geng
Chunming Xu
Huijun Ma
Youxu Dai
Ziyou Jiang
Mingyue Yang
Danyang Zhu
In Silico Discovery and Sensory Validation of Umami Peptides in Fermented Sausages: A Study Integrating Deep Learning and Molecular Modeling
Foods
deep learning
molecular docking
umami peptides
peptide prediction
title In Silico Discovery and Sensory Validation of Umami Peptides in Fermented Sausages: A Study Integrating Deep Learning and Molecular Modeling
title_full In Silico Discovery and Sensory Validation of Umami Peptides in Fermented Sausages: A Study Integrating Deep Learning and Molecular Modeling
title_fullStr In Silico Discovery and Sensory Validation of Umami Peptides in Fermented Sausages: A Study Integrating Deep Learning and Molecular Modeling
title_full_unstemmed In Silico Discovery and Sensory Validation of Umami Peptides in Fermented Sausages: A Study Integrating Deep Learning and Molecular Modeling
title_short In Silico Discovery and Sensory Validation of Umami Peptides in Fermented Sausages: A Study Integrating Deep Learning and Molecular Modeling
title_sort in silico discovery and sensory validation of umami peptides in fermented sausages a study integrating deep learning and molecular modeling
topic deep learning
molecular docking
umami peptides
peptide prediction
url https://www.mdpi.com/2304-8158/14/14/2422
work_keys_str_mv AT haochengeng insilicodiscoveryandsensoryvalidationofumamipeptidesinfermentedsausagesastudyintegratingdeeplearningandmolecularmodeling
AT chunmingxu insilicodiscoveryandsensoryvalidationofumamipeptidesinfermentedsausagesastudyintegratingdeeplearningandmolecularmodeling
AT huijunma insilicodiscoveryandsensoryvalidationofumamipeptidesinfermentedsausagesastudyintegratingdeeplearningandmolecularmodeling
AT youxudai insilicodiscoveryandsensoryvalidationofumamipeptidesinfermentedsausagesastudyintegratingdeeplearningandmolecularmodeling
AT ziyoujiang insilicodiscoveryandsensoryvalidationofumamipeptidesinfermentedsausagesastudyintegratingdeeplearningandmolecularmodeling
AT mingyueyang insilicodiscoveryandsensoryvalidationofumamipeptidesinfermentedsausagesastudyintegratingdeeplearningandmolecularmodeling
AT danyangzhu insilicodiscoveryandsensoryvalidationofumamipeptidesinfermentedsausagesastudyintegratingdeeplearningandmolecularmodeling