Machine learning-based prediction of volatile compounds profiles in Saccharomyces cerevisiae fermentation simulating canned meat

Abstract Aroma and precision fermentation converge in exciting ways, enabling the precise production of aromatic compounds. Precision fermentation employs engineered microorganisms to create and refine scents and aromas with high accuracy, allowing for customizable aromas and opening new possibiliti...

Full description

Saved in:
Bibliographic Details
Main Authors: Lin Du, Shujie Wang, Yongyan Chen, Zhongxu Zhu, Hai-Xi Sun, Tsan-Yu Chiu
Format: Article
Language:English
Published: Nature Portfolio 2025-06-01
Series:npj Science of Food
Online Access:https://doi.org/10.1038/s41538-025-00435-6
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850136944830316544
author Lin Du
Shujie Wang
Yongyan Chen
Zhongxu Zhu
Hai-Xi Sun
Tsan-Yu Chiu
author_facet Lin Du
Shujie Wang
Yongyan Chen
Zhongxu Zhu
Hai-Xi Sun
Tsan-Yu Chiu
author_sort Lin Du
collection DOAJ
description Abstract Aroma and precision fermentation converge in exciting ways, enabling the precise production of aromatic compounds. Precision fermentation employs engineered microorganisms to create and refine scents and aromas with high accuracy, allowing for customizable aromas and opening new possibilities for both culinary experiences and consumer products. Structured data on volatile compounds from canned meat and fermented products was compiled to train machine learning (ML) models aimed at predicting volatile compounds and simulating meat aroma in Saccharomyces cerevisiae. We proposed a framework encompassing data generation and preprocessing, feature selection, model construction, and evaluation. Principal Component Analysis ensured data quality control, while embedding-based feature selection identified key volatile compounds. A two-stage model was developed to quantify the importance of volatile compounds and predict meat aroma and the gradient-boosted decision trees (GBDT) model demonstrated optimal performance. Our study guides simulating meat aroma through fermentation, offering a promising approach for plant-based meat flavoring.
format Article
id doaj-art-f9fa36e2d78e4f9aaa0ef12eb09de08a
institution OA Journals
issn 2396-8370
language English
publishDate 2025-06-01
publisher Nature Portfolio
record_format Article
series npj Science of Food
spelling doaj-art-f9fa36e2d78e4f9aaa0ef12eb09de08a2025-08-20T02:30:59ZengNature Portfolionpj Science of Food2396-83702025-06-019111310.1038/s41538-025-00435-6Machine learning-based prediction of volatile compounds profiles in Saccharomyces cerevisiae fermentation simulating canned meatLin Du0Shujie Wang1Yongyan Chen2Zhongxu Zhu3Hai-Xi Sun4Tsan-Yu Chiu5College of Life Sciences, University of Chinese Academy of SciencesBGIBGIBiomics Center, Hangzhou Institute of Medicine (HIM), Chinese Academy of SciencesCollege of Life Sciences, University of Chinese Academy of SciencesBGIAbstract Aroma and precision fermentation converge in exciting ways, enabling the precise production of aromatic compounds. Precision fermentation employs engineered microorganisms to create and refine scents and aromas with high accuracy, allowing for customizable aromas and opening new possibilities for both culinary experiences and consumer products. Structured data on volatile compounds from canned meat and fermented products was compiled to train machine learning (ML) models aimed at predicting volatile compounds and simulating meat aroma in Saccharomyces cerevisiae. We proposed a framework encompassing data generation and preprocessing, feature selection, model construction, and evaluation. Principal Component Analysis ensured data quality control, while embedding-based feature selection identified key volatile compounds. A two-stage model was developed to quantify the importance of volatile compounds and predict meat aroma and the gradient-boosted decision trees (GBDT) model demonstrated optimal performance. Our study guides simulating meat aroma through fermentation, offering a promising approach for plant-based meat flavoring.https://doi.org/10.1038/s41538-025-00435-6
spellingShingle Lin Du
Shujie Wang
Yongyan Chen
Zhongxu Zhu
Hai-Xi Sun
Tsan-Yu Chiu
Machine learning-based prediction of volatile compounds profiles in Saccharomyces cerevisiae fermentation simulating canned meat
npj Science of Food
title Machine learning-based prediction of volatile compounds profiles in Saccharomyces cerevisiae fermentation simulating canned meat
title_full Machine learning-based prediction of volatile compounds profiles in Saccharomyces cerevisiae fermentation simulating canned meat
title_fullStr Machine learning-based prediction of volatile compounds profiles in Saccharomyces cerevisiae fermentation simulating canned meat
title_full_unstemmed Machine learning-based prediction of volatile compounds profiles in Saccharomyces cerevisiae fermentation simulating canned meat
title_short Machine learning-based prediction of volatile compounds profiles in Saccharomyces cerevisiae fermentation simulating canned meat
title_sort machine learning based prediction of volatile compounds profiles in saccharomyces cerevisiae fermentation simulating canned meat
url https://doi.org/10.1038/s41538-025-00435-6
work_keys_str_mv AT lindu machinelearningbasedpredictionofvolatilecompoundsprofilesinsaccharomycescerevisiaefermentationsimulatingcannedmeat
AT shujiewang machinelearningbasedpredictionofvolatilecompoundsprofilesinsaccharomycescerevisiaefermentationsimulatingcannedmeat
AT yongyanchen machinelearningbasedpredictionofvolatilecompoundsprofilesinsaccharomycescerevisiaefermentationsimulatingcannedmeat
AT zhongxuzhu machinelearningbasedpredictionofvolatilecompoundsprofilesinsaccharomycescerevisiaefermentationsimulatingcannedmeat
AT haixisun machinelearningbasedpredictionofvolatilecompoundsprofilesinsaccharomycescerevisiaefermentationsimulatingcannedmeat
AT tsanyuchiu machinelearningbasedpredictionofvolatilecompoundsprofilesinsaccharomycescerevisiaefermentationsimulatingcannedmeat