Machine Learning and Multi-Omics Integration to Reveal Biomarkers and Microbial Community Assembly Differences in Abnormal Stacking Fermentation of Sauce-Flavor <i>Baijiu</i>
Stacking fermentation is critical in sauce-flavor <i>Baijiu</i> production, but winter production often sees abnormal fermentations, like Waistline and Sub-Temp fermentation, affecting yield and quality. This study used three machine learning models (Logistic Regression, KNN, and Random...
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2025-01-01
|
| Series: | Foods |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2304-8158/14/2/245 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832588472434556928 |
|---|---|
| author | Shuai Li Yueran Han Ming Yan Shuyi Qiu Jun Lu |
| author_facet | Shuai Li Yueran Han Ming Yan Shuyi Qiu Jun Lu |
| author_sort | Shuai Li |
| collection | DOAJ |
| description | Stacking fermentation is critical in sauce-flavor <i>Baijiu</i> production, but winter production often sees abnormal fermentations, like Waistline and Sub-Temp fermentation, affecting yield and quality. This study used three machine learning models (Logistic Regression, KNN, and Random Forest) combined with multi-omics (metagenomics and flavoromics) to develop a classification model for abnormal fermentation. SHAP analysis identified 13 Sub-Temp Fermentation and 9 Waistline microbial biomarkers, along with 9 Sub-Temp Fermentation and 12 Waistline flavor biomarkers. <i>Komagataeibacter</i> and <i>Gluconacetobacter</i> are key for normal fermentation, while <i>Ligilactobacillus</i> and <i>Lactobacillus</i> are critical in abnormal cases. Excessive acid and ester markers caused unbalanced aromas in abnormal fermentations. Additionally, ecological models reveal the bacterial community assembly in abnormal fermentations was influenced by stochastic factors, while the fungal community assembly was influenced by deterministic factors. RDA analysis shows that moisture significantly drove Sub-Temp fermentation. Differential gene analysis and KEGG pathway enrichment identify metabolic pathways for flavor markers. This study provides a theoretical basis for regulating stacking fermentation and ensuring <i>Baijiu</i> quality. |
| format | Article |
| id | doaj-art-3398f81b615c472ea22a17dc512a9bfd |
| institution | Kabale University |
| issn | 2304-8158 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Foods |
| spelling | doaj-art-3398f81b615c472ea22a17dc512a9bfd2025-01-24T13:33:00ZengMDPI AGFoods2304-81582025-01-0114224510.3390/foods14020245Machine Learning and Multi-Omics Integration to Reveal Biomarkers and Microbial Community Assembly Differences in Abnormal Stacking Fermentation of Sauce-Flavor <i>Baijiu</i>Shuai Li0Yueran Han1Ming Yan2Shuyi Qiu3Jun Lu4College of Liquor and Food Engineering, Key Laboratory of Fermentation Engineering and Biological Pharmacy of Guizhou Province, Guizhou University, Guiyang 550025, ChinaGuizhou Guotai Distillery Co., Ltd., Renhuai 564501, ChinaGuizhou Guotai Distillery Co., Ltd., Renhuai 564501, ChinaCollege of Liquor and Food Engineering, Key Laboratory of Fermentation Engineering and Biological Pharmacy of Guizhou Province, Guizhou University, Guiyang 550025, ChinaGuizhou Guotai Distillery Co., Ltd., Renhuai 564501, ChinaStacking fermentation is critical in sauce-flavor <i>Baijiu</i> production, but winter production often sees abnormal fermentations, like Waistline and Sub-Temp fermentation, affecting yield and quality. This study used three machine learning models (Logistic Regression, KNN, and Random Forest) combined with multi-omics (metagenomics and flavoromics) to develop a classification model for abnormal fermentation. SHAP analysis identified 13 Sub-Temp Fermentation and 9 Waistline microbial biomarkers, along with 9 Sub-Temp Fermentation and 12 Waistline flavor biomarkers. <i>Komagataeibacter</i> and <i>Gluconacetobacter</i> are key for normal fermentation, while <i>Ligilactobacillus</i> and <i>Lactobacillus</i> are critical in abnormal cases. Excessive acid and ester markers caused unbalanced aromas in abnormal fermentations. Additionally, ecological models reveal the bacterial community assembly in abnormal fermentations was influenced by stochastic factors, while the fungal community assembly was influenced by deterministic factors. RDA analysis shows that moisture significantly drove Sub-Temp fermentation. Differential gene analysis and KEGG pathway enrichment identify metabolic pathways for flavor markers. This study provides a theoretical basis for regulating stacking fermentation and ensuring <i>Baijiu</i> quality.https://www.mdpi.com/2304-8158/14/2/245machine learningmulti-omicscommunity assemblybiomarkerabnormal fermentation |
| spellingShingle | Shuai Li Yueran Han Ming Yan Shuyi Qiu Jun Lu Machine Learning and Multi-Omics Integration to Reveal Biomarkers and Microbial Community Assembly Differences in Abnormal Stacking Fermentation of Sauce-Flavor <i>Baijiu</i> Foods machine learning multi-omics community assembly biomarker abnormal fermentation |
| title | Machine Learning and Multi-Omics Integration to Reveal Biomarkers and Microbial Community Assembly Differences in Abnormal Stacking Fermentation of Sauce-Flavor <i>Baijiu</i> |
| title_full | Machine Learning and Multi-Omics Integration to Reveal Biomarkers and Microbial Community Assembly Differences in Abnormal Stacking Fermentation of Sauce-Flavor <i>Baijiu</i> |
| title_fullStr | Machine Learning and Multi-Omics Integration to Reveal Biomarkers and Microbial Community Assembly Differences in Abnormal Stacking Fermentation of Sauce-Flavor <i>Baijiu</i> |
| title_full_unstemmed | Machine Learning and Multi-Omics Integration to Reveal Biomarkers and Microbial Community Assembly Differences in Abnormal Stacking Fermentation of Sauce-Flavor <i>Baijiu</i> |
| title_short | Machine Learning and Multi-Omics Integration to Reveal Biomarkers and Microbial Community Assembly Differences in Abnormal Stacking Fermentation of Sauce-Flavor <i>Baijiu</i> |
| title_sort | machine learning and multi omics integration to reveal biomarkers and microbial community assembly differences in abnormal stacking fermentation of sauce flavor i baijiu i |
| topic | machine learning multi-omics community assembly biomarker abnormal fermentation |
| url | https://www.mdpi.com/2304-8158/14/2/245 |
| work_keys_str_mv | AT shuaili machinelearningandmultiomicsintegrationtorevealbiomarkersandmicrobialcommunityassemblydifferencesinabnormalstackingfermentationofsauceflavoribaijiui AT yueranhan machinelearningandmultiomicsintegrationtorevealbiomarkersandmicrobialcommunityassemblydifferencesinabnormalstackingfermentationofsauceflavoribaijiui AT mingyan machinelearningandmultiomicsintegrationtorevealbiomarkersandmicrobialcommunityassemblydifferencesinabnormalstackingfermentationofsauceflavoribaijiui AT shuyiqiu machinelearningandmultiomicsintegrationtorevealbiomarkersandmicrobialcommunityassemblydifferencesinabnormalstackingfermentationofsauceflavoribaijiui AT junlu machinelearningandmultiomicsintegrationtorevealbiomarkersandmicrobialcommunityassemblydifferencesinabnormalstackingfermentationofsauceflavoribaijiui |