Machine learning discrimination and prediction of different quality grades of sauce-flavor based on biomarker and key flavor compounds screening.

The quality grade of base directly determines the final quality of sauce-flavor . However, traditional methods for assessing these grades often rely on subjective experience, lacking objectivity and accuracy. This study used GC-FID, combined with quantitative descriptive analysis (QDA) and odor activity value (OAV), to identify 27 key flavor compounds, including acetic acid, propionic acid, ethyl oleate, and isoamyl alcohol etc., as crucial contributors to quality grade differences. Sixteen bacterial biomarkers, including and etc., and 7 fungal biomarkers, including and etc., were identified as key microorganisms influencing these differences. Additionally, reducing sugar content in significantly impacted base quality. Finally, 11 machine learning classification models and 9 prediction models were evaluated, leading to the selection of the optimal model for accurate quality grade classification and prediction. This study provides a foundation for improving the evaluation system of sauce-flavor and ensuring consistent quality.