Soybean paste has been a prominent condiment in East Asia for millennia.Nonetheless,the current methodologies for comprehensively assessing the quality of commercially available soybean paste through sensory evaluatio...Soybean paste has been a prominent condiment in East Asia for millennia.Nonetheless,the current methodologies for comprehensively assessing the quality of commercially available soybean paste through sensory evaluation or traditional instruments present significant challenges.In this study,contemporary detection techniques and machine learning methodologies were employed to quantitatively characterize and evaluate the overall quality of soybean paste.Sensory evaluations were conducted on 33 varieties of commercial soybean paste using three types of sensors:a colorimeter,an electronic nose(E-nose),and an electronic tongue(E-tongue)for detection purposes.Subsequently,machine learning models,including support vector regression(SVR),random forest,extreme gradient boosting,Bayesian ridge regression,ridge regression,k-nearest neighbors,and artificial neural network,were developed based on the sensory evaluation data to characterize and assess the overall quality of the soybean paste.The findings from both sensory evaluations and sensor detection indicated notable differences between the various soybean pastes.Soybean pastes can be distinguished using three sensors.The quantitative characterization model informed by the sensor data revealed that the SVR model exhibited the highest coefficient of determination(R^(2))of 0.9998 for the training set and 0.9970 for the prediction set,which was close to the ideal value of 1.Additionally,the root mean square error for the prediction set was the lowest at 0.5359.These results suggest that SVR demonstrates superior performance in cross-validation and testing,aligning closely with human sensory perceptions,thereby establishing it as the most effective predictive model.This study underscores the potential of integrating sensor data with modern machine learning techniques to supplement traditional sensory evaluations for comprehensive characterization and assessment of soybean paste quality.The outcomes of this study offer significant insights and guidance for the advancement of the soybean paste industry and the enhancement of soybean paste quality.展开更多
Sheep whey protein,a valuable resource for bioactive peptide production,is prone to contamination or often discarded,generating resource waste.This study explored novel milk-derived antimicrobial peptides(AMPs)for she...Sheep whey protein,a valuable resource for bioactive peptide production,is prone to contamination or often discarded,generating resource waste.This study explored novel milk-derived antimicrobial peptides(AMPs)for sheep milk preservation by evaluating the antimicrobial effects of whey protein hydrolyzed by four proteases.It utilized single-factor experiments and response surface methodology,combined with computer simulations and wet-lab validation.The results revealed that the hydrolysate obtained from neutral protease exhibited the strongest antimicrobial activity.Subsequently,394 peptide sequences were identified from the 1-3 kDa fraction of the neutral protease hydrolysate via ultrafiltration centrifugation and Liquid Chromatography-Tandem Mass Spectrometry.Through various bioinformatics analyses,machine learning,and AlphaFold3,three candidate peptides-LKAWSVARLSQKFPKA,TLSQLTKLGKPFK,and KKQTALVELLKHKPK-were selected for further evaluation.200 ns molecular dynamics simulations and gmx_mmpbsa calculations revealed LKAWS-VARLSQKFPKA exhibited superior membrane-binding ability and stableα-helix structure in the environments of Staphylococcus aureus and Escherichia coli than the other two peptides.The wet-lab experiments showed that it also disrupted bacterial membranes and caused intracellular leakage,demonstrating excellent antimicrobial activity and stability against Staphylococcus aureus and Escherichia coli,along with low hemolytic toxicity.Additionally,LKAWSVARLSQKFPKA at minimum inhibitory concentrations of 32μg/mL and 128μg/mL respectively effectively inhibited the growth of Staphylococcus aureus and Escherichia coli in sheep milk.Overall,these findings provided a theoretical basis for the application of sheep whey protein and the development of novel milk-derived AMPs.展开更多
基金supported by the National Natural Science Foundation of China(32572526)Liaoning Revitalization Talents Program(XLYC2402005,XLYC2213026)+1 种基金introduction of Talents(high-level)Research Start-up Fund Project of Shenyang Agricultural University(2023YJRC002)the Shenyang Science and Technology innovation Platform Project(21-103-0-14,21-104-0-28).
文摘Soybean paste has been a prominent condiment in East Asia for millennia.Nonetheless,the current methodologies for comprehensively assessing the quality of commercially available soybean paste through sensory evaluation or traditional instruments present significant challenges.In this study,contemporary detection techniques and machine learning methodologies were employed to quantitatively characterize and evaluate the overall quality of soybean paste.Sensory evaluations were conducted on 33 varieties of commercial soybean paste using three types of sensors:a colorimeter,an electronic nose(E-nose),and an electronic tongue(E-tongue)for detection purposes.Subsequently,machine learning models,including support vector regression(SVR),random forest,extreme gradient boosting,Bayesian ridge regression,ridge regression,k-nearest neighbors,and artificial neural network,were developed based on the sensory evaluation data to characterize and assess the overall quality of the soybean paste.The findings from both sensory evaluations and sensor detection indicated notable differences between the various soybean pastes.Soybean pastes can be distinguished using three sensors.The quantitative characterization model informed by the sensor data revealed that the SVR model exhibited the highest coefficient of determination(R^(2))of 0.9998 for the training set and 0.9970 for the prediction set,which was close to the ideal value of 1.Additionally,the root mean square error for the prediction set was the lowest at 0.5359.These results suggest that SVR demonstrates superior performance in cross-validation and testing,aligning closely with human sensory perceptions,thereby establishing it as the most effective predictive model.This study underscores the potential of integrating sensor data with modern machine learning techniques to supplement traditional sensory evaluations for comprehensive characterization and assessment of soybean paste quality.The outcomes of this study offer significant insights and guidance for the advancement of the soybean paste industry and the enhancement of soybean paste quality.
基金supported by the National Natural Science Foundation of China[Grant No.32172279]LiaoNing Revitalization Talents Program[Grant No.XLYC2213026,XLYC2402005]+2 种基金Liaoning Province Science and Technology Plan Project[Grant No.2024JH2/101900005]Introduction of talents(high-level)research start-up fund project of Shenyang Agricultural University[Grant No.2023YJRC002]Shenyang Science and technology innovation platform project[Grant No.21-103-0-14,21-104-0-28].
文摘Sheep whey protein,a valuable resource for bioactive peptide production,is prone to contamination or often discarded,generating resource waste.This study explored novel milk-derived antimicrobial peptides(AMPs)for sheep milk preservation by evaluating the antimicrobial effects of whey protein hydrolyzed by four proteases.It utilized single-factor experiments and response surface methodology,combined with computer simulations and wet-lab validation.The results revealed that the hydrolysate obtained from neutral protease exhibited the strongest antimicrobial activity.Subsequently,394 peptide sequences were identified from the 1-3 kDa fraction of the neutral protease hydrolysate via ultrafiltration centrifugation and Liquid Chromatography-Tandem Mass Spectrometry.Through various bioinformatics analyses,machine learning,and AlphaFold3,three candidate peptides-LKAWSVARLSQKFPKA,TLSQLTKLGKPFK,and KKQTALVELLKHKPK-were selected for further evaluation.200 ns molecular dynamics simulations and gmx_mmpbsa calculations revealed LKAWS-VARLSQKFPKA exhibited superior membrane-binding ability and stableα-helix structure in the environments of Staphylococcus aureus and Escherichia coli than the other two peptides.The wet-lab experiments showed that it also disrupted bacterial membranes and caused intracellular leakage,demonstrating excellent antimicrobial activity and stability against Staphylococcus aureus and Escherichia coli,along with low hemolytic toxicity.Additionally,LKAWSVARLSQKFPKA at minimum inhibitory concentrations of 32μg/mL and 128μg/mL respectively effectively inhibited the growth of Staphylococcus aureus and Escherichia coli in sheep milk.Overall,these findings provided a theoretical basis for the application of sheep whey protein and the development of novel milk-derived AMPs.
