1.宁夏大学 食品科学与工程学院,宁夏 银川 750021
2.宁夏大学 动物科技学院,宁夏 银川 750021
王松磊,博士,教授,研究方向:农产品加工与无损检测,E-mail:wangsonglei163@126.com
收稿:2026-02-09,
修回:2026-03-23,
录用:2026-04-10,
网络首发:2026-04-29,
纸质出版:2026-06-15
移动端阅览
徐海龙,于建国,王彦云,崔佳锐,李海峰,王松磊.基于高光谱成像与深度学习的滩羊PGK1和PKM2酶水平预测研究[J].分析测试学报,2026,45(06):1-11.
XU Hai-long,YU Jian-guo,WANG Yan-yun,CUI Jia-rui,LI Hai-feng,WANG Song-lei.Nondestructive Prediction of PGK1 and PKM2 Enzyme Levels in Tan Sheep Using Hyperspectral Imaging and Deep Learning[J].Journal of Instrumental Analysis,2026,45(06):1-11.
徐海龙,于建国,王彦云,崔佳锐,李海峰,王松磊.基于高光谱成像与深度学习的滩羊PGK1和PKM2酶水平预测研究[J].分析测试学报,2026,45(06):1-11. DOI: 10.12452/j.fxcsxb.26020901.
XU Hai-long,YU Jian-guo,WANG Yan-yun,CUI Jia-rui,LI Hai-feng,WANG Song-lei.Nondestructive Prediction of PGK1 and PKM2 Enzyme Levels in Tan Sheep Using Hyperspectral Imaging and Deep Learning[J].Journal of Instrumental Analysis,2026,45(06):1-11. DOI: 10.12452/j.fxcsxb.26020901.
宰后肌肉糖酵解速率异常是异质肉(PSE/DFD)形成的重要驱动因素之一。磷酸甘油酸激酶1(PGK1)与丙酮酸激酶M2(PKM2)分别催化糖酵解过程中两步关键底物水平磷酸化反应,可在一定程度上表征宰后能量代谢状态。该研究以滩羊肌肉为对象,测定PGK1与PKM2的免疫反应性水平,构建可见-近红外高光谱成像(Vis-NIR HSI)结合二维相关光谱(2D-COS)的无损评估框架以增强关键谱段解析与模型可解释性。2D-COS识别出5个敏感特征波段(476、562、605、715和800 nm),其光谱响应可能与肌红蛋白状态变化以及水分结合状态/组织结构差异相关。进一步系统比较了多种预处理与特征提取方法在偏最小二乘回归(PLSR)、随机森林(RF)以及卷积神经网络(CNN)中的预测效果。结果表明,结合变量组合群体分析-迭代保留信息变量(VCPA-IRIV)的CNN模型表现最佳:PGK1预测集
R
P
2
=0.892 0,RMSEP=38.365 3,RPD=3.093 5;PKM2预测集
R
P
2
=0.903 0,RMSEP=18.177 8,RPD=3.265 9。基于最优模型实现像素级伪彩色可视化,直观呈现了不同贮藏阶段两种酶水平的空间异质性与动态变化趋势。本研究表明,Vis-NIR HSI结合2D-COS与深度学习方法可实现羊肉PGK1和PKM2水平的无损预测,为代谢相关指标的快速分级与过程监测提供技术支撑。
Abnormal postmortem glycolytic rates are among the primary driver
s of meat quality defects,such as pale,soft,exudative(PSE) and dark,firm,dry(DFD) conditions. Phosphoglycerate kinase 1(PGK1) and pyruvate kinase M2(PKM2) catalyze two key substrate-level phosphorylation steps in glycolysis and can therefore partially reflect postmortem energy metabolism status. In this study,Tan sheep muscle was used as the research object. The immunoreactivity levels of PGK1 and PKM2 were determined,and a nondestructive evaluation framework integrating visible-near-infrared hyperspectral imaging(Vis-NIR HSI) with two-dimensional correlation spectroscopy(2D-COS) was developed to enhance sensitive band interpretation and model explainability. Five sensitive wavelengths(476,562,605,715,and 800 nm) were identified by 2D-COS,and their spectral responses were plausibly associated with changes in myoglobin state and differences in water-binding status and/or tissue-structure-related scattering. Furthermore,multiple preprocessing and feature extraction strategies were systematically compared across partial least squares regression(PLSR),random forest(RF),and convolutional neural network(CNN) models. The best performance was achieved by the CNN model coupled with variable combination population analysis-iteratively retaining informative variables(VCPA-IRIV),yielding for PGK1:
R
P
2
=0.892 0,RMSEP=38.365 3,RPD=3.093 5;and for PKM2:
R
P
2
=0.903 0,RMSEP=18.177 8,RPD=3.265 9 in the prediction set. Pixel-wise pseudo color visualization based on the optimal models intuitively revealed the spatial heterogeneity and dynamic evolution of the two enzyme levels across different storage stages. These results demonstrate that Vis-NIR HSI combined with 2D-COS and deep learning enables nondestructive prediction of PGK1 and PKM2 enzyme levels in mutton,providing technical support for rapid grading and process monitoring of metabolism-related indicators.
Zhang L L , Gao S , Ma M Y , Xiao Y Y , Yu T , Jiang Q J , Li Y L , Luo R M . Food Sci. (张玲玲,高爽,马梦瑶,肖玉莹,于婷,江启健,李亚蕾,罗瑞明. 食品科学), 2026 , 47 ( 5 ): 50 - 61 .
Huang C Y , Zhang D Q , Wang Z Y , Zhao Y X , Blecker C , Li S B , Zheng X C , Chen L . Food Chem. , 2023 , 427 : 136739 .
Huang C Y , Xiang C , Wang F Z , Blecker C , Wang Z Y , Chen L . Food Front. , 2024 , 5 ( 4 ): 1629 - 1641 .
Ma X , Li N , Wang R F , Ma J X , Zhu N H , Li T T , Zhang Z X , Li H F , Wang S L , Zhang H H . Chemom. Intell. Lab. Syst. , 2026 , 268 : 105575 .
Liu S , Cui J R , Lv Y , Wang S L . Food Res. Int. , 2025 , 205 : 116000 .
Xi Q B , Chen Q M , Ahmad W , Pan J , Zhao S G , Xia Y , Ouyang Q , Chen Q S . Food Chem. , 2025 , 481 : 143997 .
Yi W G , Zhao X Y , Yun X Y , Wang S L , Dong T . Food Res. Int. , 2025 , 203 : 115905 .
Noda I . Appl. Spectrosc. , 1993 , 47 ( 9 ): 1329 - 1336 .
Penf S , Wang F P , Wei D B , Wang C P , Ma H J , Du Y G . J. Environ. Sci. , 2025 , 147 : 200 - 216 .
Liu S J , Dong F J , Hao J , Guo J H , Wang S L , Luo R M , Lv Y , Cui J R . Spectrochim . Acta A , 2023 , 291 : 122342 .
Hao J , Cui J R , Liu S J , Lv Y , Zhang Z X , Wang S L . Food Chem. , 2025 , 493 : 145727 .
Cui J R , Cao S B , Hao J , Zhang Y , Gao S , Li J S , Fatimah , Wu L G . Ind. Crops Prod. , 2025 , 236 : 121909 .
León-Ecay S , Insausti K , López-Maestresalas A , Prieto N . Meat Sci. , 2025 , 228 : 109893 .
Dong F J , Bi Y Z , Hao J , Liu S J , Yi W G , Yu W J , Lv Y , Cui J R , Li H , Xian J H , Chen S C , Wang S L . Food Chem. , 2024 , 440 : 138040 .
Xiao D , Yu P , Guo X , Luan M Q , Li F X , Yang J , Zhou J H . J. Instrum. Anal. (肖丹,于苹,郭雪,栾美琪,李飞羽,杨健,周骏辉. 分析测试学报), 2026 , 45 ( 3 ): 591 - 599 .
Ma C , Zhang W G , Zhang J , Zhou L , Xing L J , Liu R . J . Adv. Res. , 2025 .
Huang C Y , Zhang D Q , Blecker C , Zhao Y X , Xiang C , Wang Z Y , Li S B , Chen L . Food Chem. X , 2024 , 21 : 101125 .
Yang N , Liang X L , Cao J X , Zhang Q , Tan Y Z , Xu B T , Yang Y L , Wang Y , Yang Q J , Liu H , Liu J . Meat Sci. , 2022 , 185 : 108723 .
Guo Z B , Chen C , Ma G Y , Yu Q , Zhang L . Food Chem. X , 2023 , 20 : 100891 .
Ismail A , Park S , Kim H J , Hong G , Kim G , Jo C . LWT-Food Sci . Technol. , 2025 , 216 : 117302 .
Ren W J , Jiang Q Q , Qi W L . Chem. Biol. Technol. Agric. , 2025 , 12 ( 1 ): 32 .
Zheng X C , Chen L , Li X , Zhang D Q . Foods , 2023 , 12 ( 2 ): 300 .
Feng Y J , Dong F J , Wu C , Cui J R , Wang G X , Zhang Z X , Cao S M , Liu S J , Li H , Shi Y K , Yu J G , Wang S L . Food Res. Int. , 2025 , 204 : 115877 .
Ma C , Zhang J , Zhang R , Zhou L , Ni L X , Zhang W G . Food Chem. X , 2024 , 24 : 101913 .
Waga M , Nakade K . Meat Sci. , 2025 , 219 : 109664 .
Liu Z Y , Li L N , Xu W M , Xu X S , Cui Z C , Jia L C , Lv W H , Shen Z H , Shu R . Remote Sens. , 2023 , 15 ( 13 ): 3311 .
Zhang W , Kasun L C , Wang Q J , Zheng Y J , Lin Z P . Sensors , 2022 , 22 ( 24 ): 9764 .
Wang Z T , Zhang T S , Ding H Y , Zhao S Y , Fan Y , Qi D , Dai Y J , Liu Z Y . Microchem. J. , 2025 , 218 : 115161 .
0
浏览量
4
下载量
0
CSCD
关联资源
相关文章
相关作者
相关机构
京公网安备11010802024621
