基于气相色谱-质谱法和随机森林算法的不同产地香菇指纹图谱研究
|
摘要
本文采用气相色谱-质谱(GC-MS)方法,并结合随机森林算法对来自不同产地的香菇进行归属分析。首先利用GC-MS法得到各产地香菇的指纹图谱,进一步采用自适应迭代惩罚的偏最小二乘法(adaptive iteratively reweighted Penalized Least Squares,airPLS)和多尺度色谱峰校正,分别对指纹图谱进行背景扣除和保留时间校正等预处理后,再进行定性定量分析,得到各指纹图谱的主要的特征物质,进而采用随机森林算法对不同产地的香菇进行判别分析。本方法将GC-MS法和随机森林算法相融合,能够准确地区分不同产地的香菇样品。
In this study,GC-MS and random forest method were used to analyze and distinguish Lentinus edodes samples collected from different originals.Firstly,the fingerprints of samples were obtained by using GC-MS,then,adaptive iteratively reweighted Penalized Least Squares(airPLS)and multi-scale chromatographic calibration approaches were adopted to process these chromatographic fingerprints,the main characteristic components from these sample were qualitatively and quantitatively analyzed.Based on these obtained characteristic components,random forest method was used to find the similarity of samples and further classify different originals' samples.The proposed method coupling GC-MS and random forest method could accurately distinguish different originals' Lentinus edodes samples,and could be further used to evaluate the quality of Lentinus edodes.
In this study,GC-MS and random forest method were used to analyze and distinguish Lentinus edodes samples collected from different originals.Firstly,the fingerprints of samples were obtained by using GC-MS,then,adaptive iteratively reweighted Penalized Least Squares(airPLS)and multi-scale chromatographic calibration approaches were adopted to process these chromatographic fingerprints,the main characteristic components from these sample were qualitatively and quantitatively analyzed.Based on these obtained characteristic components,random forest method was used to find the similarity of samples and further classify different originals' samples.The proposed method coupling GC-MS and random forest method could accurately distinguish different originals' Lentinus edodes samples,and could be further used to evaluate the quality of Lentinus edodes.
引文
[1] YANG M Y,LONG Z F,LI J.Food Science(杨铭绎,龙志芳,李健.食品科学),2006,27(5):223.
[2] CHEN W C,YANG M,LI W,et.al.Journal of Food Science and Biotechnology(陈万超,杨焱,李文,等.食品与生物技术学报),2016,35(10):1075.
[3] LI Q,HAI Y,SHI H Q,et al.Chemistry and Bioengineering(李秦,海洋,师会勤,等.化学与生物工程),2010,27(2):87.
[4] Beluhan S,Ranogajec A.Food Chemistry,2011,124:1076.
[5] Kalac P.Food Chemistry,2009,113:9.
[6] Malheiro R,Pinho P G,Soares S.Food Research International,2013,54(3):186.
[7] YANG J L,MEI W L,DONG W H.et al.Chinese Traditional Patent Medicine(杨锦玲,梅文莉,董文化,等.中成药),2016,38(8):1765.
[8] LIANG M J,HE L C,LI Y M.Journal of Chinese Mass Spectrometry Society(梁明金,贺浪冲,李永茂.质谱学报),2004,3(25)::150.
[9] Taofiq O,Paramás A M,Martins A,et al.Industrial Crops and Products,2016,90(3):38.
[10]LI B Y,LIANG Y Z,HU Y.et al.Chinese Journal of Analytical Chemistry(李博岩,梁逸曾,胡芸,等.分析化学),2004,32(3):313.
[11]LI S F,ZHANG X,LI J.et al.Transactions of the Chinese Society of Agricultural Engineering(李水芳,张欣,李姣娟,等.农业工程学报),2016,30(4):249.
[12]Breiman L.Machine learning,2001,45(1):5.
[2] CHEN W C,YANG M,LI W,et.al.Journal of Food Science and Biotechnology(陈万超,杨焱,李文,等.食品与生物技术学报),2016,35(10):1075.
[3] LI Q,HAI Y,SHI H Q,et al.Chemistry and Bioengineering(李秦,海洋,师会勤,等.化学与生物工程),2010,27(2):87.
[4] Beluhan S,Ranogajec A.Food Chemistry,2011,124:1076.
[5] Kalac P.Food Chemistry,2009,113:9.
[6] Malheiro R,Pinho P G,Soares S.Food Research International,2013,54(3):186.
[7] YANG J L,MEI W L,DONG W H.et al.Chinese Traditional Patent Medicine(杨锦玲,梅文莉,董文化,等.中成药),2016,38(8):1765.
[8] LIANG M J,HE L C,LI Y M.Journal of Chinese Mass Spectrometry Society(梁明金,贺浪冲,李永茂.质谱学报),2004,3(25)::150.
[9] Taofiq O,Paramás A M,Martins A,et al.Industrial Crops and Products,2016,90(3):38.
[10]LI B Y,LIANG Y Z,HU Y.et al.Chinese Journal of Analytical Chemistry(李博岩,梁逸曾,胡芸,等.分析化学),2004,32(3):313.
[11]LI S F,ZHANG X,LI J.et al.Transactions of the Chinese Society of Agricultural Engineering(李水芳,张欣,李姣娟,等.农业工程学报),2016,30(4):249.
[12]Breiman L.Machine learning,2001,45(1):5.