Research on Batch Classification of γ-Polyglutamic-Acid Fermentation Based on ATR-FTIR Spectroscopy

doi:10.12068/j.issn.1005-3026.2022.10.002

Abstract

Abstract: Attenuated total reflection Fourier transform infrared spectroscopy(ATR-FTIR)technology is utilized to quickly identify and detect different fermentation batches for γ-polyglutamic-acid(γ-PGA). Based on partial least squares discriminant analysis(PLSDA)， five classification models were established to distinguish each batch from other batches， which performed well on several individual evaluation indicators(e.g.， accuracy). In order to improve the model performance on all the indicators(e.g.， accuracy， precision， sensitivity， etc.)and the model interpretability， three wavenumber selection methods including subwindow permutation analysis(SPA)， competitive adaptive reweighted sampling(CARS)and random frog(RF)were combined with PLSDA to extract key wavenumbers and then established the corresponding classification models. Experimental results show that all the performance indicators of PLSDA combined with wavenumber selection(except CARS-PLSDA)are improved. Additionally， both the model complexity and interpretability are improved. Therefore， ATR-FTIR technology combined with SPA-PLSDA or RF-PLSDA method can realize rapid identification of different γ-PGA fermentation batches.

Key words: attenuated total reflection; γ-polyglutamic-acid (γ-PGA); partial least squares discriminant analysis(PLSDA); competitive adaptive; wavenumber selection

CLC Number:

O433.4

SHAN Peng， WU Zhui， HE Nian， LIU Long-xing. Research on Batch Classification of γ-Polyglutamic-Acid Fermentation Based on ATR-FTIR Spectroscopy[J]. Journal of Northeastern University(Natural Science), 2022, 43(10): 1376-1382.

References

[1]邓星波，邹水洋，朱丹，等.γ-PGA的保湿性研究［J］.广州化工，2019，47(6):48-50.(Deng Xing-bo，Zou Shui-yang，Zhu Dan，et al.Research on moisturizing properties of γ-PGA ［J］.Guangzhou Chemical Industry，2019，47(6):48-50.)
[2]邹水洋，张树友，贾梦影，等.一种从发酵液中高效提取γ-PGA的工艺:CN105837815A［P］.2016.(Zou Shui-yang，Zhang Shu-you，Jia Meng-ying，et al.A process for efficient extraction of γ-PGA from fermentation broth:CN105837815A［P］.2016.)
[3]朱广跃，杨卫，吴健，等.HPLC法定量分析微生物法制备液中产物γ-氨基丁酸和底物L-谷氨酸［J］.食品科学，2015(24):190-194.(Zhu Guang-yue，Yang Wei，Wu Jian，et al.Quantitative analysis of product γ-aminobutyric acid and substrate L-glutamic acid in microbial preparation solution by HPLC ［J］.Food Science，2015(24):190-194.)
[4]陈旭升，李树，张超，等.微生物合成ε-聚赖氨酸的结构鉴定及其抑菌活性的研究［J］.食品与发酵工业，2008(9):54-57.(Chen Xu-sheng，Li Shu，Zhang Chao，et al.Structural identification and antibacterial activity of ε-polylysine synthesized by microorganisms［J］.Food and Fermentation Industry，2008(9):54-57.)
[5]黄红英，尹齐和.傅里叶变换衰减全反射红外光谱法(ATR-FTIR)的原理与应用进展［J］.中山大学研究生学刊(自然科学医学版)，2011，32(1):20-31.(Huang Hong-ying，Yin Qi-he.The principle and application progress of Fourier transform attenuated total reflection infrared spectroscopy(ATR-FTIR)［J］.Sun Yat-Sen University Graduate Journal(Natural Science·Medical Edition)，2011，32(1):20-31.)
[6]郭淑霞.表面增强拉曼光谱信息处理技术的研究与应用［D］.厦门:厦门大学，2014.(Guo Shu-xia.Research and application of surface-enhanced Raman spectroscopy information processing technology ［D］.Xiamen:Xiamen University，2014.)
[7]Ghosh A，Saharay R，Chakrabarty S，et al.Robust generalised quadratic discriminant analysis［J］.Pattern Recognition，2021，117:107981.
[8]Mitchell H B，Schaefer P A.A "soft" K-nearest neighbor voting scheme［J］.International Journal of Intelligent Systems，2010，16(4):459-468.
[9]Westerhuis J A，Velzen E，Hoefsloot H，et al.Multivariate paired data analysis:multilevel PLSDA versus OPLSDA［J］.Metabolomics，2010，6(1):119-128.
[10]Brereton R G，Lloyd G R.Partial least squares discriminant analysis:taking the magic away［J］.Journal of Chemometrics，2014，28(4):213-225.
[11]Jiang M，Wang C，Zhang Y，et al.Sparse partial-least-squares discriminant analysis for different geographical origins of Salvia miltiorrhiza by H-NMR-based metabolomics［J］.Phytochemical Analysis，2014，25(1):50-58.
[12]Anne-Laure B，Korbinian S.Partial least squares:a versatile tool for the analysis of high-dimensional genomic data［J］.Briefings in Bioinformatics ，2008(1):32-44.
[13]Abdi H，Williams L J.Partial least squares methods:partial least squares correlation and partial least square regression［J］.Methods in Molecular Biology，2013，930:549-579.
[14]Westerhuis J A，Hoefsloot H，Smit S，et al.Assessment of PLSDA cross validation［J］.Metabolomics，2008，4(1):81-89.
[15]曲思杨，张秋菊，王文佶，等.多次交叉验证对PLSDA模型的影响研究［J］.中国卫生统计，2017，34(1):15-17.(Qu Si-yang，Zhang Qiu-ju，Wang Wen-ji，et al.Research on the influence of multiple cross-validation on the PLSDA model ［J］.China Health Statistics，2017，34(1):15-17.)
[16]郝勇，商庆园，饶敏，等.木材种类的近红外光谱和模式识别［J］.光谱学与光谱分析，2019，39(3):705-710.(Hao Yong，Shang Qing-yuan，Rao Min，et al.Near-infrared spectroscopy and pattern recognition of wood species［J］.Spectroscopy and Spectral Analysis，2019，39(3):705-710.)
[17]Li H D，Zeng M M，Tan B B，et al.Recipe for revealing informative metabolites based on model population analysis［J］.Metabolomics，2010，6(3):353-361.
[18]Li H D，Liang Y Z，Xu Q S，et al.Key wavelengths screening using competitive adaptive reweighted sampling method for multivariate calibration［J］.Analytica Chimica Acta，2009，648(1):77-84.
[19]林两魁，徐晖，许丹，等.基于可逆跳跃马尔可夫链蒙特卡罗方法的空间邻近目标红外像平面分辨［J］.光学学报，2011(5):96-103.(Lin Liang-kui，Xu Hui，Xu Dan，et al.Infrared image plane resolution of spatially adjacent targets based on reversible hopping Markov chain Monte Carlo method［J］.Acta Optics Sinica，2011(5):96-103.)
[20]Li H D，Xu Q S，Liang Y Z.Random frog:an efficient reversible jump Markov chain Monte Carlo-like approach for variable selection with applications to gene selection and disease classification［J］.Analytica Chimica Acta，2012，740(1):20-26.
[21]Li H D.LibPLS:an integrated library for partial least squares regression and linear discriminant analysis［J］.Chemometrics & Intelligent Laboratory Systems，2018，176:34-43.
[22]Yun Y H，Li H D，Wood L E，et al.An efficient method of wavelength interval selection based on random frog for multivariate spectral calibration［J］.Spectrochimica Acta Part A:Molecular & Biomolecular Spectroscopy，2013，111:31-36.