基于多阶导数拉曼光谱组合技术的矿物油模式分类

为了实现对法庭科学领域重质矿物油物证的快速、准确、无损的鉴定,该文基于光谱分析技术提出了一种多阶导数光谱数据组合分析的方法。收集了80种不同型号、不同厂家的重质矿物油样本,利用傅里叶变换拉曼光谱分析法采集样本的原始光谱数据和导数光谱数据,并通过结合化学计量学构建分类模型。在构建的主成分分析(PCA)结合径向基函数神经网络(RBF)分类模型中,对单独的原始光谱、一阶导数谱和二阶导数谱数据的训练集准确率分别为80.0%、86.7%和86.2%,测试集准确率分别为73.3%、80.0%和72.7%;对组合后的原始光谱+一阶导数谱、原始光谱+二阶导数谱和一阶导数谱+二阶导数谱数据的分类中,训练集准确率分别为97.0%、96.7%和100%,测试集准确率分别为85.7%、90.0%和100%。结果表明,对组合后的导数光谱与原始光谱构建分类模型,准确率更高。其中,基于一阶导数谱+二阶导数谱数据构建的PCA结合RBF分类模型的结果最为理想,准确率达100%。而K最近邻算法模型由于受到样本不均匀的影响,整体分类准确率均较低。利用组合的导数光谱与原始光谱数据构建分类模型能够实现对重质矿物油样本的快速、准确、无损鉴别,可为光谱组合技术在法庭科学及其他分析测试领域的应用提供一定的借鉴和参考。     

基于高光谱技术的培养基上细菌菌落分类方法研究

利用高光谱技术对培养基上细菌(大肠杆菌、李斯特菌和金黄色葡萄球菌)菌落进行快速识别和分类。采集琼脂培养基上细菌菌落的高光谱反射图像(390~1040 nm),在对波段差图像进行大津阈值分割的基础上自动提取细菌菌落光谱,并建立细菌分类检测的全波长和简化偏最小二乘判别( PLS-DA)模型。全波长模型对预测集样本的分类准确率和置信预测分类准确率分别为100%和95.9%。此外,利用竞争性自适应重加权算法( CARS)、遗传算法( GA)和最小角回归算法( LARS-Lasso)进行波长优选并建立对应简化模型。其中,CARS简化模型在精度、稳定性及分类准确率方面均优于GA和LARS-Lasso简化模型,其对预测集样本的分类准确率和置信预测分类准确率分别达到了100%和98.0%。研究表明,高光谱是一种细菌菌落高精度、快速、无损识别检测的有效方法。简化模型中优选的波长可以为开发低成本检测仪器提供理论依据。     

基于GPU计算的并行PLS算法研究与实现

偏最小二乘算法(PLS)是与红外、近红外光谱分析结合使用最为广泛的化学计量学算法,然而当前PLS算法通常采用单线程方式实现,当校正模型数量多或样本数量大、波长点数和主成分数较多,模型需对光谱预处理和波长选择方法反复优化时,计算十分缓慢。为大幅提高建模速度,该文提出了一种基于图形处理器(GPU)的并行计算策略,利用具有大规模并行计算特性的GPU作为计算设备,结合CUBLAS库函数实现了基于GPU并行的PLS建模算法(CUPLS)。利用近红外光谱数据集进行性能对比实验,结果表明CUPLS建模算法较传统单线程实现的PLS算法,加速比可达近42倍,极大地提升了化学计量学算法的建模效率。该方法亦可用于其它化学计量学算法的加速。     

近红外光谱法定性检测菜籽油中多效唑残留

采用近红外光谱技术结合化学计量学方法对菜籽油中多效唑残留进行定性检测。在4000~10000 cm-1光谱范围内采集126个菜籽油样本的近红外透射光谱。对原始光谱进行初步分析后,分别采用线性判别分析(LDA)、簇类独立软模式法(SIMCA)和最小二乘支持向量机(LSSVM)三种不同方法建立菜籽油中多效唑残留的定性检测模型,并对不同多效唑残留的菜籽油样本的分类正确率进行分析。研究结果表明,LDA,SIMCA及LSSVM 3种方法建立的检测模型均具有较高的判别能力,其校正集和预测集的正确率分别为93.33%,91.11%,95.56%和86.11%,88.89%,83.33%。此外,高多效唑残留样本的分类正确率大致趋于100%,而低多效唑残留样本的分类正确率则有一定波动。由此可知,利用近红外光谱技术可对菜籽油中多效唑残留进行快速、无损的定性检测。     

基于卷积神经网络和近红外光谱的茶叶品种和等级鉴别

以5个品种茶叶和4个不同等级龙井茶叶为研究对象,利用近红外光谱与卷积神经网络相结合的方法,实现茶叶品种和等级的鉴别。对实验采集得到的800～2 500 nm原始光谱使用小波分析(WT)算法进行预处理,对预处理后的光谱数据分别采用联合区间偏最小二乘法(siPLS)、连续投影算法(SPA)、竞争性自适应重加权算法(CARS)提取特征波长,然后建立卷积神经网络(CNN)分类模型,实现茶叶品种和等级的鉴别。结果显示：SPA+CNN模型对品种和等级鉴别的准确率分别达到了95.83%和96.67%,CARS+CNN将准确率进一步提升到97.72%和98.67%。最后使用平移法、线性叠加法、添加噪声法对光谱数据集进行数据增强,验证卷积神经网络模型的稳定性。研究结果表明,特征波长提取结合卷积神经网络,可以实现对茶叶品种和等级的无损鉴别。为后续开发动态在线检测设备提供了高效、无损、快速的技术支持。     

红外光谱数据融合结合化学计量学无损检测汽车灯罩

汽车灯罩碎片是交通肇事案件现场经常出现的物证。为了实现对汽车灯罩物证的准确检验,该文提出一种将原始光谱与导数光谱相结合的光谱融合技术。收集不同类别和多种品牌的汽车灯罩共计44个,采用傅里叶变换红外光谱技术对样本进行分析,提取其原始光谱数据和一阶导数光谱数据,并结合化学计量学构建分类模型。在对汽车灯罩类别进行分类的Fisher判别分析模型中,单独的原始光谱数据和一阶导数光谱数据的分类准确率分别为86.40%和84.10%,融合后的光谱数据分类准确率达到93.20%,分类准确率明显提高。通过主成分分析优化模型后,融合光谱的分类准确率达到97.70%,且在进一步对汽车灯罩品牌进行分类时,分类准确率达到100.00%,实验结果理想。而在K近邻算法模型中,由于受到样本不均匀的影响,分类准确率较低。结果表明,基于原始光谱与导数光谱的光谱融合技术能够实现对汽车灯罩样本的准确分类,可以为光谱融合技术在分析检测领域的应用提供借鉴和参考。     

基于谱区优选的近红外光谱快速预测玉米秸秆中木质纤维素含量的研究

在生物燃气生产过程中,玉米秸秆中的木质纤维素(纤维素、半纤维素和木质素)成分含量对厌氧发酵性能具有重要影响。针对传统方法测定本质纤维素的耗时、成本高等问题,本研究分析了近红外光谱(NIRS)结合化学计量学进行玉米秸秆中木质纤维素含量快速检测的可行性。为提高NIRS模型的检测精度和效率,将遗传模拟退火算法(GSA)、区间偏最小二乘法(iPLS)和支持向量机(SVM)相结合,构建遗传模拟退火区间支持向量机(GSA-iSVM)进行NIRS特征谱区和SVM参数的同步优化,并与反向区间偏最小二乘法(BiPLS)、遗传模拟退火区间偏最小二乘法(GSA-iPLS)的优选特征谱区的建模性能进行对比,确定基于GSA-iSVM建立的纤维素和木质素校正模型性能最佳,基于GSA-iPLS建立的半纤维素校正模型性能最佳。纤维素、半纤维素和木质素最佳校正模型验证集的预测决定系数(R_p²)分别为0.910、 0.990和0.939,预测均方根误差(RMSEP)分别为0.881%、 0.707%和0.249%,剩余预测偏差(RPD)分别为3.283、 10.235和4.27...     

基于近红外光谱技术的日照绿茶茶鲜叶模型的优化

建立一种茶鲜叶中茶多酚含量的快速测定方法。采取日照市2个主要茶叶产区60个茶园的茶鲜叶,利用近红外光谱技术结合化学计量学方法建立优化模型进行预测。茶多酚的参考值采用国家标准方法进行测定。结果表明,采用Savitzky-Golay平滑和一阶导数处理光谱,能够有效消除光谱中的噪音及非目标因素的影响。遗传算法(Genetic Algorithm,GA)选择了针对目标组分茶多酚的200个信息变量,简化了模型。同时,采用主成分回归(PCR)和偏最小二乘(PLS)两种建模方法进行预测,其预测均方根误差(RMSEP)及剩余预测偏差(RPD)分别为0.6158、0.6743和4.7238、4.3141;决定系数(R2)分别为0.9514和0.9451。     

近红外光谱结合化学计量学评价胚胎发育潜能

使用近红外光谱分析方法测量培养后的胚胎培养液,结合偏最小二乘判别分析对胚胎发育潜能进行评价,鉴别具有妊娠能力与不具妊娠能力的胚胎。为了提高模型的判别能力,消除无信息变量对模型稳定性影响,分别采用基于蒙特卡罗的无信息变量消除法(MC-UVE)、竞争性自适应加权抽样法(CARS)与基于变量稳定性的竞争性自适应加权抽样法(SCARS),对光谱进行波长选择。结果表明,与采用全谱74%的正判率相比较,采用这3种波长选择方法,模型独立检验集的正判率分别提高至74.24%,77.12%与80.10%,建模使用变量数降至50以内。比较发现,SCARS的模型优化能力和稳定性均好于MC-UVE和CARS方法。采用近红外光谱结合化学计量学方法预测胚胎的发育潜能是可行的。     

基于近红外光谱技术与化学计量学的绿茶无损鉴别方法研究

该文利用近红外光谱技术结合化学计量学方法开发了不同品种绿茶的无损鉴别方法。通过近红外光谱技术得到了8个品种绿茶样品的近红外光谱,比较了单一以及优化组合光谱预处理方法对光谱的影响,利用无监督的主成分分析(PCA)与有监督的线性判别分析方法(LDA)分别构建了茶叶品种鉴别模型。结果表明：对比单一预处理方法,优化组合预处理具有更优的鉴别准确性。标准正态变量变换预处理消除了茶叶样品大小不均造成的光谱散射影响,一阶导数预处理实现了变动背景的消除,减少了基线漂移的影响,突出了图谱中的有效信息,采用二者相结合的预处理方式并结合无监督的主成分分析法可实现较为准确的绿茶样品种类鉴别分析,准确率达75.0%。此外,采用有监督的线性判别分析方法处理原始光谱数据,可达到100%的鉴别准确率,但该方法需提供类别的先验知识。因此,采用近红外光谱技术和化学计量学相结合的手段可实现不同品种绿茶的快速无损鉴别。     

Laser-induced breakdown spectroscopy and chemometrics for classification of toys relying on toxic elements

Quality control of toys for avoiding children exposure to potentially toxic elements is of utmost relevance and it is a common requirement in national and/or international norms for health and safety reasons. Laser-induced breakdown spectroscopy (LIBS) was recently evaluated at authors' laboratory for direct analysis of plastic toys and one of the main difficulties for the determination of Cd, Cr and Pb was the variety of mixtures and types of polymers. As most norms rely on migration (lixiviation) protocols, chemometric classification models from LIBS spectra were tested for sampling toys that present potential risk of Cd, Cr and Pb contamination. The classification models were generated from the emission spectra of 51 polymeric toys and by using Partial Least Squares - Discriminant Analysis (PLS-DA), Soft Independent Modeling of Class Analogy (SIMCA) and K-Nearest Neighbor (KNN). The classification models and validations were carried out with 40 and 11 test samples, respectively. Best results were obtained when KNN was used, with corrected predictions varying from 95% for Cd to 100% for Cr and Pb.     

Prediction of activity cliffs on the basis of images using convolutional neural networks

An activity cliff (AC) is formed by a pair of structurally similar compounds with a large difference in potency. Accordingly, ACs reveal structure–activity relationship (SAR) discontinuity and provide SAR information for compound optimization. Herein, we have investigated the question if ACs could be predicted from image data. Therefore, pairs of structural analogs were extracted from different compound activity classes that formed or did not form ACs. From these compound pairs, consistently formatted images were generated. Image sets were used to train and test convolutional neural network (CNN) models to systematically distinguish between ACs and non-ACs. The CNN models were found to predict ACs with overall high accuracy, as assessed using alternative performance measures, hence establishing proof-of-principle. Moreover, gradient weights from convolutional layers were mapped to test compounds and identified characteristic structural features that contributed to successful predictions. Weight-based feature visualization revealed the ability of CNN models to learn chemistry from images at a high level of resolution and aided in the interpretation of model decisions with intrinsic black box character.

     

Quantitative determination of acetylsalicylic acid and acetaminophen in tablets by FT-Raman spectroscopy

A procedure for quantitative determination of acetylsalicylic acid and acetaminophen in pharmaceuticals by PLS (partial least squares) and PCR (principal component regression) treatment of FT (Fourier transform)-Raman spectroscopic data is proposed. The proposed method was tested on powdered samples. Three chemometric models were built: the first, for samples consisting of an active substance diluted by lactose, starch and talc; the second, in which a simple inorganic salt was applied as an internal standard and additions were not taken into account; and the third, in which a model was constructed for a commercial pharmaceutical, where all constituents of the tablet were known. By utilising selected spectral ranges and by changing the chemometric conditions it is possible to carry out fast and precise analysis of the active component content in medicines on the basis of the simplified chemometric models. The proposed method was tested on five commercial tablets. The results were compared with data obtained by intensity ratio and pharmacopoeial methods. To appraise the quality of the models, the relative standard error of predictions (RSEPs) were calculated for calibration and prediction data sets. These were 0.7-2.0% and 0.8-2.3%, respectively, for the different PLS models. Application of these models to the Raman spectra of commercial tablets containing acetylsalicylic acid gave RSEP values of 1.3-2.0% and a mean accuracy of 1.2-1.7% with a standard deviation of 0.6-1.2%.     

Rapid and Sensitive Determination of Aminocaproic Acid Injection by Raman Spectroscopy Combined with Chemometric Models

A quantitative approach for the determination of aminocaproic acid in commercial injections based on Raman spectroscopy and chemometrics has been developed. The Raman spectra of aminocaproic acid injections were analyzed by chemometric models including classical least squares (CLS), partial least squares (PLS), principal component regression (PCR), and stepwise multiple linear regression (SMLR). To compare the quantitative ability of the models, two key parameters, difference value and root mean square error, were calculated. The results indicated that the SMLR method was more efficient than the other methods. The difference value of the SMLR method was 90.5% and the root mean square error was 2.08. Raman determinations agreed with results obtained with a standard titration method (p < 0.05). The recovery was (99.7 ± 0.58)% and the repeatability was (99.2 ± 0.67)% by the SMLR method. These results show that the chemometric modeling of Raman spectra is a specific, rapid, and convenient alternative to quantify aminocaproic acid in injections.     

应用小波特征提取肺癌组织FTIR的支持向量机分类方法研究

提出了一种新的基于傅里叶变换红外光谱(Fourier Transform Infrared Spectroscopy, FTIR)的小波特征提取与支持向量机(SVM)分类方法以提高FTIR对早期肺癌的诊断准确率. 对肺正常组织、早期肺癌及进展期肺癌组织的FTIR, 利用连续小波(CW)多分辨率分析法提取9个特征量, 支持向量机把其分为正常组与非正常组(包括早期肺癌和进展期肺癌), 对正常组织、早期肺癌和进展期肺癌的识别, 多项式核函数和径向基函数的识别准确率最高. 多项式核函数对正常组织、早期肺癌和进展期肺癌的识别准确率分别为100%, 95%及100%; 径向基函数分别为100%, 95%和100%. 实验结果表明FTIR-CW-SVM模式分类方法对正常肺癌组织、早期肺癌及进展肺癌的识别具有较好的可行性.     

Using the Method of “Optical Biopsy” of Prostatic Tissue to Diagnose Prostate Cancer

Simple SummaryAnalytical discrimination models of Raman spectra of prostate cancer tissue were constructed by using the projections onto latent structures data analysis (PLS-DA) method for different wavelengths of exciting radiation—532 and 785 nm. These models allowed us to divide the Raman spectra of prostate cancer and the spectra of hyperplasia sites for validation datasets with the accuracy of 70–80%, depending on the specificity value. Meanwhile, for the calibration datasets, the accuracy values reached 100% for the excitation of a laser with a wavelength of 785 nm. Due to the registration of Raman “fingerprints”, the main features of cellular metabolism occurring in the tissue of a malignant prostate tumor were confirmed, namely the absence of aerobic glycolysis, over-expression of markers, and a strong increase in the concentration of cholesterol and its esters, as well as fatty acids and glutamic acid.AbstractThe possibilities of using optical spectroscopy methods in the differential diagnosis of prostate cancer were investigated. Analytical discrimination models of Raman spectra of prostate tissue were constructed by using the projections onto latent structures data analysis(PLS-DA) method for different wavelengths of exciting radiation—532 and 785 nm. These models allowed us to divide the Raman spectra of prostate cancer and the spectra of hyperplasia sites for validation datasets with the accuracy of 70–80%, depending on the specificity value. Meanwhile, for the calibration datasets, the accuracy values reached 100% for the excitation of a laser with a wavelength of 785 nm. Due to the registration of Raman “fingerprints”, the main features of cellular metabolism occurring in the tissue of a malignant prostate tumor were confirmed, namely the absence of aerobic glycolysis, over-expression of markers (FASN, SREBP1, stearoyl-CoA desaturase, etc.), and a strong increase in the concentration of cholesterol and its esters, as well as fatty acids and glutamic acid. The presence of an ensemble of Raman peaks with increased intensity, inherent in fatty acid, beta-glucose, glutamic acid, and cholesterol, is a fundamental factor for the identification of prostate cancer.     

Chemometrics: An Excavator in Temperature-Dependent Near-Infrared Spectroscopy

Temperature-dependent near-infrared (NIR) spectroscopy has been developed and taken as a powerful technique for analyzing the structure of water and the interactions in aqueous systems. Due to the overlapping of the peaks in NIR spectra, it is difficult to obtain the spectral features showing the structures and interactions. Chemometrics, therefore, is adopted to improve the spectral resolution and extract spectral information from the temperature-dependent NIR spectra for structural and quantitative analysis. In this review, works on chemometric studies for analyzing temperature-dependent NIR spectra were summarized. The temperature-induced spectral features of water structures can be extracted from the spectra with the help of chemometrics. Using the spectral variation of water with the temperature, the structural changes of small molecules, proteins, thermo-responsive polymers, and their interactions with water in aqueous solutions can be demonstrated. Furthermore, quantitative models between the spectra and the temperature or concentration can be established using the spectral variations of water and applied to determine the compositions in aqueous mixtures.     

Analysis of the essential oils of Coriandrum sativum Using GC-MS coupled with chemometric resolution methods

The essential oils extracted from Coriandrum sativum L. were analyzed by GC-MS coupled with chemometric resolution methods. Through the chemometric resolution methods, peak clusters were uniquely resolved into the pure chromatographic profiles and mass spectra of each component. Qualitative analysis was performed by comparing the pure mass spectra with those in the NIST 05 mass spectral library. Quantitative analysis was performed using the total volume integration method. A total of 118 constituents were detected, of which 104 were identified, accounting for 97.27% of the total content. The results indicate that GC-MS combined with chemometric resolution methods can greatly enhance the capability of separation and the reliability of qualitative and quantitative results. The combined method is an economical and accurate approach for the rapid analysis of the complex essential oil samples in Coriandrum sativum L.     

Pure Ion Chromatograms Combined with Advanced Machine Learning Methods Improve Accuracy of Discriminant Models in LC–MS-Based Untargeted Metabolomics

Untargeted metabolomics based on liquid chromatography coupled with mass spectrometry (LC–MS) can detect thousands of features in samples and produce highly complex datasets. The accurate extraction of meaningful features and the building of discriminant models are two crucial steps in the data analysis pipeline of untargeted metabolomics. In this study, pure ion chromatograms were extracted from a liquor dataset and left-sided colon cancer (LCC) dataset by K-means-clustering-based Pure Ion Chromatogram extraction method version 2.0 (KPIC2). Then, the nonlinear low-dimensional embedding by uniform manifold approximation and projection (UMAP) showed the separation of samples from different groups in reduced dimensions. The discriminant models were established by extreme gradient boosting (XGBoost) based on the features extracted by KPIC2. Results showed that features extracted by KPIC2 achieved 100% classification accuracy on the test sets of the liquor dataset and the LCC dataset, which demonstrated the rationality of the XGBoost model based on KPIC2 compared with the results of XCMS (92% and 96% for liquor and LCC datasets respectively). Finally, XGBoost can achieve better performance than the linear method and traditional nonlinear modeling methods on these datasets. UMAP and XGBoost are integrated into KPIC2 package to extend its performance in complex situations, which are not only able to effectively process nonlinear dataset but also can greatly improve the accuracy of data analysis in non-target metabolomics.     

An approach to comparative analysis of chromatographic fingerprints for assuring the quality of botanical drugs

The present study was focused on developing the chemometric methods for analysis of the chromatographic fingerprint to control the quality of botanical drugs, which has gained attention in Asia and other countries. We developed a novel approach to generate a set of fingerprint features, called Fisher components (FCs) that were extracted from the chromatographic fingerprint. The method greatly reduces the dimensionality of the fingerprint vector, and the resulting FCs still retain most discriminatory information of the original fingerprint. Choosing an example of relevance to contemporary botanical drugs, we applied the FCs to a set of Shenmai injection samples. We successfully identified the manufacturers of the samples using two classifiers, linear discriminant analysis (LDA) and k-Nearest Neighbor (k-NN) based on the FCs. We also applied a similarity assessment together with the visual analysis using the FCs to exam the products from different manufacturers. We found that the lot-to-lot consistency of products can be accurately determined using the FCs. Finally, we demonstrated that the application of chemometric methods for chromatographic fingerprinting offers reliability to detect suspected fraud samples. In summary, we demonstrated that the presented approaches could be useful to determine the identity, consistency, and authenticity of Shenmai injection through chromatographic fingerprinting. The methods are equally applicable to other botanical drugs.