支持向量回归在人体血红蛋白无创检测中的应用

采用线性渐变滤光片(Linear variable filter, LVF),优化设计高性能、便携式的人体血液成分近红外检测设备,研究了支持向量回归(Support vector regression, SVR)模型对人体血红蛋白(Hemoglobin, Hb)的预测能力及稳定性,以实现贫血疾病的无创诊断.无创采集100位志愿者食指前端光谱信息并划分定标集、验证集1和2.应用网格搜索方法优选惩罚参数与核函数参数c=5.28, g=0.33,用以建立稳健的SVR模型.随后,分别对验证集1和2中Hb水平进行定量分析.实验结果表明: 预测标准偏差(RMSEP) 分别为10.20 g/L和10.85 g/L,相对预测标准偏差(R-RMSEP) 为6.85%和7.48%,测量精度较高且SVR模型对不同样品的适应性较强,基本满足临床检测要求.基于SVR算法自行设计的LVF型近红外光谱检测设备在贫血症的无创诊断中有着良好的应用前景.     

Multi-way modeling of hydro-chemical data of an alluvial river system--a case study

A large data set pertaining to water quality of an alluvial river was analyzed using multi-way data analysis methods with a view to extract the hidden information, spatial and temporal variation trends in the river water quality. Four-way data (8 monitoring sites × 22 water quality variables × 10 monitoring years × 12 sampling months) analysis was performed using PARAFAC and Tucker3 models. A two component PARAFAC model, although explained 35.1% of the data variance, could not fit to the data set. Tucker3 model of optimum complexity (2,3,1,3) explaining 39.7% of the data variance, allowed interpretation of the data information in four modes. The model explained spatial and temporal variation trends in terms of water quality variables during the study period and revealed that sampling sites in mid-stretch of the river were dominated mainly by the variables of anthropogenic origin. The results delineated the mid stretch of the river as critical from pollution point of view and also identified summer months as having high influence on river water quality in this stretch. The information regarding spatial and temporal variations in water quality generated by the four-way modeling of data would be useful in developing long-term water resources management strategies in the river basin.     

基于地统计学与支持向量回归的QSAR建模

基于主成分分析(PCA)、地统计学(GS)和支持向量回归(SVR), 提出了一种新的定量构效关系(QSAR)个体化预测方法——Weight-PCA-GS-SVR. 其基本思路是: 先以PCA降维并消除自变量间的信息冗余, 继以SVR经非线性主成分筛选去除与因变量无关的主成分, 再以保留主成分计算样本间的加权距离, 然后以高维GS确定公用变程; 每一个待测样本都以自身为中心从训练集中找出加权距离小于公用变程的私有k个近邻, 以SVR训练建模完成个体化预测. Weight-PCA-GS-SVR从行、列两个方向对模型进行了优化, 为自变量提供了一种新的加权方法, 为解决最优k近邻选择难题提供了新的思路, 并具有SVR原来的优点. 经3个化合物活性实例数据集验证, 新方法在所有参比模型中预测精度最高, 且明显优于文献报道结果, Weight-PCA-GS-SVR在QSAR等回归预测领域有较广泛的应用前景.     

基于岭回归和SVM的高维特征选择与肽QSAR建模

岭回归估计权重绝对值在一定程度上体现了对应特征作用大小, 据此发展了基于岭回归(RR)和支持向量机(SVM)的高维特征选择算法. 对苦味二肽(BTT)和细胞毒性T淋巴细胞(CTL)表位9 肽两个肽体系, 以氨基酸的531 个物理化学性质参数直接表征肽结构, 各获得1062、4779 个初始特征; 对训练集, 初始特征以岭回归排序后序贯引入, 当SVM留一法交叉测试(LOOCV)的均方误差(MSE)显著上扬时终止, 最后以多轮末尾淘汰进一步精筛, 分别获得7、18个物理化学意义明确的保留特征. 基于保留特征与支持向量回归(SVR), 对训练集建立定量构效关系(QSAR)模型, 预测独立测试集, 其拟合精度、留一法交叉测试精度、独立预测精度均优于现有文献报道结果. 新方法运行速度快, 选取的特征物理化学意义明确, 解释性强, 在肽、蛋白质定量构效关系建模等高维数据回归预测领域有较广泛应用前景.     

Multi-way partial least squares modeling of water quality data

A 10 years surface water quality data set pertaining to a polluted river was analyzed using partial least squares (PLS) regression models. Both the unfold-PLS and N-PLS (tri-PLS and quadri-PLS) models were calibrated through leave-one out cross-validation method. These were applied to the multivariate, multi-way data array with a view to assess and compare their predictive capabilities for biochemical oxygen demand (BOD) of river water in terms of their relative mean squares error of cross-validation, prediction and variance captured. The sum of squares of residuals and leverages were computed and analyzed to identify the sites, variables, years and months which may have influence on the constructed model. Both the tri- and quadri-PLS models yielded relatively low validation error as compared to unfold-PLS and captured high variance in model. Moreover, both of these methods produced acceptable model precision and accuracy. In case of tri-PLS the root mean squares errors were 1.65 and 2.17 for calibration and prediction, respectively; whereas these were 2.58 and 1.09 for quadri-PLS. At a preliminary level it seems that BOD can be predicted but a different data arrangement is needed. Moreover, analysis of the scores and loadings plots of the N-PLS models could provide information on time evolution of the river water quality.     

Autoignition temperature: comprehensive data analysis and predictive models

ABSTRACT

Here we report a new predictive model for autoignition temperature (AIT), an important physical parameter widely used to assess potential safety hazards of combustible materials. Available structure-AIT data extracted from different sources were critically analysed. Support vector regression (SVR) models on different data subsets were built in order to identify a reliable compound set on which a realistic model could be built. This led to a selection of the dataset containing 875 compounds annotated with AIT values. The thereupon-based SVR model performs reasonably well in cross-validation with the determination coefficient r ² = 0.77 and mean absolute error MAE = 37.8°C. External validation on 20 industrial compounds missing in the training set confirmed its good predictive power (MAE = 28.7°C).     

Application of genetic algorithm‐support vector regression (GA‐SVR) for quantitative analysis of herbal medicines

In this paper, a genetic algorithm‐support vector regression (GA‐SVR) coupled approach was proposed for investigating the relationship between fingerprints and properties of herbal medicines. GA was used to select variables so as to improve the predictive ability of the models. Two other widely used approaches, Random Forests (RF) and partial least squares regression (PLSR) combined with GA (namely GA‐RF and GA‐PLSR, respectively), were also employed and compared with the GA‐SVR method. The models were evaluated in terms of the correlation coefficient between the measured and predicted values (Rp), root mean square error of prediction, and root mean square error of leave‐one‐out cross‐validation. The performance has been tested on a simulated system, a chromatographic data set, and a near‐infrared spectroscopic data set. The obtained results indicate that the GA‐SVR model provides a more accurate answer, with higher Rp and lower root mean square error. The proposed method is suitable for the quantitative analysis and quality control of herbal medicines. Copyright © 2012 John Wiley & Sons, Ltd.     

海水中铁(Ⅲ)-二元有机酸盐配合物的光化学反应研究

采用实验室模拟的方法研究了高压汞灯模拟日光照射下铁(Ⅲ)-二元有机酸盐配合物在天然海水中的光化学反应.结果发现,在二元有机酸盐配体的存在下,铁(Ⅲ)发生光化学反应生成还原态的铁(Ⅲ),铁(Ⅲ)会被溶液中的氧再氧化为铁(Ⅲ).铁(Ⅲ)的光还原反应速率受到配体浓度、pH、光强以及温度的影响.在二元有机酸与Fe(Ⅲ)浓度配比大于2的情况下,Fe(Ⅲ)-二元有机酸盐配合物的光还原反应初期铁(Ⅲ)浓度的增长符合一级动力学反应规律,100min后浓度趋于稳定,方程式为[Fe(Ⅲ)]t=kOA[OA]·[Fe(Ⅲ)]ini×[1-exp{-(kOA[OA]+kox)t}]/(kOA[OA]+kox).光强升高和pH降低都能加快光还原反应速率,而改变温度则基本上对光还原反应速率无影响,证明铁(Ⅲ)的光还原反应为自由基引发的电子转移过程.     

Estimating sampling and analysis uncertainties to assess the fitness for purpose of a water quality monitoring network

In order to verify that the protocols used for water quality monitoring of surface waters within the Long-term Environmental Research Monitoring and Testing System (OPE), located in the north-eastern part of France in relation with a geological disposal for radioactive waste project, are fit for purpose, a validation study was conducted following the methodology described in the Eurachem/citac and Nordtest guidance documents on uncertainty arising from sampling. As one of the objectives of the OPE water monitoring programme was to investigate the spatial and temporal variability of water quality, quality requirements were set to having a measurement variance, including sampling and analytical contributions, less than 20 % of the total variance to minimise the impact of measurement over the observed environmental variability. The replicate method was then selected in order to estimate the measurement uncertainty, including the sampling contribution, as well as the spatial and temporal variability of water quality of surface waters. To minimise costs, a single-split level was selected. Analytical uncertainties were assessed from inter-laboratory data and/or internal quality control data from the last 2–5 years. Finally, ANOVA was applied to the data sets after elimination of outliers. Results showed that for pH, electrical conductivity, turbidity and nitrate, the sampling uncertainty was negligible, whereas for other parameters such as dissolved oxygen, total suspend solids, total organic carbon, nitrite and phosphate, the sampling contribution to the measurement uncertainty was largely significant. For all parameters except calcium, the sampling and analytical protocols were considered fit for purpose.     

基于迭代自组织数据分析算法与蚁群算法建立有机物黏度的QSPR模型

为了构建310个有机物分子结构与其黏度之间的定量结构-性质关系(QSPR)模型,探讨影响有机物液体黏度的结构因素,首先运用迭代自组织数据分析技术(ISODATA)将样本集初步分类,划分为训练集和测试集,进而应用DRAGON2.1软件计算310个有机物分子的分子结构描述符,以蚁群算法(ACO)筛选分子描述符,得到5个参数,随后分别采用多元线性回归法(MLR)和支持向量机法(SVM)建立ACO-MLR模型和ACOSVM模型.结果表明,非线性ACO-SVM模型(相关系数R2train=0.9013,R2test=0.9026)的性能优于线性ACOMLR模型(R2train=0.7680,R2test=0.8725).ACO-MLR模型和ACO-SVM模型对测试集所得预测值与实验值的相关系数分别为0.934和0.950,预测效果令人满意.本文应用Williams图对模型的应用域进行了一定的研究,所建立的模型为工程上提供了一种根据分子结构预测有机物黏度的有效方法.     

预测毛细管区带电泳有效淌度的支持向量回归建模方法

提出预测毛细管电泳迁移行为的支持向量回归建模方法。以核苷为实际研究对象,利用正交试验获得的数据,结合二标记物技术,用支持向量回归算法建立毛细管区带电泳的柱温、电压、缓冲液浓度和pH值与3种核苷的有效淌度之间的相关模型。将其与偏最小二乘回归和人工神经网络方法相比较,结果表明所建模型的预测准确性优于后两者,适宜用于毛细管电泳迁移行为的预测。