构建支持向量机-偏最小二乘法为药物构效关系建模

为研究药物构效关系积累样本数据的过程中,需为小样本建模。此时较易造成过拟合,影响模型的预测性能和稳定性。为此可用偏最小二乘(PLS)法从样本数据中成对地提取最优成分,消除自变量间的复共线性,并有效的降维,然后应用最小二乘支持向量机对成对成分进行非线性回归,并以基于误差修正的策略调整,使之更有效地表达自、因变量间的非线性关系。由此构建为EB-LSSVM-PLS算法,所建模型的预报精度高,稳定性良好。将其应用于新型黄烷酮类衍生物的QSAR建模,效果令人满意,其泛化性能优于其它方法。     

用自适应偏最小二乘回归为药物定量构效关系建模

提出了一种自适应偏最小二乘回归（APLSR）方法。对于指定的预测对象，APLSR将根据样本在结构参数空间中的分布，分析它们对预测对象的预报能力，自适应地为各个样本分配权值，并从样本数据中提取和选用PLS成分，从而实施自适应加权PLSR，以获得预报性能良好的模型，作者将APLSR应用于含硫苯衍生物的QSAR建模，取得了令人满意的效果。     

优化的径向基-循环子空间网络为药物定量构效关系建模

径向基．循环子空间回归(RBF-CSR)网络,保留了径向基-偏最小二乘(RBF—PLS)网络的优点,且可在更广的范围内选择最优模型,但仍存在着参数难以确定,计算量大等问题。对此,本研究兼顾网络模型的拟合与预测性能,采用具有高效全局搜优能力的优进遗传算法(EGA)优化网络参数,构建为EGA-RBF-CSR方法,并将其成功应用于苯乙酰胺类除草剂的构效关系(QSAR)建模,效果良好,显示出很强的学习能力,所建模型具有良好的预报性能和稳定性,并优于其他方法。     

循环子空间回归为喹喏酮N1位构效关系建模

拟从线性泛函的角度分析循环子空间回归(CSR).CSR方法将从自变量参数矩阵和因变量向量中提取成分,循环地构造并扩张Krylov子空间,且以此作为源空间,运用最小二乘准则解得映射到因变量实空间的线性泛函.整个求解过程包容了最小二乘回归(LSR)、主成分回归(PCR)、偏最小二乘回归(PLS)以及其它中间的回归方法.然后由预报能力的强弱,从中确定最佳回归模型.本文应用CSR方法为喹喏酮N₁位抗菌构效关系建模,效果良好.     

TIBO衍生物类抗艾滋病药物三维定量结构活性关系研究

采用三维全息原子场作用矢量(3D-HoVAIF)对20个TIBO类衍生物抗艾滋病药物进行定量构效关系(QSAR)研究。运用偏最小二乘回归(Partial Least Square Regression,PLS)建模,同时采用内部及外部双重验证的办法对所得模型稳定性能进行深入分析和检验。PLS建模的复相关系数(Rcum)、留一法(Leave-one-out,LOO)交互校验(Cross-validation,CV)复相关系数(QCV)和外部样本校验复相关系数(Qext)分别为0.837、0.804、0.812。结果表明,3D-HoVAIF能较好表征TIBO类衍生物抗艾滋病药物分子结构信息,     

藏药五脉绿绒蒿提取过程的在线近红外光谱质量控制研究北大核心CSCD

利用近红外光谱技术和自建的在线检测系统,实现了藏药五脉绿绒蒿提取过程中总黄酮含量的在线近红外光谱监测和提取终点的判定。以403个样品为建模集,分别获得了主成分回归(PCR)、偏最小二乘(PLS)、决策树(DT)、随机森林(RF)算法下的最佳光谱预处理方法和建模区间,以残差预测偏差(RPD)值为指标选择最佳建模方法。以62个样品为外部验证集,考察模型应用于总黄酮含量实时监测的可行性。此外,还探讨了利用模型预测值进行相对浓度变化率(RCCR)分析直接判定提取终点的可行性,并比较了标准偏差绝对距离法(ADSD)和移动窗口标准偏差法(MBSD)对提取终点判定的适用性。结果表明,在预处理方法为Constant+一阶导数+SG平滑、建模区间5300~9000 cm^(-1)条件下所建的总黄酮含量的PLS模型效果最好,其校正集和验证集的误差均方根均小于0.14、相关系数均大于0.97,RPD值为4.68。所建PLS模型对未知样品的平均预测率为79%,实际值与预测值的相关系数大于0.98,表明模型有较好的预测效果。外部验证集中RCCR法判定的预测提取终点和ADSD法判定的提取终点均与实际提取终点一致。所建模型性能较好,通过对未知样品进行准确快速的定量分析,实现了五脉绿绒蒿提取过程中总黄酮含量的实时监测,同时,以RCCR和ADSD作为提取终点的判定方法较为准确,可为藏药材提取过程在线近红外光谱分析技术的研究提供有益借鉴。     

快速协同浊点萃取-荧光分光光度法结合偏最小二乘测定水中2,4-二甲基苯酚

建立了快速协同浊点萃取-荧光分光光度法结合偏最小二乘(PLS)测定水中2,4-二甲基苯酚(DMP)的方法。以聚乙二醇6000为萃取剂,乙腈为协同诱导剂,与无水Na2SO4共同作用,室温1 min内完成对DMP萃取,并采用荧光光度法测定目标分析物。选择化学计量学中的PLS建模,以排除水样中主要干扰物苯酚的影响,实现对DMP的准确测定。结果表明,PLS建模时,提取2个主成分最佳,DMP分析结果的相对预报误差在可接受范围内。DMP的线性范围是0.10～3.0μg/mL,检出限(LOD)为3.4 ng/mL。该方法已用于环境水样中DM P的测定,加标回收率为99.4%～107%。     

基于不同建模方法的ACE抑制肽QSAR比较研究

以自组建的血管紧张素转化酶(Angiotensin I-converting enzyme)抑制肽库为研究对象,采用氨基酸描述符SVHEHS(Scores vector of hydrophobic,electronic,hydrogen bonds and steric properties)对各肽样本进行结构表征后,进行自交叉协方差(Auto cross covariances,ACC)处理,并分别利用多元线性回归(Multiple linear regression,MLR)、偏最小二乘(Partial least square regression,PLS)、人工神经网络(Artificial neural networks,ANN)3种建模方法进行ACE抑制肽QSAR建模。结果显示,所得MLR、PLS与ANN模型的相关系数(Correlation coefficient,R2)分别为0.744、0.862、0.958,留一交叉验证相关系数(Leave-one-out cross-validated correlation coefficient,Q2LOO)分别为0.532、0.829、0.948,外部验证复相关系数(External validated correlation coefficient,Q2ext)分别为0.567、0.632、0.634。因此,SVHEHS结合上述3种建模方法均适用于ACE抑制肽的QSAR研究,其中ANN的建模效果最优。     

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。     

循环空间回归为喹喏酮N1位构效关系建模

拟从线性泛函的角度分析循环子空间回归（CSR）。CSR方法将从自变量参数矩阵和因变量向量中提取成分,循环地构造并扩张Krylov子窨,且以此作为源空间,运用最小二乘准则解最映射到因变量实空间的线性泛函。整个求解过程包容了最小二乘回归（LSR）、主成分回归（PCR）、偏最小二乘回归（PLS）以及其它中间的回归方法。然后以预报能力的强弱,从中确定最佳回归模型。本文应用SCR方法为喹喏酮N1位抗菌构效关系建模,效果良好。     

QSAR study of angiotensin II antagonists using robust boosting partial least squares regression

In the current study, robust boosting partial least squares (RBPLS) regression has been proposed to model the activities of a series of 4H-1,2,4-triazoles as angiotensin II antagonists. RBPLS works by sequentially employing PLS method to the robustly reweighted versions of the training compounds, and then combing these resulting predictors through weighted median. In PLS modeling, an F-statistic has been introduced to automatically determine the number of PLS components. The results obtained by RBPLS have been compared to those by boosting partial least squares (BPLS) repression and partial least squares (PLS) regression, showing the good performance of RBPLS in improving the QSAR modeling. In addition, the interaction of angiotensin II antagonists is a complex one, including topological, spatial, thermodynamic and electronic effects.     

Modeling based on subspace orthogonal projections for QSAR and QSPR research

A novel projection modeling method for quantitative structure activity relationship (QSAR) and quantitative structure property relationship (QSPR) is developed in this paper. Orthogonalization of block variables is introduced to deal with the problem of variable selection. Projections based on least squares are used to construct the modeling space in order to search for the best regression directions for chemical modeling. A suitable prediction space for such a model is further defined to confine the usage range of the model. Three real data sets were analyzed to check the performance of the proposed modeling method. The results obtained from Monte‐Carlo cross‐validation (MCCV) showed that the proposed modeling method might provide better results for QSAR and QSPR modeling than PCR and PLS with respect to both fitting and prediction abilities. Copyright © 2007 John Wiley & Sons, Ltd.     

LapRLSR for NIR spectral modeling and its application to online monitoring of the column separation of Salvianolate

A novel near infrared (NIR) modeling method—Laplacian regularized least squares regression (LapRLSR) was presented, which can take the advantage of many unlabeled spectra to promote the prediction performance of the model even if there are only few calibration samples. Using LapRLSR modeling, NIR spectral analysis was applied to the online monitoring of the concentration of salvia acid B in the column separation of Salvianolate. The results demonstrated that LapRLSR outperformed partial least squares (PLS) significantly, and NIR online analysis was applicable.     

段式正交信号校正方法及在小麦近红外光谱数据分析中的应用

针对光谱数据峰宽、局部效应显著、含有噪音、变量个数多及彼此间常存在严重的复共线性等问题,改进和设计一种光谱数据局部校正方法:基于窗口平滑的段式正交信号校正方法,并将之结合偏最小二乘回归,以实现光谱数据的预处理及定量分析。通过NIPALS算法初始化将滤去的正交成分,以近邻分段方式进行逐个波长点的正交信号校正。而后将去噪后的光谱矩阵作为新的自变量阵,通过偏最小二乘回归构建其与性质参变量间的校正模型。通过小麦近红外漫反射光谱数据的应用实验结果表明,本方法正交成分估计稳定,去噪明显,模型的预报性能优于其它方法,PLS成分数减少,模型更加简洁。     

基于多模型共识的偏最小二乘法用于近红外光谱定量分析

建立了多模型共识偏最小二乘(cPLS)建模方法, 并应用于烟草样品近红外(NIR)光谱与常规成分氯含量之间的建模研究, 探讨了建模参数对预测结果的影响. 结果表明, cPLS方法与传统的偏最小二乘算法(PLS)相比, 所建模型更稳定可靠, 预测结果也可得到了明显改善.     

基于机器学习方法的丙型肝炎病毒聚合酶NS5B非核苷抑制剂的定量构效关系研究

对89 个苯并异噻唑和苯并噻嗪类丙型肝炎病毒(HCV) NS5B聚合酶非核苷抑制剂进行了定量构效关系(QSAR)研究. 采用遗传算法组合偏最小二乘(GA-PLS)和线性逐步回归分析(LSRA)两种特征选择方法选择最优描述符子集, 然后建立多元线性回归和偏最小二乘线性回归模型. 并首次尝试使用遗传算法耦合支持向量机方法(GA-SVM)对两种特征选择方法所选的描述符子集分别建立非线性支持向量机回归模型. 三种机器学习方法所建模型均得到比较满意的预测效果. 采用LSRA所选的6 个描述符建立的三个QSAR模型对于测试集的相关系数为0.958-0.962, GA-SVM法给出最好的预测精度(0.962). 采用GA-PLS所选的7个描述符建立的三个QSAR模型对于测试集的相关系数为0.918-0.960, 偏最小二乘回归模型的结果最好(0.960). 本工作提供了一种有效的方法来预测丙型肝炎病毒抑制剂的生物活性, 该方法也可以扩展到其他类似的定量构效关系研究领域.     

Co‐evolution of non‐linear PLS model components

The issue of outer model weight updating is important in extending partial least squares (PLS) regression to modelling data that shows significant non‐linearity. This paper presents a novel co‐evolutionary component approach to the weight updating problem. Specification of the non‐linear PLS model is achieved using an evolutionary computational (EC) method that can co‐evolve all non‐linear inner models and all input projection weights simultaneously. In this method, modular symbolic non‐linear equations are used to represent the inner models and binary sequences are used to represent the projection weights. The approach is flexible, and other representations could be employed within the same co‐evolutionary framework. The potential of these methods is illustrated using a simulated pH neutralisation process data set exhibiting significant non‐linearity. It is demonstrated that the co‐evolutionary component architecture can produce results which are competitive with non‐linear neural network‐based PLS algorithms that use iterative projection weight updating. In addition, a data sampling method for mitigating overfitting to the training data is described. Copyright © 2007 John Wiley & Sons, Ltd.