Variable selection and model validation of 2D and 3D molecular descriptors>

We have found that molecular shape and electrostatics, in conjunction with 2D structural fingerprints, are important variables in discriminating classes of active and inactive compounds. The subject of this paper is how to explore the selection of these variables and identify their relative importance in quantitative structure–activity relationships (QSAR) analysis. We show the use of these variables in a form of similarity searching with respect to a crystal structure of a known bound ligand. This analysis is then validated through k-fold cross-validation of enrichments via several common classifiers. Additionally, we show an effective methodology using the variables in hypothesis generation; namely, when the crystal structure of a bound ligand is not known.     

Laplacian normalization and random walk on heterogeneous networks for disease-gene prioritization

Random walk on heterogeneous networks is a recently emerging approach to effective disease gene prioritization. Laplacian normalization is a technique capable of normalizing the weight of edges in a network. We use this technique to normalize the gene matrix and the phenotype matrix before the construction of the heterogeneous network, and also use this idea to define the transition matrices of the heterogeneous network. Our method has remarkably better performance than the existing methods for recovering known gene–phenotype relationships. The Shannon information entropy of the distribution of the transition probabilities in our networks is found to be smaller than the networks constructed by the existing methods, implying that a higher number of top-ranked genes can be verified as disease genes. In fact, the most probable gene–phenotype relationships ranked within top 3 or top 5 in our gene lists can be confirmed by the OMIM database for many cases. Our algorithms have shown remarkably superior performance over the state-of-the-art algorithms for recovering gene–phenotype relationships. All Matlab codes can be available upon email request.     

差分拉曼光谱结合SVM对便签纸的鉴别分析

基于差分拉曼光谱技术与支持向量机(SVM)模型,提出了一种对便签纸类检材的快速可视化鉴别方法。实验获取了40组不同品牌便签纸样本的差分拉曼光谱数据,利用BP神经网络和差分技术完成谱图的除噪与基线校正后,借助F检验与主成分分析提取谱段信息,构建出SVM分类模型。实验结果表明,当设置Linear为SVM模型的核函数时,可以实现对样本测试集的完全准确划分,K折交叉验证的结果理想。相比于传统聚类分析手段,本方法可以在原始高维光谱数据中筛选出有效特征矩阵,且SVM模型兼具高效性和准确性,为公安实践中纸张类物证的区分鉴别提供一种新思路。     

更正

刊登在《光谱学与光谱分析》第39卷第12期第3705页中文摘要第9行 、 第3707页左栏第10行、 第3709页左栏第5行、 英文摘要第13行: “320~340 nm”应为“280~315 nm”;“340~420 nm”应 为“315~340 nm”。     

Prediction of Programmed-temperature Retention Values of Naphthas by Artificial Neural Networks

Abstract

It is proposed for the first time a method of prediction of the programmed-temperature retention times of components of naphthas in capillary gas chromatography using artificial neural networks. People are used to predict the programmed-temperature retention time using many formulas such as the integral formula, which requires that four parameters must be determined by calculation or experiments. However the results obtained by the formula are not so good to meet the demand of industry. In order to predict retention time accurately and conveniently, artificial neural networks using five-fold cross-validation and leave-20%-out methods have been applied. Only two parameters: density and isothermal retention index were used as input vectors. The average RMS error for predicted values of five different networks was 0.18, whereas the RMS error of predictions by the integral formula was 0.69. Obviously, the predictions by neural networks were much better than predictions by the formula, and neural networks need fewer parameters than the formula. So neural networks can successfully and conveniently solve the problem of predictions of programmed-temperature retention times, and provide useful data for analysis of naphthas in petrochemical industry.     

QSPR checking and validation: a case study with hydroxy radical reaction rate constant

Traditionally, QSAR and QSPR models have been fitted by splitting the available compounds into separate learning and validation sets. The model is then fitted to the learning set and assessed using the validation set. Cross-validation (CV) uses all available compounds for both purposes, so that the full body of available information is brought to bear on both the learning and the validation portions of the study. The price paid for this additional information is a substantially greater computational load. A common mistake in using CV is to omit some of the repetitive computations. This mistake leads to substantial bias in the assessment. A hydroxyl radical reaction rate dataset is used to illustrate the superiority of CV and the pitfalls from its improper execution when modeling using nearest neighbors, paralleling behavior in the well-studied linear model setting.     

Asymptotic Behavior of Bandwidth Selected by the Cross-Validation Method for Local Polynomial Fitting

In this paper, the asymptotic optimality of the cross validation bandwidth selector for the local polynomial fitting under strongly mixing dependence is obtained. The asymptotic normality of the bandwidth selected by the cross-validation method is derived, which is an extension of W. Härdle, P. Hall, and J. S. Marron (1988, J. Am. Statist. Assoc.83, 86–101).     

Assessing the statistical validity of proteomics based biomarkers

A strategy is presented for the statistical validation of discrimination models in proteomics studies. Several existing tools are combined to form a solid statistical basis for biomarker discovery that should precede a biochemical validation of any biomarker. These tools consist of permutation tests, single and double cross-validation. The cross-validation steps can simply be combined with a new variable selection method, called rank products. The strategy is especially suited for the low-samples-to-variables-ratio (undersampling) case, as is often encountered in proteomics and metabolomics studies. As a classification method, principal component discriminant analysis is used; however, the methodology can be used with any classifier. A dataset containing serum samples from Gaucher patients and healthy controls serves as a test case. Double cross-validation shows that the sensitivity of the model is 89% and the specificity 90%. Potential putative biomarkers are identified using the novel variable selection method. Results from permutation tests support the choice of double cross-validation as the tool for determining error rates when the modelling procedure involves a tuneable parameter. This shows that even cross-validation does not guarantee unbiased results. The validation of discrimination models with a combination of permutation tests and double cross-validation helps to avoid erroneous results which may result from the undersampling.     

Computer Vision Based Automatic Recognition of Pointer Instruments: Data Set Optimization and Reading

With the promotion of intelligent substations, more and more robots have been used in industrial sites. However, most of the meter reading methods are interfered with by the complex background environment, which makes it difficult to extract the meter area and pointer centerline, which is difficult to meet the actual needs of the substation. To solve the current problems of pointer meter reading for industrial use, this paper studies the automatic reading method of pointer instruments by putting forward the Faster Region-based Convolutional Network (Faster-RCNN) based object detection integrating with traditional computer vision. Firstly, the Faster-RCNN is used to detect the target instrument panel region. At the same time, the Poisson fusion method is proposed to expand the data set. The K-fold verification algorithm is used to optimize the quality of the data set, which solves the lack of quantity and low quality of the data set, and the accuracy of target detection is improved. Then, through some image processing methods, the image is preprocessed. Finally, the position of the centerline of the pointer is detected by the Hough transform, and the reading can be obtained. The evaluation of the algorithm performance shows that the method proposed in this paper is suitable for automatic reading of pointer meters in the substation environment, and provides a feasible idea for the target detection and reading of pointer meters.