关键词： Bagged nearest neighbor   Nonparametric regression   Probability estimation   Random forest   Support vector machine  

摘要： Probability estimation for binary and multicategory outcome using logistic and multinomial logistic regression has a long-standing tradition in biostatistics. However, biases may occur if the model is misspecified. In contrast, outcome probabilities for individuals can be estimated consistently with machine learning approaches, including k-nearest neighbors (k-NN), bagged nearest neighbors (b-NN), random forests (RF), and support vector machines (SVM). Because machine learning methods are rarely used by applied biostatisticians, the primary goal of this paper is to explain the concept of probability estimation with these methods and to summarize recent theoretical findings. Probability estimation in k-NN, b-NN, and RF can be embedded into the class of nonparametric regression learning machines;therefore, we start with the construction of nonparametric regression estimates and review results on consistency and rates of convergence. In SVMs, outcome probabilities for individuals are estimated consistently by repeatedly solving classification problems. For SVMs we review classification problem and then dichotomous probability estimation. Next we extend the algorithms for estimating probabilities using k-NN, b-NN, and RF to multicategory outcomes and discuss approaches for the multicategory probability estimation problem using SVM. In simulation studies for dichotomous and multicategory dependent variables we demonstrate the general validity of the machine learning methods and compare it with logistic regression. However, each method fails in at least one simulation scenario. We conclude with a discussion of the failures and give recommendations for selecting and tuning the methods. Applications to real data and example code are provided in a companion article

关键词： 结节病   肺结核   DCT   NB   SVM  

摘要： 结节病和肺结核的临床鉴别诊断目前仍然是困难的。搜集了106例结节病和肺结核的对比资料,并筛选出对分类有意义的临床指标作为特征,将其进行必要的量化和缩放形成训练数据,然后分别用支持向量机(SVM:Support Vector Machine)、决策分类树(DCT:Decision Classification Tree)、朴素贝叶斯(NB:Nave Bayes)3种不同的方法进行训练,并用5倍交叉验证评估各种不同的模型的有效性。实验结果表明,这3种方法在识别结节病时对应的ROC曲线下的面积分别为0.978,0.96,0.690,得到的测试精度分别达到100%,96.15%,96.15%,训练精度分别为95.28%,90.57%,92.38%。用这3种方法得到的分类器对19例临床未能确诊的病患进行预测,DCT方法的预测结果与SVM方法的结果高度吻合(19例中仅1例预测结果不同),而NB方法预测结果稍差(19例中有3例与SVM预测结果不一致)。实验结果表明,3种方法中,SVM方法的分类能力和分类精度最高。临床实验结果表明,19例临床未能确诊的病患按照SVM算法预测的结果进行治疗均得到了康复。

关键词： 提升小波   支持向量机   核函数   交叉验证   肝癌和肺癌基因芯片  

摘要： 针对肿瘤的早期诊断,提出了一种基于提升小波变换的特征提取的方法,对肿瘤数据样本进行分析鉴别.该方法利用提升小波变换对190例肝癌(包括对照)和107例肺癌(包括对照)基因表达谱芯片数据进行处理后,提取信号的低频信息,经支持向量机训练学习,构造分类器模型,用于癌和非癌样本的区分甄别.实验结果表明,经提升小波变换提取的特征基因,送入分类器中能得到较高的分类率,且在支持向量机中选取线性核函数或径向基函数都能达到较好的分类效果.通过随机选取的20例基因表改谱芯片样本,对所建立的模型进行了测试,获得了很好的效果,因此,本文提出的方法对肿瘤的诊断有一定的应用意义.

关键词： Bayesian analysis   Statistical data interpretation   Systems biology  

摘要： In this article we introduce modern statistical machine learning and bioinformatics approaches that have been used in learning statistical relationships from big data in medicine and behavioral science that typically include clinical, genomic (and proteomic) and environmental variables. Every year, data collected from biomedical and behavioral science is getting larger and more complicated. Thus, in medicine, we also need to be aware of this trend and understand the statistical tools that are available to analyze these datasets. Many statistical analyses that are aimed to analyze such big datasets have been introduced recently. However, given many different types of clinical, genomic, and environmental data, it is rather uncommon to see statistical methods that combine knowledge resulting from those different data types. To this extent, we will introduce big data in terms of clinical data, single nucleotide polymorphism and gene expression studies and their interactions with environment. In this article, we will introduce the concept of well-known regression analyses such as linear and logistic regressions that has been widely used in clinical data analyses and modern statistical models such as Bayesian networks that has been introduced to analyze more complicated data. Also we will discuss how to represent the interaction among clinical, genomic, and environmental data in using modern statistical models. We conclude this article with a promising modern statistical method called Bayesian networks that is suitable in analyzing big data sets that consists with different type of large data from clinical, genomic, and environmental data. Such statistical model form big data will provide us with more comprehensive understanding of human physiology and disease.

关键词： agriculture   ASTER satellite images   object-oriented image analysis   hierarchical classification   neural networks  

摘要： The strategic management of agricultural lands involves crop field monitoring each year. Crop discrimination via remote sensing is a complex task, especially if different crops have a similar spectral response and cropping pattern. In such cases, crop identification could be improved by combining object-based image analysis and advanced machine learning methods. In this investigation, we evaluated the C4.5 decision tree, logistic regression (LR), support vector machine (SVM) and multilayer perceptron (MLP) neural network methods, both as single classifiers and combined in a hierarchical classification, for the mapping of nine major summer crops (both woody and herbaceous) from ASTER satellite images captured in two different dates. Each method was built with different combinations of spectral and textural features obtained after the segmentation of the remote images in an object-based framework. As single classifiers, MLP and SVM obtained maximum overall accuracy of 88%, slightly higher than LR (86%) and notably higher than C4.5 (79%). The SVM+SVM classifier (best method) improved these results to 89%. In most cases, the hierarchical classifiers considerably increased the accuracy of the most poorly classified class (minimum sensitivity). The SVM+SVM method offered a significant improvement in classification accuracy for all of the studied crops compared to the conventional decision tree classifier, ranging between 4% for safflower and 29% for corn, which suggests the application of object-based image analysis and advanced machine learning methods in complex crop classification tasks.

关键词： Protein solubility   Protein solubility prediction   In silico prediction   Recombinant protein expression   Escherichia coli   Machine learning   Bioinformatics   Computational biology  

摘要： Background: Over the last 20 years in biotechnology, the production of recombinant proteins has been a crucial bioprocess in both biopharmaceutical and research arena in terms of human health, scientific impact and economic volume. Although logical strategies of genetic engineering have been established, protein overexpression is still an art. In particular, heterologous expression is often hindered by low level of production and frequent fail due to opaque reasons. The problem is accentuated because there is no generic solution available to enhance heterologous overexpression. For a given protein, the extent of its solubility can indicate the quality of its function. Over 30% of synthesized proteins are not soluble. In certain experimental circumstances, including temperature, expression host, etc., protein solubility is a feature eventually defined by its sequence. Until now, numerous methods based on machine learning are proposed to predict the solubility of protein merely from its amino acid sequence. In spite of the 20 years of research on the matter, no comprehensive review is available on the published methods. Results: This paper presents an extensive review of the existing models to predict protein solubility in Escherichia coli recombinant protein overexpression system. The models are investigated and compared regarding the datasets used, features, feature selection methods, machine learning techniques and accuracy of prediction. A discussion on the models is provided at the end. Conclusions: This study aims to investigate extensively the machine learning based methods to predict recombinant protein solubility, so as to offer a general as well as a detailed understanding for researches in the field. Some of the models present acceptable prediction performances and convenient user interfaces. These models can be considered as valuable tools to predict recombinant protein overexpression results before performing real laboratory experiments, thus saving labou

关键词： Machine learning   Reconstructing missing data   Euphrates basin   Runoff prediction  

摘要： Machine learning (ML) techniques have been popular data-driven approaches for hydrological studies during the last few decades owing to their capability to identify complex nonlinear relationships between input and output data without the requirement for physical understanding of the system. This paper aims to predict river flows using various ML methods [feed forward neural network (FFNN), adaptive neuro fuzzy inference system (ANFIS), and genetic programming (GP)] and also a non-ML method (multiple linear regression) in the Euphrates Basin in Turkey. Infilling the missing data in the runoff record of the selected stations in Euphrates Basin is also an objective of this study. The ML methods were applied to the three main sub-basins of the Euphrates Basin, namely the Upper, Middle, and Lower Euphrates Basins. ANFIS and FFNN methods were the most successful ML methods for runoff estimation in the Upper and Lower Euphrates Basins, whereas GP and ANFIS models were the best ones in the Middle Euphrates Basin. Missing flow data were constructed successfully in the selected stations.

关键词： Landsat   ALOS/PALSAR   L-band   maximum likelihood classification   support vector machines   neural networks   random forest   topographic effects   Hyrcanian mountainous forest   Iran  

摘要： Forest environment classification in mountain regions based on single-sensor remote sensing approaches is hindered by forest complexity and topographic effects. Temperate broadleaf forests in western Asia such as the Hyrcanian forest in northern Iran have already suffered from intense anthropogenic activities. In those regions, forests mainly extend in rough terrain and comprise different stand structures, which are difficult to discriminate. This paper explores the joint analysis of Landsat7/ETM+, L-band SAR and their derived parameters and the effect of terrain corrections to overcome the challenges of discriminating forest stand age classes in mountain regions. We also verified the performances of three machine learning methods which have recently shown promising results using multisource data;support vector machines (SVM), neural networks (NN), random forest (RF) and one traditional classifier (i.e., maximum likelihood classification (MLC)) as a benchmark. The non-topographically corrected ETM+ data failed to differentiate among different forest stand age classes (average classification accuracy (OA) = 65%). This confirms the need to reduce relief effects prior data classification in mountain regions. SAR backscattering alone cannot properly differentiate among different forest stand age classes (OA = 62%). However, textures and PolSAR features are very efficient for the separation of forest classes (OA = 82%). The highest classification accuracy was achieved by the joint usage of SAR and ETM+ (OA = 86%). However, this shows a slight improvement compared to the ETM+ classification (OA = 84%). The machine learning classifiers proved t o be more robust and accurate compared to MLC. SVM and RF statistically produced better classification results than NN in the exploitation of the considered multi-source data.

关键词： Artificial Intelligence   Calibration   Computer Simulation   Groundwater   Water Movements   Water Movements  

摘要： Quantitative analyses of groundwater flow and transport typically rely on a physically-based model, which is inherently subject to error. Errors in model structure, parameter and data lead to both random and systematic error even in the output of a calibrated model. We develop complementary data-driven models (DDMs) to reduce the predictive error of physically-based groundwater models. Two machine learning techniques, the instance-based weighting and support vector regression, are used to build the DDMs. This approach is illustrated using two real-world case studies of the Republican River Compact Administration model and the Spokane Valley-Rathdrum Prairie model. The two groundwater models have different hydrogeologic settings, parameterization, and calibration methods. In the first case study, cluster analysis is introduced for data preprocessing to make the DDMs more robust and computationally efficient. The DDMs reduce the root-mean-square error (RMSE) of the temporal, spatial, and spatiotemporal prediction of piezometric head of the groundwater model by 82%, 60%, and 48%, respectively. In the second case study, the DDMs reduce the RMSE of the temporal prediction of piezometric head of the groundwater model by 77%. It is further demonstrated that the effectiveness of the DDMs depends on the existence and extent of the structure in the error of the physically-based model.

关键词： Genotype-phenotype relationship   Insertion/deletion   Machine learning   Indeuctive logic programming  

摘要： Background: Small insertion and deletion polymorphisms (Indels) are the second most common mutations in the human genome, after Single Nucleotide Polymorphisms (SNPs). Recent studies have shown that they have significant influence on genetic variation by altering human traits and can cause multiple human diseases. In particular, many Indels that occur in protein coding regions are known to impact the structure or function of the protein. A major challenge is to predict the effects of these Indels and to distinguish between deleterious and neutral variants. When an Indel occurs within a coding region, it can be either frameshifting (FS) or non-frameshifting (NFS). FS-Indels either modify the complete C-terminal region of the protein or result in premature termination of translation. NFS-Indels insert/delete multiples of three nucleotides leading to the insertion/deletion of one or more amino acids. Results: In order to study the relationships between NFS-Indels and Mendelian diseases, we characterized NFS-Indels according to numerous structural, functional and evolutionary parameters. We then used these parameters to identify specific characteristics of disease-causing and neutral NFS-Indels. Finally, we developed a new machine learning approach, KD4i, that can be used to predict the phenotypic effects of NFS-Indels. Conclusions: We demonstrate in a large-scale evaluation that the accuracy of KD4i is comparable to existing state-of-the- art methods. However, a major advantage of our approach is that we also provide the reasons for the predictions, in the form of a set of rules. The rules are interpretable by non-expert humans and they thus represent new knowledge about the relationships between the genotype and phenotypes of NFS-Indels and the causative molecular perturbations that result in the disease.