Classification using functional data analysis for temporal gene expression data

MOTIVATION: Temporal gene expression profiles provide an important characterization of gene function, as biological systems are predominantly developmental and dynamic. We propose a method of classifying collections of temporal gene expression curves in which individual expression profiles are modeled as independent realizations of a stochastic process. The method uses a recently developed functional logistic regression tool based on functional principal components, aimed at classifying gene expression curves into known gene groups. The number of eigenfunctions in the classifier can be chosen by leave-one-out cross-validation with the aim of minimizing the classification error. RESULTS: We demonstrate that this methodology provides low-error-rate classification for both yeast cell-cycle gene expression profiles and Dictyostelium cell-type specific gene expression patterns. It also works well in simulations. We compare our functional principal components approach with a B-spline implementation of functional discriminant analysis for the yeast cell-cycle data and simulations. This indicates comparative advantages of our approach which uses fewer eigenfunctions/base functions. The proposed methodology is promising for the analysis of temporal gene expression data and beyond. AVAILABILITY: MATLAB programs are available upon request.     

Accurate molecular classification of cancer using simple rules

Background

One intractable problem with using microarray data analysis for cancer classification is how to reduce the extremely high-dimensionality gene feature data to remove the effects of noise. Feature selection is often used to address this problem by selecting informative genes from among thousands or tens of thousands of genes. However, most of the existing methods of microarray-based cancer classification utilize too many genes to achieve accurate classification, which often hampers the interpretability of the models. For a better understanding of the classification results, it is desirable to develop simpler rule-based models with as few marker genes as possible.

Methods

We screened a small number of informative single genes and gene pairs on the basis of their depended degrees proposed in rough sets. Applying the decision rules induced by the selected genes or gene pairs, we constructed cancer classifiers. We tested the efficacy of the classifiers by leave-one-out cross-validation (LOOCV) of training sets and classification of independent test sets.

Results

We applied our methods to five cancerous gene expression datasets: leukemia (acute lymphoblastic leukemia [ALL] vs. acute myeloid leukemia [AML]), lung cancer, prostate cancer, breast cancer, and leukemia (ALL vs. mixed-lineage leukemia [MLL] vs. AML). Accurate classification outcomes were obtained by utilizing just one or two genes. Some genes that correlated closely with the pathogenesis of relevant cancers were identified. In terms of both classification performance and algorithm simplicity, our approach outperformed or at least matched existing methods.

Conclusion

In cancerous gene expression datasets, a small number of genes, even one or two if selected correctly, is capable of achieving an ideal cancer classification effect. This finding also means that very simple rules may perform well for cancerous class prediction.     

Learning Retention Mechanisms and Evolutionary Parameters of Duplicate Genes from Their Expression Data

Learning about the roles that duplicate genes play in the origins of novel phenotypes requires an understanding of how their functions evolve. A previous method for achieving this goal, CDROM, employs gene expression distances as proxies for functional divergence and then classifies the evolutionary mechanisms retaining duplicate genes from comparisons of these distances in a decision tree framework. However, CDROM does not account for stochastic shifts in gene expression or leverage advances in contemporary statistical learning for performing classification, nor is it capable of predicting the parameters driving duplicate gene evolution. Thus, here we develop CLOUD, a multi-layer neural network built on a model of gene expression evolution that can both classify duplicate gene retention mechanisms and predict their underlying evolutionary parameters. We show that not only is the CLOUD classifier substantially more powerful and accurate than CDROM, but that it also yields accurate parameter predictions, enabling a better understanding of the specific forces driving the evolution and long-term retention of duplicate genes. Further, application of the CLOUD classifier and predictor to empirical data from Drosophila recapitulates many previous findings about gene duplication in this lineage, showing that new functions often emerge rapidly and asymmetrically in younger duplicate gene copies, and that functional divergence is driven by strong natural selection. Hence, CLOUD represents a major advancement in classifying retention mechanisms and predicting evolutionary parameters of duplicate genes, thereby highlighting the utility of incorporating sophisticated statistical learning techniques to address long-standing questions about evolution after gene duplication.     

Simple decision rules for classifying human cancers from gene expression profiles

MOTIVATION: Various studies have shown that cancer tissue samples can be successfully detected and classified by their gene expression patterns using machine learning approaches. One of the challenges in applying these techniques for classifying gene expression data is to extract accurate, readily interpretable rules providing biological insight as to how classification is performed. Current methods generate classifiers that are accurate but difficult to interpret. This is the trade-off between credibility and comprehensibility of the classifiers. Here, we introduce a new classifier in order to address these problems. It is referred to as k-TSP (k-Top Scoring Pairs) and is based on the concept of 'relative expression reversals'. This method generates simple and accurate decision rules that only involve a small number of gene-to-gene expression comparisons, thereby facilitating follow-up studies. RESULTS: In this study, we have compared our approach to other machine learning techniques for class prediction in 19 binary and multi-class gene expression datasets involving human cancers. The k-TSP classifier performs as efficiently as Prediction Analysis of Microarray and support vector machine, and outperforms other learning methods (decision trees, k-nearest neighbour and na?ve Bayes). Our approach is easy to interpret as the classifier involves only a small number of informative genes. For these reasons, we consider the k-TSP method to be a useful tool for cancer classification from microarray gene expression data. AVAILABILITY: The software and datasets are available at http://www.ccbm.jhu.edu CONTACT: actan@jhu.edu.     

Interpretable gene expression classifier with an accurate and compact fuzzy rule base for microarray data analysis

An accurate classifier with linguistic interpretability using a small number of relevant genes is beneficial to microarray data analysis and development of inexpensive diagnostic tests. Several frequently used techniques for designing classifiers of microarray data, such as support vector machine, neural networks, k-nearest neighbor, and logistic regression model, suffer from low interpretabilities. This paper proposes an interpretable gene expression classifier (named iGEC) with an accurate and compact fuzzy rule base for microarray data analysis. The design of iGEC has three objectives to be simultaneously optimized: maximal classification accuracy, minimal number of rules, and minimal number of used genes. An "intelligent" genetic algorithm IGA is used to efficiently solve the design problem with a large number of tuning parameters. The performance of iGEC is evaluated using eight commonly-used data sets. It is shown that iGEC has an accurate, concise, and interpretable rule base (1.1 rules per class) on average in terms of test classification accuracy (87.9%), rule number (3.9), and used gene number (5.0). Moreover, iGEC not only has better performance than the existing fuzzy rule-based classifier in terms of the above-mentioned objectives, but also is more accurate than some existing non-rule-based classifiers.     

基于决策森林特征基因的两种识别方法

应用DNA芯片可获得成千上万个基因的表达谱数据。寻找对疾病有鉴别力的特征基因 ,滤掉与疾病无关的基因是基因表达谱数据分析的关键问题。利用决策森林方法的集成优势 ,提出基于决策森林的两种特征基因识别方法。该方法先由决策森林按照一定的显著性水平滤掉大部分与疾病类别无关的基因 ,然后采用统计频数法和扰动法 ,根据所选特征对分类的贡献程度对初选的特征基因作更加精细地选择。最后 ,选用神经网络作为外部分类器对所选的特征基因子集进行评价 ,将提出的方法应用于 4 0例结肠癌组织与 2 2例正常组织中 2 0 0 0个基因的表达谱实验数据。结果表明 :上述两种方法选出的特征基因均具有较高的疾病鉴别能力 ,均可获得最优特征基因子集 ,基于决策森林的统计频数法优于扰动法。     

Screening features to improve the class prediction of acute myeloid leukemia and myelodysplastic syndrome

After more than three decades of intensive investigations, the underpinning mechanism of myelodysplastic syndrome (MDS) and acute myeloid leukemia (AML) pathogenesis still remains largely uncharacterized, and their diagnosis relies heavily on the subjective factors. Recently gene expression profiling technique showed significant improvement in classifying some subtypes of AML, but the model's discriminating power of MDS from AML is still in its infancy. Feature selection plays an important role in the classification of the samples on the basis of the gene expression profiles. Our hypothesis explains that a better choice of features could improve the classification of the diseased and normal stage samples, and the potential application of feature screening to produce feature sets, with better accuracies and lowest number of embedded features. The observed results suggest that feature selection proves to be an essential and affirmative step in the biomedical data mining models based on gene expression profiles.     

Penalized Cox regression analysis in the high-dimensional and low-sample size settings, with applications to microarray gene expression data

MOTIVATION: An important application of microarray technology is to relate gene expression profiles to various clinical phenotypes of patients. Success has been demonstrated in molecular classification of cancer in which the gene expression data serve as predictors and different types of cancer serve as a categorical outcome variable. However, there has been less research in linking gene expression profiles to the censored survival data such as patients' overall survival time or time to cancer relapse. It would be desirable to have models with good prediction accuracy and parsimony property. RESULTS: We propose to use the L(1) penalized estimation for the Cox model to select genes that are relevant to patients' survival and to build a predictive model for future prediction. The computational difficulty associated with the estimation in the high-dimensional and low-sample size settings can be efficiently solved by using the recently developed least-angle regression (LARS) method. Our simulation studies and application to real datasets on predicting survival after chemotherapy for patients with diffuse large B-cell lymphoma demonstrate that the proposed procedure, which we call the LARS-Cox procedure, can be used for identifying important genes that are related to time to death due to cancer and for building a parsimonious model for predicting the survival of future patients. The LARS-Cox regression gives better predictive performance than the L(2) penalized regression and a few other dimension-reduction based methods. CONCLUSIONS: We conclude that the proposed LARS-Cox procedure can be very useful in identifying genes relevant to survival phenotypes and in building a parsimonious predictive model that can be used for classifying future patients into clinically relevant high- and low-risk groups based on the gene expression profile and survival times of previous patients.     

Quantitative trait associated microarray gene expression data analysis

Selection on phenotypes may cause genetic change. To understand the relationship between phenotype and gene expression from an evolutionary viewpoint, it is important to study the concordance between gene expression and profiles of phenotypes. In this study, we use a novel method of clustering to identify genes whose expression profiles are related to a quantitative phenotype. Cluster analysis of gene expression data aims at classifying genes into several different groups based on the similarity of their expression profiles across multiple conditions. The hope is that genes that are classified into the same clusters may share underlying regulatory elements or may be a part of the same metabolic pathways. Current methods for examining the association between phenotype and gene expression are limited to linear association measured by the correlation between individual gene expression values and phenotype. Genes may be associated with the phenotype in a nonlinear fashion. In addition, groups of genes that share a particular pattern in their relationship to phenotype may be of evolutionary interest. In this study, we develop a method to group genes based on orthogonal polynomials under a multivariate Gaussian mixture model. The effect of each expressed gene on the phenotype is partitioned into a cluster mean and a random deviation from the mean. Genes can also be clustered based on a time series. Parameters are estimated using the expectation-maximization algorithm and implemented in SAS. The method is verified with simulated data and demonstrated with experimental data from 2 studies, one clusters with respect to severity of disease in Alzheimer's patients and another clusters data for a rat fracture healing study over time. We find significant evidence of nonlinear associations in both studies and successfully describe these patterns with our method. We give detailed instructions and provide a working program that allows others to directly implement this method in their own analyses.     

Tissue differences revealed by gene expression profiles of various cell lines

Mechanisms through which tissues are formed and maintained remain unknown but are fundamental aspects in biology. Tissue-specific gene expression is a valuable tool to study such mechanisms. But in many biomedical studies, cell lines, rather than human body tissues, are used to investigate biological mechanisms Whether or not cell lines maintain their tissue-specific characteristics after they are isolated and cultured outside the human body remains to be explored. In this study, we applied a novel computational method to identify core genes that contribute to the differentiation of cell lines from various tissues. Several advanced computational techniques, such as Monte Carlo feature selection method, incremental feature selection method, and support vector machine (SVM) algorithm, were incorporated in the proposed method, which extensively analyzed the gene expression profiles of cell lines from different tissues. As a result, we extracted a group of functional genes that can indicate the differences of cell lines in different tissues and built an optimal SVM classifier for identifying cell lines in different tissues. In addition, a set of rules for classifying cell lines were also reported, which can give a clearer picture of cell lines in different issues although its performance was not better than the optimal SVM classifier. Finally, we compared such genes with the tissue-specific genes identified by the Genotype-tissue Expression project. Results showed that most expression patterns between tissues remained in the derived cell lines despite some uniqueness that some genes show tissue specificity.     

Gene Expression Signature Differentiates Histology But Not Progression Status of Early-Stage NSCLC

Advances in molecular analyses based on high-throughput technologies can contribute to a more accurate classification of non–small cell lung cancer (NSCLC), as well as a better prediction of both the disease course and the efficacy of targeted therapies. Here we set out to analyze whether global gene expression profiling performed in a group of early-stage NSCLC patients can contribute to classifying tumor subtypes and predicting the disease prognosis. Gene expression profiling was performed with the use of the microarray technology in a training set of 108 NSCLC samples. Subsequently, the recorded findings were validated further in an independent cohort of 44 samples. We demonstrated that the specific gene patterns differed significantly between lung adenocarcinoma (AC) and squamous cell lung carcinoma (SCC) samples. Furthermore, we developed and validated a novel 53-gene signature distinguishing SCC from AC with 93% accuracy. Evaluation of the classifier performance in the validation set showed that our predictor classified the AC patients with 100% sensitivity and 88% specificity. We revealed that gene expression patterns observed in the early stages of NSCLC may help elucidate the histological distinctions of tumors through identification of different gene-mediated biological processes involved in the pathogenesis of histologically distinct tumors. However, we showed here that the gene expression profiles did not provide additional value in predicting the progression status of the early-stage NSCLC. Nevertheless, the gene expression signature analysis enabled us to perform a reliable subclassification of NSCLC tumors, and it can therefore become a useful diagnostic tool for a more accurate selection of patients for targeted therapies.     

Comparative analysis of microarray normalization procedures: effects on reverse engineering gene networks

MOTIVATION: An increasingly common application of gene expression profile data is the reverse engineering of cellular networks. However, common procedures to normalize expression profiles generated using the Affymetrix GeneChips technology were originally developed for a rather different purpose, namely the accurate measure of differential gene expression between two or more phenotypes. As a result, current evaluation strategies lack comprehensive metrics to assess the suitability of available normalization procedures for reverse engineering and, in general, for measuring correlation between the expression profiles of a gene pair. RESULTS: We benchmark four commonly used normalization procedures (MAS5, RMA, GCRMA and Li-Wong) in the context of established algorithms for the reverse engineering of protein-protein and protein-DNA interactions. Replicate sample, randomized and human B-cell data sets are used as an input. Surprisingly, our study suggests that MAS5 provides the most faithful cellular network reconstruction. Furthermore, we identify a crucial step in GCRMA responsible for introducing severe artifacts in the data leading to a systematic overestimate of pairwise correlation. This has key implications not only for reverse engineering but also for other methods, such as hierarchical clustering, relying on accurate measurements of pairwise expression profile correlation. We propose an alternative implementation to eliminate such side effect.     

Validation of alternative methods of data normalization in gene co-expression studies

MOTIVATION: Clusters of genes encoding proteins with related functions, or in the same regulatory network, often exhibit expression patterns that are correlated over a large number of conditions. Protein associations and gene regulatory networks can be modelled from expression data. We address the question of which of several normalization methods is optimal prior to computing the correlation of the expression profiles between every pair of genes. RESULTS: We use gene expression data from five experiments with a total of 78 hybridizations and 23 diverse conditions. Nine methods of data normalization are explored based on all possible combinations of normalization techniques according to between and within gene and experiment variation. We compare the resulting empirical distribution of gene x gene correlations with the expectations and apply cross-validation to test the performance of each method in predicting accurate functional annotation. We conclude that normalization methods based on mixed-model equations are optimal.     

Discovering relational-based association rules with multiple minimum supports on microarray datasets

MOTIVATION: Association rule analysis methods are important techniques applied to gene expression data for finding expression relationships between genes. However, previous methods implicitly assume that all genes have similar importance, or they ignore the individual importance of each gene. The relation intensity between any two items has never been taken into consideration. Therefore, we proposed a technique named REMMAR (RElational-based Multiple Minimum supports Association Rules) algorithm to tackle this problem. This method adjusts the minimum relation support (MRS) for each gene pair depending on the regulatory relation intensity to discover more important association rules with stronger biological meaning. RESULTS: In the actual case study of this research, REMMAR utilized the shortest distance between any two genes in the Saccharomyces cerevisiae gene regulatory network (GRN) as the relation intensity to discover the association rules from two S.cerevisiae gene expression datasets. Under experimental evaluation, REMMAR can generate more rules with stronger relation intensity, and filter out rules without biological meaning in the protein-protein interaction network (PPIN). Furthermore, the proposed method has a higher precision (100%) than the precision of reference Apriori method (87.5%) for the discovered rules use a literature survey. Therefore, the proposed REMMAR algorithm can discover stronger association rules in biological relationships dissimilated by traditional methods to assist biologists in complicated genetic exploration.     

Modelling regulatory pathways in E. coli from time series expression profiles

MOTIVATION: Cells continuously reprogram their gene expression network as they move through the cell cycle or sense changes in their environment. In order to understand the regulation of cells, time series expression profiles provide a more complete picture than single time point expression profiles. Few analysis techniques, however, are well suited to modelling such time series data. RESULTS: We describe an approach that naturally handles time series data with the capabilities of modelling causality, feedback loops, and environmental or hidden variables using a Dynamic Bayesian network. We also present a novel way of combining prior biological knowledge and current observations to improve the quality of analysis and to model interactions between sets of genes rather than individual genes. Our approach is evaluated on time series expression data measured in response to physiological changes that affect tryptophan metabolism in E. coli. Results indicate that this approach is capable of finding correlations between sets of related genes.     

Using DNA microarrays to study gene expression in closely related species

MOTIVATION: Comparisons of gene expression levels within and between species have become a central tool in the study of the genetic basis for phenotypic variation, as well as in the study of the evolution of gene regulation. DNA microarrays are a key technology that enables these studies. Currently, however, microarrays are only available for a small number of species. Thus, in order to study gene expression levels in species for which microarrays are not available, researchers face three sets of choices: (i) use a microarray designed for another species, but only compare gene expression levels within species, (ii) construct a new microarray for every species whose gene expression profiles will be compared or (iii) build a multi-species microarray with probes from each species of interest. Here, we use data collected using a multi-primate cDNA array to evaluate the reliability of each approach. RESULTS: We find that, for inter-species comparisons, estimates of expression differences based on multi-species microarrays are more accurate than those based on multiple species-specific arrays. We also demonstrate that within-species expression differences can be estimated using a microarray for a closely related species, without discernible loss of information. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.