A Multiple-Filter-Multiple-Wrapper Approach to Gene Selection and Microarray Data Classification

Filters and wrappers are two prevailing approaches for gene selection in microarray data analysis. Filters make use of statistical properties of each gene to represent its discriminating power between different classes. The computation is fast but the predictions are inaccurate. Wrappers make use of a chosen classifier to select genes by maximizing classification accuracy, but the computation burden is formidable. Filters and wrappers have been combined in previous studies to maximize the classification accuracy for a chosen classifier with respect to a filtered set of genes. The drawback of this single-filter-single-wrapper (SFSW) approach is that the classification accuracy is dependent on the choice of specific filter and wrapper. In this paper, a multiple-filter-multiple-wrapper (MFMW) approach is proposed that makes use of multiple filters and multiple wrappers to improve the accuracy and robustness of the classification, and to identify potential biomarker genes. Experiments based on six benchmark data sets show that the MFMW approach outperforms SFSW models (generated by all combinations of filters and wrappers used in the corresponding MFMW model) in all cases and for all six data sets. Some of MFMW-selected genes have been confirmed to be biomarkers or contribute to the development of particular cancers by other studies.     

遗传优化算法在基因数据分类中的应用

本文提出了一种基于遗传算法的基因微阵列数据特征提取方法。首先对原始数据进行标准化,然后利用方差分析方法对数据进行降低维数处理,最后利用遗传算法对数据进行优化。针对基因数据对遗传算子和适应度函数进行设置,优化数据集选取特征基因,得到较小的特征子集。为了验证选取的特征,利用样本划分法通过判别分析建立分类器进行判定。实验论证此方法具有理想的分类效果,算法稳定、效率高。     

Identifying Differentially Expressed Genes in Time Course Microarray Data

Identifying differentially expressed (DE) genes across conditions or treatments is a typical problem in microarray experiments. In time course microarray experiments (under two or more conditions/treatments), it is sometimes of interest to identify two classes of DE genes: those with no time-condition interactions (called parallel DE genes, or PDE), and those with time-condition interactions (nonparallel DE genes, NPDE). Although many methods have been proposed for identifying DE genes in time course experiments, methods for discerning NPDE genes from the general DE genes are still lacking. We propose a functional ANOVA mixed-effect model to model time course gene expression observations. The fixed effect of (the mean curve) of the model decomposes bivariate functions of time and treatments (or experimental conditions) as in the classic ANOVA method and provides the associated notions of main effects and interactions. Random effects capture time-dependent correlation structures. In this model, identifying NPDE genes is equivalent to testing the significance of the time-condition interaction, for which an approximate F-test is suggested. We examined the performance of the proposed method on simulated datasets in comparison with some existing methods, and applied the method to a study of human reaction to the endotoxin stimulation, as well as to a cell cycle expression data set.     

A Kernel-Based Multivariate Feature Selection Method for Microarray Data Classification

High dimensionality and small sample sizes, and their inherent risk of overfitting, pose great challenges for constructing efficient classifiers in microarray data classification. Therefore a feature selection technique should be conducted prior to data classification to enhance prediction performance. In general, filter methods can be considered as principal or auxiliary selection mechanism because of their simplicity, scalability, and low computational complexity. However, a series of trivial examples show that filter methods result in less accurate performance because they ignore the dependencies of features. Although few publications have devoted their attention to reveal the relationship of features by multivariate-based methods, these methods describe relationships among features only by linear methods. While simple linear combination relationship restrict the improvement in performance. In this paper, we used kernel method to discover inherent nonlinear correlations among features as well as between feature and target. Moreover, the number of orthogonal components was determined by kernel Fishers linear discriminant analysis (FLDA) in a self-adaptive manner rather than by manual parameter settings. In order to reveal the effectiveness of our method we performed several experiments and compared the results between our method and other competitive multivariate-based features selectors. In our comparison, we used two classifiers (support vector machine, -nearest neighbor) on two group datasets, namely two-class and multi-class datasets. Experimental results demonstrate that the performance of our method is better than others, especially on three hard-classify datasets, namely Wang''s Breast Cancer, Gordon''s Lung Adenocarcinoma and Pomeroy''s Medulloblastoma.     

An Integrated Approach for Analyzing Clinical Genomic Variant Data from Next-Generation Sequencing

Next-generation sequencing (NGS) technologies provide the potential for developing high-throughput and low-cost platforms for clinical diagnostics. A limiting factor to clinical applications of genomic NGS is downstream bioinformatics analysis for data interpretation. We have developed an integrated approach for end-to-end clinical NGS data analysis from variant detection to functional profiling. Robust bioinformatics pipelines were implemented for genome alignment, single nucleotide polymorphism (SNP), small insertion/deletion (InDel), and copy number variation (CNV) detection of whole exome sequencing (WES) data from the Illumina platform. Quality-control metrics were analyzed at each step of the pipeline by use of a validated training dataset to ensure data integrity for clinical applications. We annotate the variants with data regarding the disease population and variant impact. Custom algorithms were developed to filter variants based on criteria, such as quality of variant, inheritance pattern, and impact of variant on protein function. The developed clinical variant pipeline links the identified rare variants to Integrated Genome Viewer for visualization in a genomic context and to the Protein Information Resource’s iProXpress for rich protein and disease information. With the application of our system of annotations, prioritizations, inheritance filters, and functional profiling and analysis, we have created a unique methodology for downstream variant filtering that empowers clinicians and researchers to interpret more effectively the relevance of genomic alterations within a rare genetic disease.     

Hierarchical Gene Selection and Genetic Fuzzy System for Cancer Microarray Data Classification

This paper introduces a novel approach to gene selection based on a substantial modification of analytic hierarchy process (AHP). The modified AHP systematically integrates outcomes of individual filter methods to select the most informative genes for microarray classification. Five individual ranking methods including t-test, entropy, receiver operating characteristic (ROC) curve, Wilcoxon and signal to noise ratio are employed to rank genes. These ranked genes are then considered as inputs for the modified AHP. Additionally, a method that uses fuzzy standard additive model (FSAM) for cancer classification based on genes selected by AHP is also proposed in this paper. Traditional FSAM learning is a hybrid process comprising unsupervised structure learning and supervised parameter tuning. Genetic algorithm (GA) is incorporated in-between unsupervised and supervised training to optimize the number of fuzzy rules. The integration of GA enables FSAM to deal with the high-dimensional-low-sample nature of microarray data and thus enhance the efficiency of the classification. Experiments are carried out on numerous microarray datasets. Results demonstrate the performance dominance of the AHP-based gene selection against the single ranking methods. Furthermore, the combination of AHP-FSAM shows a great accuracy in microarray data classification compared to various competing classifiers. The proposed approach therefore is useful for medical practitioners and clinicians as a decision support system that can be implemented in the real medical practice.     

Learning a Weighted Meta-Sample Based Parameter Free Sparse Representation Classification for Microarray Data

Sparse representation classification (SRC) is one of the most promising classification methods for supervised learning. This method can effectively exploit discriminating information by introducing a regularization terms to the data. With the desirable property of sparisty, SRC is robust to both noise and outliers. In this study, we propose a weighted meta-sample based non-parametric sparse representation classification method for the accurate identification of tumor subtype. The proposed method includes three steps. First, we extract the weighted meta-samples for each sub class from raw data, and the rationality of the weighting strategy is proven mathematically. Second, sparse representation coefficients can be obtained by regularization of underdetermined linear equations. Thus, data dependent sparsity can be adaptively tuned. A simple characteristic function is eventually utilized to achieve classification. Asymptotic time complexity analysis is applied to our method. Compared with some state-of-the-art classifiers, the proposed method has lower time complexity and more flexibility. Experiments on eight samples of publicly available gene expression profile data show the effectiveness of the proposed method.     

An Evolutionary Approach for Identifying Driver Mutations in Colorectal Cancer

The traditional view of cancer as a genetic disease that can successfully be treated with drugs targeting mutant onco-proteins has motivated whole-genome sequencing efforts in many human cancer types. However, only a subset of mutations found within the genomic landscape of cancer is likely to provide a fitness advantage to the cell. Distinguishing such “driver” mutations from innocuous “passenger” events is critical for prioritizing the validation of candidate mutations in disease-relevant models. We design a novel statistical index, called the Hitchhiking Index, which reflects the probability that any observed candidate gene is a passenger alteration, given the frequency of alterations in a cross-sectional cancer sample set, and apply it to a mutational data set in colorectal cancer. Our methodology is based upon a population dynamics model of mutation accumulation and selection in colorectal tissue prior to cancer initiation as well as during tumorigenesis. This methodology can be used to aid in the prioritization of candidate mutations for functional validation and contributes to the process of drug discovery.     

A Model-Based Approach for Identifying Signatures of Ancient Balancing Selection in Genetic Data

While much effort has focused on detecting positive and negative directional selection in the human genome, relatively little work has been devoted to balancing selection. This lack of attention is likely due to the paucity of sophisticated methods for identifying sites under balancing selection. Here we develop two composite likelihood ratio tests for detecting balancing selection. Using simulations, we show that these methods outperform competing methods under a variety of assumptions and demographic models. We apply the new methods to whole-genome human data, and find a number of previously-identified loci with strong evidence of balancing selection, including several HLA genes. Additionally, we find evidence for many novel candidates, the strongest of which is FANK1, an imprinted gene that suppresses apoptosis, is expressed during meiosis in males, and displays marginal signs of segregation distortion. We hypothesize that balancing selection acts on this locus to stabilize the segregation distortion and negative fitness effects of the distorter allele. Thus, our methods are able to reproduce many previously-hypothesized signals of balancing selection, as well as discover novel interesting candidates.     

A Latent Variable Approach for Meta-Analysis of Gene Expression Data from Multiple Microarray Experiments

Background  

With the explosion in data generated using microarray technology by different investigators working on similar experiments, it is of interest to combine results across multiple studies.     

An Integrated Peptide-Antigen Microarray on Plasmonic Gold Films for Sensitive Human Antibody Profiling

High-throughput screening for interactions of peptides with a variety of antibody targets could greatly facilitate proteomic analysis for epitope mapping, enzyme profiling, drug discovery and biomarker identification. Peptide microarrays are suited for such undertaking because of their high-throughput capability. However, existing peptide microarrays lack the sensitivity needed for detecting low abundance proteins or low affinity peptide-protein interactions. This work presents a new peptide microarray platform constructed on nanostructured plasmonic gold substrates capable of metal enhanced NIR fluorescence enhancement (NIR-FE) by hundreds of folds for screening peptide-antibody interactions with ultrahigh sensitivity. Further, an integrated histone peptide and whole antigen array is developed on the same plasmonic gold chip for profiling human antibodies in the sera of systemic lupus erythematosus (SLE) patients, revealing that collectively a panel of biomarkers against unmodified and post-translationally modified histone peptides and several whole antigens allow more accurate differentiation of SLE patients from healthy individuals than profiling biomarkers against peptides or whole antigens alone.     

An Integrated Approach to Three-Dimensional Data Collection at Dinosaur Tracksites in the Rocky Mountain West

Public lands in the Rocky Mountain West are home to an abundance of vertebrate paleontological resources. These fossils typically are found in badlands terrain and at some distance from convenient transportation. These and other factors often make conventional surveying and mapping techniques time-consuming and problematic. Even obtaining quality images, at useful scales with limited distortions, can be difficult. In order to preserve the value of these unique paleontological resources, an integrated approach to close-range photogrammetry and high-accuracy ground-control surveying was developed in northern Wyoming for the documentation of tracks at the Red Gulch Dinosaur Tracksite. At this site, several methods for taking high-resolution, low-distortion photographs of localities were investigated. These methods included using tripods of various heights, remote-controlled airplanes, and an Aerial Camera Blimp System. In addition, the use of a variety of ground-control collection methods, including high accuracy GPS and Light Detection and Ranging, have also been investigated. These various field data collection methods were successfully integrated using soft copy photogrammetry to produce digital terrain models, which can represent the surface to a precision of 1 cm or less. The three-dimensional data were brought into GIS software where they are displayed, combined with photographs, and rotated for viewing from different perspectives. As a result of the success of these technologies in Wyoming, studies of other dinosaur tracksites in Colorado, Utah, and Wyoming (as well as bonebeds) have utilized these methods. The information gained from these sites is aiding in our understanding of community dynamics and preservational history of dinosaur populations in the Rocky Mountain West.     

Strategies to Avoid Wrongly Labelled Genomes Using as Example the Detected Wrong Taxonomic Affiliation for Aeromonas Genomes in the GenBank Database

Around 27,000 prokaryote genomes are presently deposited in the Genome database of GenBank at the National Center for Biotechnology Information (NCBI) and this number is exponentially growing. However, it is not known how many of these genomes correspond correctly to their designated taxon. The taxonomic affiliation of 44 Aeromonas genomes (only five of these are type strains) deposited at the NCBI was determined by a multilocus phylogenetic analysis (MLPA) and by pairwise average nucleotide identity (ANI). Discordant results in relation to taxa assignation were found for 14 (35.9%) of the 39 non-type strain genomes on the basis of both the MLPA and ANI results. Data presented in this study also demonstrated that if the genome of the type strain is not available, a genome of the same species correctly identified can be used as a reference for ANI calculations. Of the three ANI calculating tools compared (ANI calculator, EzGenome and JSpecies), EzGenome and JSpecies provided very similar results. However, the ANI calculator provided higher intra- and inter-species values than the other two tools (differences within the ranges 0.06–0.82% and 0.92–3.38%, respectively). Nevertheless each of these tools produced the same species classification for the studied Aeromonas genomes. To avoid possible misinterpretations with the ANI calculator, particularly when values are at the borderline of the 95% cutoff, one of the other calculation tools (EzGenome or JSpecies) should be used in combination. It is recommended that once a genome sequence is obtained the correct taxonomic affiliation is verified using ANI or a MLPA before it is submitted to the NCBI and that researchers should amend the existing taxonomic errors present in databases.     

A Novel Approach for Identifying Causal Models of Complex Diseases from Family Data

Causal models including genetic factors are important for understanding the presentation mechanisms of complex diseases. Familial aggregation and segregation analyses based on polygenic threshold models have been the primary approach to fitting genetic models to the family data of complex diseases. In the current study, an advanced approach to obtaining appropriate causal models for complex diseases based on the sufficient component cause (SCC) model involving combinations of traditional genetics principles was proposed. The probabilities for the entire population, i.e., normal–normal, normal–disease, and disease–disease, were considered for each model for the appropriate handling of common complex diseases. The causal model in the current study included the genetic effects from single genes involving epistasis, complementary gene interactions, gene–environment interactions, and environmental effects. Bayesian inference using a Markov chain Monte Carlo algorithm (MCMC) was used to assess of the proportions of each component for a given population lifetime incidence. This approach is flexible, allowing both common and rare variants within a gene and across multiple genes. An application to schizophrenia data confirmed the complexity of the causal factors. An analysis of diabetes data demonstrated that environmental factors and gene–environment interactions are the main causal factors for type II diabetes. The proposed method is effective and useful for identifying causal models, which can accelerate the development of efficient strategies for identifying causal factors of complex diseases.     

An Integrated Approach for Landmark-Based Resistant Shape Analysis in 3D

The study of shape changes in morphology has seen a significant renovation in the last 20 years, particularly as a consequence of the development of geometric morphometric methods based on Cartesian coordinates of points. In order to extract information about shape differences when Cartesian coordinates are used, it is necessary to establish a common reference frame or system for all specimens to be compared. Therefore, a central issue in coordinate-based methods is which criterion should be used to align these configurations of points, since shape differences highly depend on those alignments. This is usually accomplished by aligning the configurations in a way that the sum of squared distances between coordinates of homologous points (landmarks) is minimized: the least-squares superimposition method. However, it is widely recognized that this method has some limitations when shape differences are not homogeneous across landmarks. Here we present an integrated approach for the resistant shape comparison of 3D landmark sets. It includes a new ordinary resistant Procrustes superimposition and its corresponding generalized resistant Procrustes version. In addition, they are combined with existing resistant multivariate statistical techniques for depicting the results. We demonstrate, by using both simulated and real datasets, that resistant Procrustes better detects and measures localized shape variation whenever present in up to half but one of the landmarks. The resistant Procrustes results are highly concordant with a priori biological information, and might dramatically improve the quality of inferences on patterns of shape variation.     

TAFFYS: An Integrated Tool for Comprehensive Analysis of Genomic Aberrations in Tumor Samples

Background

Tumor single nucleotide polymorphism (SNP) array is a common platform for investigating the cancer genomic aberration and the functionally important altered genes. Original SNP array signals are usually corrupted by noise, and need to be de-convoluted into absolute copy number profile by analytical methods. Unfortunately, in contrast with the popularity of tumor Affymetrix SNP array, the methods that are specifically designed for this platform are still limited. The complicated characteristics of noise in signals is one of the difficulties for dissecting tumor Affymetrix SNP array data, as they inevitably blur the distinction between aberrations and create an obstacle for the copy number aberration (CNA) identification.

Results

We propose a tool named TAFFYS for comprehensive analysis of tumor Affymetrix SNP array data. TAFFYS introduce a wavelet-based de-noising approach and copy number-specific signal variance model for suppressing and modelling the noise in signals. Then a hidden Markov model is employed for copy number inference. Finally, by using the absolute copy number profile, statistical significance of each aberration region is calculated in term of different aberration types, including amplification, deletion and loss of heterozygosity (LOH). The result shows that copy number specific-variance model and wavelet de-noising algorithm fits well with the Affymetrix SNP array signals, leading to more accurate estimation for diluted tumor sample (even with only 30% of cancer cells) than other existed methods. Results of examinations also demonstrate a good compatibility and extensibility for different Affymetrix SNP array platforms. Application on the 35 breast tumor samples shows that TAFFYS can automatically dissect the tumor samples and reveal statistically significant aberration regions where cancer-related genes locate.

Conclusions

TAFFYS provide an efficient and convenient tool for identifying the copy number alteration and allelic imbalance and assessing the recurrent aberrations for the tumor Affymetrix SNP array data.