skip to main content

Title: Inverse Projection Representation and Category Contribution Rate for Robust Tumor Recognition
Sparse representation based classification (SRC) methods have achieved remarkable results. SRC, however, still suffer from requiring enough training samples, insufficient use of test samples, and instability of representation. In this paper, a stable inverse projection representation based classification (IPRC) is presented to tackle these problems by effectively using test samples. An IPR is first proposed and its feasibility and stability are analyzed. A classification criterion named category contribution rate is constructed to match the IPR and complete classification. Moreover, a statistical measure is introduced to quantify the stability of representation-based classification methods. Based on the IPRC technique, a robust tumor recognition framework is presented by interpreting microarray gene expression data, where a two-stage hybrid gene selection method is introduced to select informative genes. Finally, the functional analysis of candidate's pathogenicity-related genes is given. Extensive experiments on six public tumor microarray gene expression datasets demonstrate the proposed technique is competitive with state-of-the-art methods.  more » « less
Award ID(s):
Author(s) / Creator(s):
; ; ; ;
Date Published:
Journal Name:
IEEE/ACM Transactions on Computational Biology and Bioinformatics
Page Range / eLocation ID:
1262 - 1275
Medium: X
Sponsoring Org:
National Science Foundation
More Like this
  1. Abstract Background

    Binary classification rules based on a small-sample of high-dimensional data (for instance, gene expression data) are ubiquitous in modern bioinformatics. Constructing such classifiers is challenging due to (a) the complex nature of underlying biological traits, such as gene interactions, and (b) the need for highly interpretable glass-box models. We use the theory of high dimensional model representation (HDMR) to build interpretable low dimensional approximations of the log-likelihood ratio accounting for the effects of each individual gene as well as gene-gene interactions. We propose two algorithms approximating the second order HDMR expansion, and a hypothesis test based on the HDMR formulation to identify significantly dysregulated pairwise interactions. The theory is seen as flexible and requiring only a mild set of assumptions.


    We apply our approach to gene expression data from both synthetic and real (breast and lung cancer) datasets comparing it also against several popular state-of-the-art methods. The analyses suggest the proposed algorithms can be used to obtain interpretable prediction rules with high prediction accuracies and to successfully extract significantly dysregulated gene-gene interactions from the data. They also compare favorably against their competitors across multiple synthetic data scenarios.


    The proposed HDMR-based approach appears to produce a reliable classifier that additionally allows one to describe how individual genes or gene-gene interactions affect classification decisions. Both real and synthetic data analyses suggest that our methods can be used to identify gene networks with dysregulated pairwise interactions, and are therefore appropriate for differential networks analysis.

    more » « less
  2. Abstract Motivation

    High-throughput sequencing technologies, in particular RNA sequencing (RNA-seq), have become the basic practice for genomic studies in biomedical research. In addition to studying genes individually, for example, through differential expression analysis, investigating co-ordinated expression variations of genes may help reveal the underlying cellular mechanisms to derive better understanding and more effective prognosis and intervention strategies. Although there exists a variety of co-expression network based methods to analyze microarray data for this purpose, instead of blindly extending these methods for microarray data that may introduce unnecessary bias, it is crucial to develop methods well adapted to RNA-seq data to identify the functional modules of genes with similar expression patterns.


    We have developed a fully Bayesian covariate-dependent negative binomial factor analysis (dNBFA) method—dNBFA—for RNA-seq count data, to capture coordinated gene expression changes, while considering effects from covariates reflecting different influencing factors. Unlike existing co-expression network based methods, our proposed model does not require multiple ad-hoc choices on data processing, transformation, as well as co-expression measures and can be directly applied to RNA-seq data. Furthermore, being capable of incorporating covariate information, the proposed method can tackle setups with complex confounding factors in different experiment designs. Finally, the natural model parameterization removes the need for a normalization preprocessing step, as commonly adopted to compensate for the effect of sequencing-depth variations. Efficient Bayesian inference of model parameters is derived by exploiting conditional conjugacy via novel data augmentation techniques. Experimental results on several real-world RNA-seq datasets on complex diseases suggest dNBFA as a powerful tool for discovering the gene modules with significant differential expression and meaningful biological insight.

    Availability and implementation

    dNBFA is implemented in R language and is available at

    more » « less
  3. null (Ed.)
    Abstract Background DNA methylation is an epigenetic event involving the addition of a methyl-group to a cytosine-guanine base pair (i.e., CpG site). It is associated with different cancers. Our research focuses on studying non-small cell lung cancer hemimethylation, which refers to methylation occurring on only one of the two DNA strands. Many studies often assume that methylation occurs on both DNA strands at a CpG site. However, recent publications show the existence of hemimethylation and its significant impact. Therefore, it is important to identify cancer hemimethylation patterns. Methods In this paper, we use the Wilcoxon signed rank test to identify hemimethylated CpG sites based on publicly available non-small cell lung cancer methylation sequencing data. We then identify two types of hemimethylated CpG clusters, regular and polarity clusters, and genes with large numbers of hemimethylated sites. Highly hemimethylated genes are then studied for their biological interactions using available bioinformatics tools. Results In this paper, we have conducted the first-ever investigation of hemimethylation in lung cancer. Our results show that hemimethylation does exist in lung cells either as singletons or clusters. Most clusters contain only two or three CpG sites. Polarity clusters are much shorter than regular clusters and appear less frequently. The majority of clusters found in tumor samples have no overlap with clusters found in normal samples, and vice versa. Several genes that are known to be associated with cancer are hemimethylated differently between the cancerous and normal samples. Furthermore, highly hemimethylated genes exhibit many different interactions with other genes that may be associated with cancer. Hemimethylation has diverse patterns and frequencies that are comparable between normal and tumorous cells. Therefore, hemimethylation may be related to both normal and tumor cell development. Conclusions Our research has identified CpG clusters and genes that are hemimethylated in normal and lung tumor samples. Due to the potential impact of hemimethylation on gene expression and cell function, these clusters and genes may be important to advance our understanding of the development and progression of non-small cell lung cancer. 
    more » « less
  4. Summary

    Precise classification of tumours is critical for the diagnosis and treatment of cancer. Diagnostic pathology has traditionally relied on macroscopic and microscopic histology and tumour morphology as the basis for the classification of tumours. Current classification frameworks, however, cannot discriminate between tumours with similar histopathologic features, which vary in clinical course and in response to treatment. In recent years, there has been a move towards the use of complementary deoxyribonucleic acid microarrays for the classi-fication of tumours. These high throughput assays provide relative messenger ribonucleic acid expression measurements simultaneously for thousands of genes. A key statistical task is to perform classification via different expression patterns. Gene expression profiles may offer more information than classical morphology and may provide an alternative to classical tumour diagnosis schemes. The paper considers several Bayesian classification methods based on reproducing kernel Hilbert spaces for the analysis of microarray data. We consider the logistic likelihood as well as likelihoods related to support vector machine models. It is shown through simulation and examples that support vector machine models with multiple shrinkage parameters produce fewer misclassification errors than several existing classical methods as well as Bayesian methods based on the logistic likelihood or those involving only one shrinkage parameter.

    more » « less
  5. Abstract Motivation Detecting cancer gene expression and transcriptome changes with mRNA-sequencing (RNA-Seq) or array-based data are important for understanding the molecular mechanisms underlying carcinogenesis and cellular events during cancer progression. In previous studies, the differentially expressed genes were detected across patients in one cancer type. These studies ignored the role of mRNA expression changes in driving tumorigenic mechanisms that are either universal or specific in different tumor types. To address the problem, we introduce two network-based multi-task learning frameworks, NetML and NetSML, to discover common differentially expressed genes shared across different cancer types as well as differentially expressed genes specific to each cancer type. The proposed frameworks consider the common latent gene co-expression modules and gene-sample biclusters underlying the multiple cancer datasets to learn the knowledge crossing different tumor types. Results Large-scale experiments on simulations and real cancer high-throughput datasets validate that the proposed network-based multi-task learning frameworks perform better sample classification compared with the models without the knowledge sharing across different cancer types. The common and cancer specific molecular signatures detected by multi-task learning frameworks on TCGA ovarian cancer, breast cancer, and prostate cancer datasets are correlated with the known marker genes and enriched in cancer relevant KEGG pathways and Gene Ontology terms. Availability and Implementation Source code is available at: Supplementary information Supplementary data are available at Bioinformatics 
    more » « less