UNLABELLED: Phenotypic Up-regulated Gene Support Vector Machine (PUGSVM) is a cancer Biomedical Informatics Grid (caBIG™) analytical tool for multiclass gene selection and classification. PUGSVM addresses the problem of imbalanced class separability, small sample size and high gene space dimensionality, where multiclass gene markers are defined by the union of one-versus-everyone phenotypic upregulated genes, and used by a well-matched one-versus-rest support vector machine. PUGSVM provides a simple yet more accurate strategy to identify statistically reproducible mechanistic marker genes for characterization of heterogeneous diseases. AVAILABILITY: http://www.cbil.ece.vt.edu/caBIG-PUGSVM.htm.

UNLABELLED: Differential dependency network (DDN) is a caBIG® (cancer Biomedical Informatics Grid) analytical tool for detecting and visualizing statistically significant topological changes in transcriptional networks representing two biological conditions. Developed under caBIG®'s In Silico Research Centers of Excellence (ISRCE) Program, DDN enables differential network analysis and provides an alternative way for defining network biomarkers predictive of phenotypes. DDN also serves as a useful systems biology tool for users across biomedical research communities to infer how genetic, epigenetic or environment variables may affect biological networks and clinical phenotypes. Besides the standalone Java application, we have also developed a Cytoscape plug-in, CytoDDN, to integrate network analysis and visualization seamlessly. AVAILABILITY: The Java and MATLAB source code can be downloaded at the authors' web site http://www.cbil.ece.vt.edu/software.htm.

BACKGROUND: Genes work coordinately as gene modules or gene networks. Various computational approaches have been proposed to find gene modules based on gene expression data; for example, gene clustering is a popular method for grouping genes with similar gene expression patterns. However, traditional gene clustering often yields unsatisfactory results for regulatory module identification because the resulting gene clusters are co-expressed but not necessarily co-regulated. RESULTS: We propose a novel approach, motif-guided sparse decomposition (mSD), to identify gene regulatory modules by integrating gene expression data and DNA sequence motif information. The mSD approach is implemented as a two-step algorithm comprising estimates of (1) transcription factor activity and (2) the strength of the predicted gene regulation event(s). Specifically, a motif-guided clustering method is first developed to estimate the transcription factor activity of a gene module; sparse component analysis is then applied to estimate the regulation strength, and so predict the target genes of the transcription factors. The mSD approach was first tested for its improved performance in finding regulatory modules using simulated and real yeast data, revealing functionally distinct gene modules enriched with biologically validated transcription factors. We then demonstrated the efficacy of the mSD approach on breast cancer cell line data and uncovered several important gene regulatory modules related to endocrine therapy of breast cancer. CONCLUSION: We have developed a new integrated strategy, namely motif-guided sparse decomposition (mSD) of gene expression data, for regulatory module identification. The mSD method features a novel motif-guided clustering method for transcription factor activity estimation by finding a balance between co-regulation and co-expression. The mSD method further utilizes a sparse decomposition method for regulation strength estimation. The experimental results show that such a motif-guided strategy can provide context-specific regulatory modules in both yeast and breast cancer studies.

BACKGROUND: In cancer, gene networks and pathways often exhibit dynamic behavior, particularly during the process of carcinogenesis. Thus, it is important to prioritize those genes that are strongly associated with the functionality of a network. Traditional statistical methods are often inept to identify biologically relevant member genes, motivating researchers to incorporate biological knowledge into gene ranking methods. However, current integration strategies are often heuristic and fail to incorporate fully the true interplay between biological knowledge and gene expression data. RESULTS: To improve knowledge-guided gene ranking, we propose a novel method called coordinative component analysis (COCA) in this paper. COCA explicitly captures those genes within a specific biological context that are likely to be expressed in a coordinative manner. Formulated as an optimization problem to maximize the coordinative effort, COCA is designed to first extract the coordinative components based on a partial guidance from knowledge genes and then rank the genes according to their participation strengths. An embedded bootstrapping procedure is implemented to improve statistical robustness of the solutions. COCA was initially tested on simulation data and then on published gene expression microarray data to demonstrate its improved performance as compared to traditional statistical methods. Finally, the COCA approach has been applied to stem cell data to identify biologically relevant genes in signaling pathways. As a result, the COCA approach uncovers novel pathway members that may shed light into the pathway deregulation in cancers. CONCLUSION: We have developed a new integrative strategy to combine biological knowledge and microarray data for gene ranking. The method utilizes knowledge genes for a guidance to first extract coordinative components, and then rank the genes according to their contribution related to a network or pathway. The experimental results show that such a knowledge-guided strategy can provide context-specific gene ranking with an improved performance in pathway member identification.

MOTIVATION: Significant efforts have been made to acquire data under different conditions and to construct static networks that can explain various gene regulation mechanisms. However, gene regulatory networks are dynamic and condition-specific; under different conditions, networks exhibit different regulation patterns accompanied by different transcriptional network topologies. Thus, an investigation on the topological changes in transcriptional networks can facilitate the understanding of cell development or provide novel insights into the pathophysiology of certain diseases, and help identify the key genetic players that could serve as biomarkers or drug targets. RESULTS: Here, we report a differential dependency network (DDN) analysis to detect statistically significant topological changes in the transcriptional networks between two biological conditions. We propose a local dependency model to represent the local structures of a network by a set of conditional probabilities. We develop an efficient learning algorithm to learn the local dependency model using the Lasso technique. A permutation test is subsequently performed to estimate the statistical significance of each learned local structure. In testing on a simulation dataset, the proposed algorithm accurately detected all the genes with network topological changes. The method was then applied to the estrogen-dependent T-47D estrogen receptor-positive (ER+) breast cancer cell line datasets and human and mouse embryonic stem cell datasets. In both experiments using real microarray datasets, the proposed method produced biologically meaningful results. We expect DDN to emerge as an important bioinformatics tool in transcriptional network analyses. While we focus specifically on transcriptional networks, the DDN method we introduce here is generally applicable to other biological networks with similar characteristics. AVAILABILITY: The DDN MATLAB toolbox and experiment data are available at http://www.cbil.ece.vt.edu/software.htm.

MOTIVATION: Unraveling the transcriptional regulatory program mediated by transcription factors (TFs) is a fundamental objective of computational biology, yet still remains a challenge. METHOD: Here, we present a new methodology that integrates microarray and TF binding data for unraveling transcriptional regulatory networks. The algorithm is based on a two-stage constrained matrix decomposition model. The model takes into account the non-linear structure in gene expression data, particularly in the TF-target gene interactions and the combinatorial nature of gene regulation by TFs. The gene expression profile is modeled as a linear weighted combination of the activity profiles of a set of TFs. The TF activity profiles are deduced from the expression levels of TF target genes, instead directly from TFs themselves. The TF-target gene relationships are derived from ChIP-chip and other TF binding data. The proposed algorithm can not only identify transcriptional modules, but also reveal regulatory programs of which TFs control which target genes in which specific ways (either activating or inhibiting). RESULTS: In comparison with other methods, our algorithm identifies biologically more meaningful transcriptional modules relating to specific TFs. We applied the new algorithm on yeast cell cycle and stress response data. While known transcriptional regulations were confirmed, novel TF-gene interactions were predicted and provide new insights into the regulatory mechanisms of the cell.

BACKGROUND: The main limitations of most existing clustering methods used in genomic data analysis include heuristic or random algorithm initialization, the potential of finding poor local optima, the lack of cluster number detection, an inability to incorporate prior/expert knowledge, black-box and non-adaptive designs, in addition to the curse of dimensionality and the discernment of uninformative, uninteresting cluster structure associated with confounding variables. RESULTS: In an effort to partially address these limitations, we develop the VIsual Statistical Data Analyzer (VISDA) for cluster modeling, visualization, and discovery in genomic data. VISDA performs progressive, coarse-to-fine (divisive) hierarchical clustering and visualization, supported by hierarchical mixture modeling, supervised/unsupervised informative gene selection, supervised/unsupervised data visualization, and user/prior knowledge guidance, to discover hidden clusters within complex, high-dimensional genomic data. The hierarchical visualization and clustering scheme of VISDA uses multiple local visualization subspaces (one at each node of the hierarchy) and consequent subspace data modeling to reveal both global and local cluster structures in a "divide and conquer" scenario. Multiple projection methods, each sensitive to a distinct type of clustering tendency, are used for data visualization, which increases the likelihood that cluster structures of interest are revealed. Initialization of the full dimensional model is based on first learning models with user/prior knowledge guidance on data projected into the low-dimensional visualization spaces. Model order selection for the high dimensional data is accomplished by Bayesian theoretic criteria and user justification applied via the hierarchy of low-dimensional visualization subspaces. Based on its complementary building blocks and flexible functionality, VISDA is generally applicable for gene clustering, sample clustering, and phenotype clustering (wherein phenotype labels for samples are known), albeit with minor algorithm modifications customized to each of these tasks. CONCLUSION: VISDA achieved robust and superior clustering accuracy, compared with several benchmark clustering schemes. The model order selection scheme in VISDA was shown to be effective for high dimensional genomic data clustering. On muscular dystrophy data and muscle regeneration data, VISDA identified biologically relevant co-expressed gene clusters. VISDA also captured the pathological relationships among different phenotypes revealed at the molecular level, through phenotype clustering on muscular dystrophy data and multi-category cancer data.

MOTIVATION: We address the problem of identifying gene transcriptional modules from gene expression data by proposing a new approach. Genes mostly interact with each other to form transcriptional modules for context-specific cellular activities or functions. Unraveling such transcriptional modules is important for understanding biological network, deciphering regulatory mechanisms and identifying biomarkers. METHOD: The proposed algorithm is based on two-stage matrix decomposition. We first model microarray data as non-linear mixtures and adopt the non-linear independent component analysis to reduce the non-linear distortion and separate the data into independent latent components. We then apply the probabilistic sparse matrix decomposition approach to model the 'hidden' expression profiles of genes across the independent latent components as linear weighted combinations of a small number of transcriptional regulator profiles. Finally, we propose a general scheme for identifying gene modules from the outcomes of the matrix decomposition. RESULTS: The proposed algorithm partitions genes into non-mutually exclusive transcriptional modules, independent from expression profile similarity measurement. The modules contain genes with not only similar but different expression patterns, and show the highest enrichment of biological functions in comparison with those by other methods. The usefulness of the algorithm was validated by a yeast microarray data analysis. AVAILABILITY: The software is available upon request to the authors.

SUMMARY: VISDA (Visual Statistical Data Analyzer) is a caBIG analytical tool for cluster modeling, visualization and discovery that has met silver-level compatibility under the caBIG initiative. Being statistically principled and visually interfaced, VISDA exploits both hierarchical statistics modeling and human gift for pattern recognition to allow a progressive yet interactive discovery of hidden clusters within high dimensional and complex biomedical datasets. The distinctive features of VISDA are particularly useful for users across the cancer research and broader research communities to analyze complex biological data. AVAILABILITY: http://gforge.nci.nih.gov/projects/visda/

The success of system test is measured by test quality and cost. System test quality and cost rely on several factors, such as component and board test quality, system test completeness, the support of system diagnostics, and a process that controls overall quality, resource and cost balances. Traditional structural test techniques used at the component level can achieve both high test quality and low test costs. This paper describes an approach to extend the functionalities of structural test techniques to the board and system level to improve the test accessibility, test time, and diagnostic capability. This approach has become practice in a large telecommunication company and the benefits received from this practice are tremendous. Examples will be given at the end of the paper

MOTIVATION: A major challenge in post-genomic research has been to understand how physiological and pathological phenotypes arise from the networks of expressed genes. Here, we addressed this issue by developing an algorithm to mimic the behavior of regulatory networks in silico and to identify the dynamic response to disease and changing cellular conditions. RESULTS: With regulatory pathway and gene expression data as input, the algorithm provides quantitative assessments of a wide range of responses, including susceptibility to disease, potential usefulness of a given drug, or consequences to such external stimuli as pharmacological interventions or caloric restriction. The algorithm is particularly amenable to the analysis of systems that are difficult to recapitulate in vitro, yet they may have important clinical value. The hypotheses derived from the algorithm were biologically relevant and were successfully validated via independent experiments, as illustrated here in the analysis of the leukemia-associated BCR-ABL pathway and the insulin/IGF pathway related to longevity. The algorithm correctly identified the leukemia drug target and genes important for longevity, and also provided new insights into our understanding of these two processes. AVAILABILITY: The software package is available upon request to the authors.

A neural-network-based framework has been developed to search for an optimal wavelet kernel that can be used for a specific image processing task. In this paper, a linear convolution neural network was employed to seek a wavelet that minimizes errors and maximizes compression efficiency for an image or a defined image pattern such as microcalcifications in mammograms and bone in computed tomography (CT) head images. We have used this method to evaluate the performance of tap-4 wavelets on mammograms, CTs, magnetic resonance images, and Lena images. We found that the Daubechies wavelet or those wavelets with similar filtering characteristics can produce the highest compression efficiency with the smallest mean-square-error for many image patterns including general image textures as well as microcalcifications in digital mammograms. However, the Haar wavelet produces the best results on sharp edges and low-noise smooth areas. We also found that a special wavelet whose low-pass filter coefficients are 0.32252136, 0.85258927, 1.38458542, and -0.14548269) produces the best preservation outcomes in all tested microcalcification features including the peak signal-to-noise ratio, the contrast and the figure of merit in the wavelet lossy compression scheme. Having analyzed the spectrum of the wavelet filters, we can find the compression outcomes and feature preservation characteristics as a function of wavelets. This newly developed optimization approach can be generalized to other image analysis applications where a wavelet decomposition is employed.

A multiple circular path convolution neural network (MCPCNN) architecture specifically designed for the analysis of tumor and tumor-like structures has been constructed. We first divided each suspected tumor area into sectors and computed the defined mass features for each sector independently. These sector features were used on the input layer and were coordinated by convolution kernels of different sizes that propagated signals to the second layer in the neural network system. The convolution kernels were trained, as required, by presenting the training cases to the neural network. In this study, randomly selected mammograms were processed by a dual morphological enhancement technique. Radiodense areas were isolated and were delineated using a region growing algorithm. The boundary of each region of interest was then divided into 36 sectors using 36 equi-angular dividers radiated from the center of the region. A total of 144 Breast Imaging-Reporting and Data System-based features (i.e., four features per sector for 36 sectors) were computed as input values for the evaluation of this newly invented neural network system. The overall performance was 0.78-0.80 for the areas (Az) under the receiver operating characteristic curves using the conventional feed-forward neural network in the detection of mammographic masses. The performance was markedly improved with Az values ranging from 0.84 to 0.89 using the MCPCNN. This paper does not intend to claim the best mass detection system. Instead it reports a potentially better neural network structure for analyzing a set of the mass features defined by an investigator.

This paper presents a statistical model supported approach for enhanced segmentation and extraction of suspicious mass areas from mammographic images. With an appropriate statistical description of various discriminate characteristics of both true and false candidates from the localized areas, an improved mass detection may be achieved in computer-assisted diagnosis (CAD). In this study, one type of morphological operation is derived to enhance disease patterns of suspected masses by cleaning up unrelated background clutters, and a model-based image segmentation is performed to localize the suspected mass areas using stochastic relaxation labeling scheme. We discuss the importance of model selection when a finite generalized Gaussian mixture is employed, and use the information theoretic criteria to determine the optimal model structure and parameters. Examples are presented to show the effectiveness of the proposed methods on mass lesion enhancement and segmentation when applied to mammographical images. Experimental results demonstrate that the proposed method achieves a very satisfactory performance as a preprocessing procedure for mass detection in CAD.

Based on the enhanced segmentation of suspicious mass areas, further development of computer-assisted mass detection may be decomposed into three distinctive machine learning tasks: 1) construction of the featured knowledge database; 2) mapping of the classified and/or unclassified data points in the database; and 3) development of an intelligent user interface. A decision support system may then be constructed as a complementary machine observer that should enhance the radiologists performance in mass detection. We adopt a mathematical feature extraction procedure to construct the featured knowledge database from all the suspicious mass sites localized by the enhanced segmentation. The optimal mapping of the data points is then obtained by learning the generalized normal mixtures and decision boundaries, where a is developed to carry out both soft and hard clustering. A visual explanation of the decision making is further invented as a decision support, based on an interactive visualization hierarchy through the probabilistic principal component projections of the knowledge database and the localized optimal displays of the retrieved raw data. A prototype system is developed and pilot tested to demonstrate the applicability of this framework to mammographic mass detection.

We have developed a combined method utilizing morphological operations, a finite generalized Gaussian mixture (FGGM) modeling, and a contextual Bayesian relaxation labeling technique (CBRL) to enhance and extract suspicious masses. A feature space is constructed based on multiple feature extraction from the regions of interest (ROIs). Finally, a multi-modular probabilistic decision-based classifier is employed to distinguish true masses from non-masses.

The objective of this research is to model the mammographic parenchymal, ductal patterns and enhance the microcalcifications using deterministic fractal approach. According to the theory of deterministic fractal geometry, images can be modeled by deterministic fractal objects which are attractors of sets of two-dimensional (2-D) affine transformations. The iterated functions systems and the collage theorem are the mathematical foundations of fractal image modeling. In this paper, a methodology based on fractal image modeling is developed to analyze and model breast background structures. We show that general mammographic parenchymal and ductal patterns can be well modeled by a set of parameters of affine transformations. Therefore, microcalcifications can be enhanced by taking the difference between the original image and the modeled image. Our results are compared with those of the partial wavelet reconstruction and morphological operation approaches. The results demonstrate that the fractal modeling method is an effective way to enhance microcalcifications. It may also be able to improve the detection and classification of microcalcifications in a computer-aided diagnosis system.

In routine chest radiographs, the mediastinum is often underexposed and vascular structures are obscured by the diaphragm. We have developed a region-based processing algorithm to enhance contrast and brightness of selected anatomical regions, such as the mediastinum, without altering the other regions. We employ wavelet processing technique to segment a chest radiograph into different gray level regions and then apply different degrees of contrast enhancement procedure to them. The image enhancement is controlled by a proposed sigmoid function. The enhanced images showed improved visualization in the mediastinum area over the original unprocessed chest radiographs. Furthermore, the visibility of vascular structures which are obscured by the diaphragm and mediastinum is improved.

This paper represents the authors' research on a hybrid method combined with contour coding, full-frame discrete wavelet (FFDWT) and full-frame discrete cosine transforms (FFDCT) for medical image compression. In this study, ten X-ray chest radiographs and ten mammograms were randomly selected from the authors' clinical database. Each image was split into the top three most significant bits (3MSB) image and the remaining was remapped to a least significant bit (RLSB) image. The 3MSB image was compressed by an error-free contour coding and received an average of 0.1 bit/pixel. The RLSB image was either transformed to a multi-channel wavelet or the cosine transform domain for entropy evaluation and compression.

We have developed several training methods in conjunction with a convolution neural network for general medical image pattern recognition. An unconventional method of using rotation and shift invariance is also proposed to enhance the neural net performance. The structure of the artificial neural network is a simplified network structure of the neocognitron. Two-dimensional local connection as a group is the fundamental architecture for the signal propagation in the convolution neural network. Weighting coefficients of convolution kernels are formed by the neural network through backpropagated training for this artificial neural net. In addition, radiologists' reading procedure was modelled in order to instruct the artificial neural network to recognize the predefined image patterns and those of interest to experts. Our training techniques involve (a) radiologists' rating for each suspected image area, (b) backpropagation of generalized distribution, (c) trainer imposed functions, (d) shift and rotation invariance of diagnosis interpretation, and (e) consistency of clinical input data using appropriate background reduction functions. We have tested these methods for detecting lung nodules on chest radiographs and microcalcications on mammograms. The performance studies have shown the potential use of this technique in a clinical environment. We also used a profile double-matching technique for initial nodule search and used a wavelet high pass filtering technique to enhance subtle clustered microcalcifications. We set searching parameters at a highly sensitive level to identify all potential disease areas. The artificial convolution neural network acts as a final detection classifier to determine whether a disease pattern is shown on the suspected image area.