Modeling Of Gene Expression Data Research Articles

GeNetOntology: identifying affected gene ontology terms via grouping, scoring, and modeling of gene expression data utilizing biological knowledge-based machine learning.

Introduction: Identifying significant sets of genes that are up/downregulated under specific conditions is vital to understand disease development mechanisms at the molecular level. Along this line, in order to analyze transcriptomic data, several computational feature selection (i.e., gene selection) methods have been proposed. On the other hand, uncovering the core functions of the selected genes provides a deep understanding of diseases. In order to address this problem, biological domain knowledge-based feature selection methods have been proposed. Unlike computational gene selection approaches, these domain knowledge-based methods take the underlying biology into account and integrate knowledge from external biological resources. Gene Ontology (GO) is one such biological resource that provides ontology terms for defining the molecular function, cellular component, and biological process of the gene product. Methods: In this study, we developed a tool named GeNetOntology which performs GO-based feature selection for gene expression data analysis. In the proposed approach, the process of Grouping, Scoring, and Modeling (G-S-M) is used to identify significant GO terms. GO information has been used as the grouping information, which has been embedded into a machine learning (ML) algorithm to select informative ontology terms. The genes annotated with the selected ontology terms have been used in the training part to carry out the classification task of the ML model. The output is an important set of ontologies for the two-class classification task applied to gene expression data for a given phenotype. Results: Our approach has been tested on 11 different gene expression datasets, and the results showed that GeNetOntology successfully identified important disease-related ontology terms to be used in the classification model. Discussion: GeNetOntology will assist geneticists and scientists to identify a range of disease-related genes and ontologies in transcriptomic data analysis, and it will also help doctors design diagnosis platforms and improve patient treatment plans.

Information-incorporated Gaussian graphical model for gene expression data.

In the analysis of gene expression data, network approaches take a system perspective and have played an irreplaceably important role. Gaussian graphical models (GGMs) have been popular in the network analysis of gene expression data. They investigate the conditional dependence between genes and "transform" the problem of estimating network structures into a sparse estimation of precision matrices. When there is a moderate to large number of genes, the number of parameters to be estimated may overwhelm the limited sample size, leading to unreliable estimation and selection. In this article, we propose incorporating information from previous studies (for example, those deposited at PubMed) to assist estimating the network structure in the present data. It is recognized that such information can be partial, biased, or even wrong. A penalization-based estimation approach is developed, shown to have consistency properties, and realized using an effective computational algorithm. Simulation demonstrates its competitive performance under various information accuracy scenarios. The analysis of TCGA lung cancer prognostic genes leads to network structures different from thealternatives.

Nontargeted Pattern Recognition in the Search for Pyrolysis Gas Chromatography/Mass Spectrometry Resin Markers in Historic Lacquered Objects.

A differential expression analysis technology developed for linear modeling of gene expression data was used in combination with thermally assisted hydrolysis and methylation gas chromatography/mass spectrometry (THM-GC/MS) to support the analysis of lacquers and varnishes on historical objects. Exudates from tropical trees, such as Manila copal, sandarac, South American copal, and Congo copal, which were frequently used in finishing layers on decorative objects up to the early 20th century, were compared through this approach. Highly discriminating features indicate biomarkers that can help to identify copals in resinous lacquers. The approach allows new, more systematic ways for finding biomarkers in the analysis of lacquered objects of art and varnishes.

Editor's Highlight: Application of Gene Set Enrichment Analysis for Identification of Chemically Induced, Biologically Relevant Transcriptomic Networks and Potential Utilization in Human Health Risk Assessment.

The rate of new chemical development in commerce combined with a paucity of toxicity data for legacy chemicals presents a unique challenge for human health risk assessment. There is a clear need to develop new technologies and incorporate novel data streams to more efficiently inform derivation of toxicity values. One avenue of exploitation lies in the field of transcriptomics and the application of gene expression analysis to characterize biological responses to chemical exposures. In this context, gene set enrichment analysis (GSEA) was employed to evaluate tissue-specific, dose-response gene expression data generated following exposure to multiple chemicals for various durations. Patterns of transcriptional enrichment were evident across time and with increasing dose, and coordinated enrichment plausibly linked to the etiology of the biological responses was observed. GSEA was able to capture both transient and sustained transcriptional enrichment events facilitating differentiation between adaptive versus longer term molecular responses. When combined with benchmark dose (BMD) modeling of gene expression data from key drivers of biological enrichment, GSEA facilitated characterization of dose ranges required for enrichment of biologically relevant molecular signaling pathways, and promoted comparison of the activation dose ranges required for individual pathways. Median transcriptional BMD values were calculated for the most sensitive enriched pathway as well as the overall median BMD value for key gene members of significantly enriched pathways, and both were observed to be good estimates of the most sensitive apical endpoint BMD value. Together, these efforts support the application of GSEA to qualitative and quantitative human health risk assessment.

Automated Protocol for Large-Scale Modeling of Gene Expression Data.

With the continued rise of phenotypic- and genotypic-based screening projects, computational methods to analyze, process, and ultimately make predictions in this field take on growing importance. Here we show how automated machine learning workflows can produce models that are predictive of differential gene expression as a function of a compound structure using data from A673 cells as a proof of principle. In particular, we present predictive models with an average accuracy of greater than 70% across a highly diverse ∼1000 gene expression profile. In contrast to the usual in silico design paradigm, where one interrogates a particular target-based response, this work opens the opportunity for virtual screening and lead optimization for desired multitarget gene expression profiles.

Knowledge transfer via classification rules using functional mapping for integrative modeling of gene expression data.

BackgroundMost ‘transcriptomic’ data from microarrays are generated from small sample sizes compared to the large number of measured biomarkers, making it very difficult to build accurate and generalizable disease state classification models. Integrating information from different, but related, ‘transcriptomic’ data may help build better classification models. However, most proposed methods for integrative analysis of ‘transcriptomic’ data cannot incorporate domain knowledge, which can improve model performance. To this end, we have developed a methodology that leverages transfer rule learning and functional modules, which we call TRL-FM, to capture and abstract domain knowledge in the form of classification rules to facilitate integrative modeling of multiple gene expression data. TRL-FM is an extension of the transfer rule learner (TRL) that we developed previously. The goal of this study was to test our hypothesis that “an integrative model obtained via the TRL-FM approach outperforms traditional models based on single gene expression data sources”.ResultsTo evaluate the feasibility of the TRL-FM framework, we compared the area under the ROC curve (AUC) of models developed with TRL-FM and other traditional methods, using 21 microarray datasets generated from three studies on brain cancer, prostate cancer, and lung disease, respectively. The results show that TRL-FM statistically significantly outperforms TRL as well as traditional models based on single source data. In addition, TRL-FM performed better than other integrative models driven by meta-analysis and cross-platform data merging.ConclusionsThe capability of utilizing transferred abstract knowledge derived from source data using feature mapping enables the TRL-FM framework to mimic the human process of learning and adaptation when performing related tasks. The novel TRL-FM methodology for integrative modeling for multiple ‘transcriptomic’ datasets is able to intelligently incorporate domain knowledge that traditional methods might disregard, to boost predictive power and generalization performance. In this study, TRL-FM’s abstraction of knowledge is achieved in the form of functional modules, but the overall framework is generalizable in that different approaches of acquiring abstract knowledge can be integrated into this framework.Electronic supplementary materialThe online version of this article (doi:10.1186/s12859-015-0643-8) contains supplementary material, which is available to authorized users.

Robust modeling of differential gene expression data using normal/independent distributions: a Bayesian approach.

In this paper, the problem of identifying differentially expressed genes under different conditions using gene expression microarray data, in the presence of outliers, is discussed. For this purpose, the robust modeling of gene expression data using some powerful distributions known as normal/independent distributions is considered. These distributions include the Student’s t and normal distributions which have been used previously, but also include extensions such as the slash, the contaminated normal and the Laplace distributions. The purpose of this paper is to identify differentially expressed genes by considering these distributional assumptions instead of the normal distribution. A Bayesian approach using the Markov Chain Monte Carlo method is adopted for parameter estimation. Two publicly available gene expression data sets are analyzed using the proposed approach. The use of the robust models for detecting differentially expressed genes is investigated. This investigation shows that the choice of model for differentiating gene expression data is very important. This is due to the small number of replicates for each gene and the existence of outlying data. Comparison of the performance of these models is made using different statistical criteria and the ROC curve. The method is illustrated using some simulation studies. We demonstrate the flexibility of these robust models in identifying differentially expressed genes.

Cancer Outlier Analysis Based on Mixture Modeling of Gene Expression Data

Molecular heterogeneity of cancer, partially caused by various chromosomal aberrations or gene mutations, can yield substantial heterogeneity in gene expression profile in cancer samples. To detect cancer-related genes which are active only in a subset of cancer samples or cancer outliers, several methods have been proposed in the context of multiple testing. Such cancer outlier analyses will generally suffer from a serious lack of power, compared with the standard multiple testing setting where common activation of genes across all cancer samples is supposed. In this paper, we consider information sharing across genes and cancer samples, via a parametric normal mixture modeling of gene expression levels of cancer samples across genes after a standardization using the reference, normal sample data. A gene-based statistic for gene selection is developed on the basis of a posterior probability of cancer outlier for each cancer sample. Some efficiency improvement by using our method was demonstrated, even under settings with misspecified, heavy-tailed t-distributions. An application to a real dataset from hematologic malignancies is provided.

Statistical Analysis of Biomarkers for Personalized Medicine

Recently there has been enhanced and advanced biomedical technology such as high-throughput microarrays and molecular imaging to monitor SNPs, gene and protein expressions, and so forth, to provide exhaustive situations for individuals. In principle we could get much more information to know the biological and medical status from such data sets, which are viewed as biomarkers in a wide sense to help to do identification, association, and prediction studies for phenotypes such as cancer subtypes, prognosis, treatment responsiveness, and adverse reactions for personalized medicine. However, it is frequently difficult to extract only an informative part in the hull of data sets which include a garbage heap of uninformative observations. In particular, we cannot confirm statistical evidence because of the small sample size relative to the dimension of the data when we achieve the practical use of such statistical applications. For example, if we implement machine learning methods for the prediction of the treatment effects, then we typically face difficulties to confirm the reproducibility and robustness for the performance. In the meanwhile, effective study design is crucial for developing and validating biomarkers. In effect we present eight papers challenging this difficult situation of statistical analysis for biomarkers including statistical estimation, prediction, and testing hypothesis. The paper, “The number of candidate variants in exome sequencing for Mendelian Disease under no genetic heterogeneity,” by J. Nishino and S. Mano studies the expected number of candidate single nucleotide variants (SNVs) in exome data for autosomal dominant or recessive Mendelian disorders so that the filtering method is useful with an assumption of “no genetic heterogeneity.” The paper, “Radial basis function-sparse partial least squares for application to brain imaging data,” by H. Yoshida et al. proposes a novel statistical method, called radial basis function sparse partial least squares (RBF-sPLS), for investigating the relationship between clinical characteristics and brain morphology based on three-dimensional MRI data. The paper, “Power analysis of C-TDT for small sample size genome-wide association studies by the joint use of case-parent trios and pairs,” by F. Rajabli et al. addresses family-based genetic association studies with missing genotype information for one of the parents. The paper provides a simulation study for the disequilibrium test statistic across different sample sizes for a family-based genome-wide association study. The paper, “Genomic biomarkers for personalized medicine: development and validation in clinical studies” by S. Matsui addresses the two critical statistical analyses of high-dimensional genomic data, gene screening and prediction, in the framework of development and validation of genomic biomarkers or signatures with biomarker-based clinical trial designs to assess clinical utility of a biomarker or a new treatment with a companion biomarker. The paper, “Multiple suboptimal solutions for prediction rules in gene expression data,” by O. Komori et al. reanalyzes the gene expression data for pattern recognition of phenotypes to extract informative features embedded in the data. The paper concludes that it is not possible to extract only informative genes with high performance in the all observed genes and points out that the mutual coherence among genes is too high to find the solution of informative genes. The paper, “An empirical Bayes optimal discovery procedure based on semiparametric hierarchical mixture models,” by H. Noma and S. Matsui proposes an empirical Bayes optimal discovery procedure with the smoothing-by-roughening approach in semiparametric hierarchical mixture models. This approach provides analytically a tractable posterior distribution with the flexible prior section in genome-wide studies. The paper, “Cancer outlier analysis based on mixture modeling of gene expression data,” by K. Mori et al. proposes a gene-based statistic for gene selection on the basis of a posterior probability of cancer outlier for each cancer sample with an application to real data from hematologic malignancies. The paper, “A robust rerank approach for feature selection and its application to pooling-based GWA studies,” by J. Liu et al. proposes a method based on the concept of rank-over-variable which is shown to be insensitive to the selection of tuning parameters compared with t-statistics, AUC statistics, and SAM with simulation studies and real data analysis of pooling-based genome-wide association (GWA) study to demonstrate the usefulness of their method. Shinto Eguchi Shigeyuki Matsui Su-Yun Huang Chuhsing Kate Hsiao

Efficient Feature Selection Model for Gene Expression Data

Finding subset of informative gene is very crucial for biology process because several genes increase sharply and most of them are not related with others. In general, feature selection technique consists of two steps 1) all genes is ranked by a filter approach 2) rank list is sent to a wrapper approach. Nevertheless, the accuracy rate for recognition gene is not enough. Therefore, this paper proposes efficient feature selection model for gene expression data. First, two filter approaches are used to define many subset of attribute such as Correlation based Feature Selection (Cfs) and Gain Ratio (GR). Second, wrapper approach is used to evaluate each length of attribute that based on Support Vector Machine (SVM) and Random Forest (RF). The result of experiment depicts CfsSVM, CfsRF, GRSVM, and GRRF based on proposed model produce higher accuracy rate such as 87.10%, 90.32%, 87.10, and 88.71%, respectively.

Quantitative utilization of prior biological knowledge in the Bayesian network modeling of gene expression data

BackgroundBayesian Network (BN) is a powerful approach to reconstructing genetic regulatory networks from gene expression data. However, expression data by itself suffers from high noise and lack of power. Incorporating prior biological knowledge can improve the performance. As each type of prior knowledge on its own may be incomplete or limited by quality issues, integrating multiple sources of prior knowledge to utilize their consensus is desirable.ResultsWe introduce a new method to incorporate the quantitative information from multiple sources of prior knowledge. It first uses the Naïve Bayesian classifier to assess the likelihood of functional linkage between gene pairs based on prior knowledge. In this study we included cocitation in PubMed and schematic similarity in Gene Ontology annotation. A candidate network edge reservoir is then created in which the copy number of each edge is proportional to the estimated likelihood of linkage between the two corresponding genes. In network simulation the Markov Chain Monte Carlo sampling algorithm is adopted, and samples from this reservoir at each iteration to generate new candidate networks. We evaluated the new algorithm using both simulated and real gene expression data including that from a yeast cell cycle and a mouse pancreas development/growth study. Incorporating prior knowledge led to a ~2 fold increase in the number of known transcription regulations recovered, without significant change in false positive rate. In contrast, without the prior knowledge BN modeling is not always better than a random selection, demonstrating the necessity in network modeling to supplement the gene expression data with additional information.Conclusionour new development provides a statistical means to utilize the quantitative information in prior biological knowledge in the BN modeling of gene expression data, which significantly improves the performance.

A brassinosteroid transcriptional network revealed by genome‐wide identification of BESI target genes in Arabidopsis thaliana

Brassinosteroids (BRs) are important regulators for plant growth and development. BRs signal to control the activities of the BES1 and BZR1 family transcription factors. The transcriptional network through which BES1 and BZR regulate large number of target genes is mostly unknown. By combining chromatin immunoprecipitation coupled with Arabidopsis tiling arrays (ChIP-chip) and gene expression studies, we have identified 1609 putative BES1 target genes, 404 of which are regulated by BRs and/or in gain-of-function bes1-D mutant. BES1 targets contribute to BR responses and interactions with other hormonal or light signaling pathways. Computational modeling of gene expression data using Algorithm for the Reconstruction of Accurate Cellular Networks (ARACNe) reveals that BES1-targeted transcriptional factors form a gene regulatory network (GRN). Mutants of many genes in the network displayed defects in BR responses. Moreover, we found that BES1 functions to inhibit chloroplast development by repressing the expression of GLK1 and GLK2 transcription factors, confirming a hypothesis generated from the GRN. Our results thus provide a global view of BR regulated gene expression and a GRN that guides future studies in understanding BR-regulated plant growth.

Dimension Reduction of Microarray Data in the Presence of a Censored Survival Response: A Simulation Study

An important aspect of microarray studies involves the prediction of patient survival based on their gene expression levels. To cope with the high dimensionality of the microarray gene expression data, it is customary to first reduce the dimension of the gene expression data via dimension reduction methods, and then use the Cox proportional hazards model to predict patient survival. In this paper, we propose a variant of Partial Least Squares, denoted as Rank-based Modified Partial Least Squares (RMPLS), that is insensitive to outlying values of both the response and the gene expressions. We assess the performance of RMPLS and several dimension reduction methods using a simulation model for gene expression data with a censored response. In particular, Principal Component Analysis (PCA), modified Partial Least Squares (MPLS), RMPLS, Sliced Inverse Regression (SIR), Correlation Principal Component Regression (CPCR), Supervised Principal Component Regression (SPCR) and Univariate Selection (UNIV) are compared in terms of mean squared error of the estimated survival function and the estimated coefficients of the covariates, and in terms of the bias of the estimated survival function. It turns out that RMPLS outperforms all other methods in terms of the mean squared error and the bias of the survival function in the presence of outliers in the response. In addition, RMPLS is comparable to MPLS in the absence of outliers. In this setting, both RMPLS and MPLS outperform all other methods considered in this study in terms of mean squared error and bias of the estimated survival function.

Multivariate curve resolution of time course microarray data.

BackgroundModeling of gene expression data from time course experiments often involves the use of linear models such as those obtained from principal component analysis (PCA), independent component analysis (ICA), or other methods. Such methods do not generally yield factors with a clear biological interpretation. Moreover, implicit assumptions about the measurement errors often limit the application of these methods to log-transformed data, destroying linear structure in the untransformed expression data.ResultsIn this work, a method for the linear decomposition of gene expression data by multivariate curve resolution (MCR) is introduced. The MCR method is based on an alternating least-squares (ALS) algorithm implemented with a weighted least squares approach. The new method, MCR-WALS, extracts a small number of basis functions from untransformed microarray data using only non-negativity constraints. Measurement error information can be incorporated into the modeling process and missing data can be imputed. The utility of the method is demonstrated through its application to yeast cell cycle data.ConclusionProfiles extracted by MCR-WALS exhibit a strong correlation with cell cycle-associated genes, but also suggest new insights into the regulation of those genes. The unique features of the MCR-WALS algorithm are its freedom from assumptions about the underlying linear model other than the non-negativity of gene expression, its ability to analyze non-log-transformed data, and its use of measurement error information to obtain a weighted model and accommodate missing measurements.

Partial least squares dimension reduction for microarray gene expression data with a censored response

An important application of DNA microarray technologies involves monitoring the global state of transcriptional program in tumor cells. One goal in cancer microarray studies is to compare the clinical outcome, such as relapse-free or overall survival, for subgroups of patients defined by global gene expression patterns. A method of comparing patient survival, as a function of gene expression, was recently proposed in [Bioinformatics 18 (2002) 1625] by Nguyen and Rocke. Due to the (a) high-dimensionality of microarray gene expression data and (b) censored survival times, a two-stage procedure was proposed to relate survival times to gene expression profiles. The first stage involves dimensionality reduction of the gene expression data by partial least squares (PLS) and the second stage involves prediction of survival probability using proportional hazard regression. In this paper, we provide a systematic assessment of the performance of this two-stage procedure. PLS dimension reduction involves complex non-linear functions of both the predictors and the response data, rendering exact analytical study intractable. Thus, we assess the methodology under a simulation model for gene expression data with a censored response variable. In particular, we compare the performance of PLS dimension reduction relative to dimension reduction via principal components analysis (PCA) and to a modified PLS (MPLS) approach. PLS performed substantially better relative to dimension reduction via PCA when the total predictor variance explained is low to moderate (e.g. 40%–60%). It performed similar to MPLS and slightly better in some cases. Additionally, we examine the effect of censoring on dimension reduction stage. The performance of all methods deteriorates for a high censoring rate, although PLS–PH performed relatively best overall.

A Clustering Method for Discovering Patterns Using Gene Regulatory Processes

Clustering is a descriptive task that seeks to identify homogeneous groups of objects based on the values of their attributes (dimensions). The k-means and hierarchical as well as self-organizing maps have all been used for clustering expression profiles and a number of algorithms have been developed for expression data and applied to analyze it. These Clustering methods usually use metric distance for similarity measure. Correlation coefficient is also used but has a problem that it removes difference attributable to both the mean and the dispersion of the observations. Moreover, it may be unreasonable that every observation is assigned to one of clusters when the purpose is to find groups with similar pattern. Alter et al. [1] show that several significant eigengenes and the corresponding eigenarrays capture most of the expression information in field of genetics and some of the eigengenes represent independent regulatory programs or processes from its expression pattern across all arrays. Normalizing the data by filtering out the eigengenes (and the corresponding eigenarrays) that are inferred to represent noise or experimental artifacts enables meaningful comparison of the expression of different genes across different arrays in different expression. Such normalization may improve any further analysis of the expression data. Q-mode factor analysis has been used to find groups like clustering analysis and could be a good method to find patterns. However, this approach to clustering is plagued with a number of problems [3]. Genes with similar expression profiles may have something in common in their regulatory mechanisms. In this study, Q-mode factor analysis is used to model the gene regulatory processes which control genes and gene products and we modify the Q-mode factor analysis for discovering useful patterns in gene expression data. As a result of the factor modeling of gene expression data, our method can improve the result of clustering by removing noises and produce characteristic values of expression data.