Independent component analysis-based penalized discriminant method for tumor classification using gene expression data

BackgroundTranscripts with alternative 5′-untranslated regions (UTRs) result from the activity of alternative promoters and they can determine gene expression by influencing its stability and translational efficiency, thus executing complex regulation of developmental, physiological and pathological processes. Transcriptional regulation of human SMAD4, a key tumor suppressor deregulated in most gastrointestinal cancers, entails four alternative promoters. These promoters and alternative transcripts they generate remain unexplored as contributors to the SMAD4 deregulation in cancer. The aim of this study was to investigate the relative abundance of the transcript SMAD4–201 in colorectal cell lines and tissues in order to establish if its fluctuations may be associated with colorectal cancer (CRC).MethodsRelative abundance of SMAD4–201 in total SMAD4 mRNA was analyzed using quantitative PCR in a set of permanent human colon cell lines and tumor and corresponding healthy tissue samples from patients with CRC.ResultsThe relative abundance of SMAD4–201 in analyzed cell lines varied between 16 and 47%. A similar relative abundance of SMAD4–201 transcript was found in the majority of analyzed human tumor tissue samples, and it was averagely 20% lower in non-malignant in comparison to malignant tissue samples (p = 0.001). Transcript SMAD4–202 was not detectable in any of the analyzed samples, so the observed fluctuations in the composition of SMAD4 transcripts can be attributed to transcripts other than SMAD4–201 and SMAD4–202.ConclusionThe expression profile of SMAD4–201 in human tumor and non-tumor tissue samples may indicate the translational potential of this molecule in CRC, but further research is needed to clarify its usability as a potential biomarker for early diagnosis.

The classification of tissue samples based on gene expression data is an important problem in medical diagnosis of diseases such as cancer. In gene expression data, the number of genes is usually very high (in the thousands) compared to the number of data samples (in the tens or low hundreds); that is, the data dimension is large compared to the number of data points (such data is said to be undersampled). To cope with performance and accuracy problems associated with high dimensionality, it is commonplace to apply a preprocessing step that transforms the data to a space of significantly lower dimension with limited loss of the information present in the original data. Linear Discriminant Analysis (LDA) is a well-known technique for dimension reduction and feature extraction, but it is not applicable for undersampled data due to singularity problems associated with the matrices in the underlying representation. This paper presents a dimension reduction and feature extraction scheme, called Uncorrelated Linear Discriminant Analysis (ULDA), for undersampled problems and illustrates its utility on gene expression data. ULDA employs the Generalized Singular Value Decomposition method to handle undersampled data and the features that it produces in the transformed space are uncorrelated, which makes it attractive for gene expression data. The properties of ULDA are established rigorously and extensive experimental results on gene expression data are presented to illustrate its effectiveness in classifying tissue samples. These results provide a comparative study of various state-of-the-art classification methods on well-known gene expression data sets.

Deoxyribonucleic acid (DNA) microarrays are part of a promising class of biotechnologies that allow the simultaneous monitoring of expression levels in cells for thousands of genes. One of important issues in microarray experiments is the classification of biological samples and predicting clinical or other outcomes using gene expression data. A closely related issue is the identification of marker genes that have good predictive power for an outcome of interest. Although classification is not a new subject in the statistical literature, the large number of genes with relatively small sample size generated by microarray experiments raises new computational challenges. In this study, the gene expressions of breast cancer tumors are investigated and the performance of several popular classification methods, including decision tree, logistic regression, linear discriminant analysis, and k-nearest neighbor are compared. The results show that certain genes are significantly differentially expressed across groups of patients, and k-nearest neighbor method achieves better performance in class prediction than the other classification methods.

Gene expression data that is being used to gather information from tissue samples is expected to significantly improve the development of efficient tumor diagnosis. For more accurate classification of tumor, extracting discriminant components from thousands of genes is an important problem which becomes challenging task due to the large number of genes and small sample size. We propose a novel approach which combines the revised feature score criterion with independent component analysis that has been developing recently to further improve the classification performance of gene expression data based on support vector machines. Two sets of gene expression data (colon tumor dataset and leukemia dataset) are examined to confirm that the proposed approach can extract a small quantity of independent components which drastically reduce the dimensionality of the original gene expression data when retaining higher recognition rate. For example, 100% cross-validation accuracy has been achieved with only extracting 2 or 3 independent components from leukemia dataset in our experiments.

Feature Selection From Gene Expression Data Using Simulated Annealing and Partial Least Squares Regression Coefficients

Breast cancer outcome can be predicted using models derived from gene expression data or clinical data. Only a few studies have created a single prediction model using both gene expression and clinical data. These studies often remain inconclusive regarding an obtained improvement in prediction performance. We rigorously compare three different integration strategies (early, intermediate, and late integration) as well as classifiers employing no integration (only one data type) using five classifiers of varying complexity. We perform our analysis on a set of 295 breast cancer samples, for which gene expression data and an extensive set of clinical parameters are available as well as four breast cancer datasets containing 521 samples that we used as independent validation.mOn the 295 samples, a nearest mean classifier employing a logical OR operation (late integration) on clinical and expression classifiers significantly outperforms all other classifiers. Moreover, regardless of the integration strategy, the nearest mean classifier achieves the best performance. All five classifiers achieve their best performance when integrating clinical and expression data. Repeating the experiments using the 521 samples from the four independent validation datasets also indicated a significant performance improvement when integrating clinical and gene expression data. Whether integration also improves performances on other datasets (e.g. other tumor types) has not been investigated, but seems worthwhile pursuing. Our work suggests that future models for predicting breast cancer outcome should exploit both data types by employing a late OR or intermediate integration strategy based on nearest mean classifiers.

Gene expression based cancer classification

Tumor purity is the percent of cancer cells present in a sample of tumor tissue. The non-cancerous cells (immune cells, fibroblasts, etc.) have an important role in tumor biology. We applied a supervised machine learning method, XGBoost, to data from 33 TCGA tumor types to predict tumor purity using RNA-seq gene expression data. Across the 33 tumor types, the median correlation between observed and predicted tumor-purity ranged from 0.75 to 0.87 with small root mean square errors, suggesting that tumor purity can be accurately predicted using expression data. We further confirmed that a ten-gene set (CSF2RB, RHOH, C1S, CCDC69, CCL22, CYTIP, POU2AF1, FGR, CCL21, and IL7R) whose expression levels alone were predictive of tumor purity regardless of tumor type. We tested the predicative power of the ten-gene set on an independent dataset that was not from TCGA and showed that the expression levels of the ten genes can accurately predict the cancer cell proportions in those independent samples. The correlation coefficient between the predicted and experimentally obtained tumor purity was 0.88. Our analyses suggested that the ten-gene set may serve as a biomarker for tumor purity prediction using gene expression data. Citation Format: Yuanyuan Li. Putative biomarkers for tumor sample purity prediction based on gene expression data [abstract]. In: Proceedings of the American Association for Cancer Research Annual Meeting 2019; 2019 Mar 29-Apr 3; Atlanta, GA. Philadelphia (PA): AACR; Cancer Res 2019;79(13 Suppl):Abstract nr 5107.

Identification of conserved gene network modules in different stages of cancer may lead to uncovering mechanisms behind cancer initiation and progression. This work is based on two hypotheses. Hypothesis-l: the network modules conserved in all cancer stages are potential biomarkers related to the trajectory of cancer development or progression of cancer from initiation to stage-to-stage to metastasis. Hypothesis-2: The network modules from a stage, which are not conserved in other stages, can be considered as the stage-specific biomarkers for diagnosis.To test the hypotheses, gene expression and clinical data of Breast Invasive Carcinoma (BRCA) from The Cancer Genome Atlas (TCGA) were used for analysis. Gene expression data was divided into five groups- stage I to stage IV and normal tissue samples. First, the co-expression networks for each of the four stages and normal samples were generated. Second, the modules from each of the stage-specific networks were discovered using weighted gene co-expression network analysis (WGCNA). Third, survival analysis was performed to identify the prognostically significant modules. Fourth, module preservation analysis was performed to determine whether a module from one stage is preserved in other cancer stages as well as in normal stage. Finally, gene ontology and pathway enrichment analyses were performed for the prognostically significant and conserved modules.The present study discovered several gene-network modules for breast cancer preserved in all cancer stages and are significant in overall survival; hence, they can be considered potential biomarkers for cancers, related to the trajectory of cancer development. The modules that were found not to be conserved in different stages can be considered as stage-specific biomarkers.

BackgroundClassification studies using gene expression datasets are usually based on small numbers of samples and tens of thousands of genes. The selection of those genes that are important for distinguishing the different sample classes being compared, poses a challenging problem in high dimensional data analysis. We describe a new procedure for selecting significant genes as recursive cluster elimination (RCE) rather than recursive feature elimination (RFE). We have tested this algorithm on six datasets and compared its performance with that of two related classification procedures with RFE.ResultsWe have developed a novel method for selecting significant genes in comparative gene expression studies. This method, which we refer to as SVM-RCE, combines K-means, a clustering method, to identify correlated gene clusters, and Support Vector Machines (SVMs), a supervised machine learning classification method, to identify and score (rank) those gene clusters for the purpose of classification. K-means is used initially to group genes into clusters. Recursive cluster elimination (RCE) is then applied to iteratively remove those clusters of genes that contribute the least to the classification performance. SVM-RCE identifies the clusters of correlated genes that are most significantly differentially expressed between the sample classes. Utilization of gene clusters, rather than individual genes, enhances the supervised classification accuracy of the same data as compared to the accuracy when either SVM or Penalized Discriminant Analysis (PDA) with recursive feature elimination (SVM-RFE and PDA-RFE) are used to remove genes based on their individual discriminant weights.ConclusionSVM-RCE provides improved classification accuracy with complex microarray data sets when it is compared to the classification accuracy of the same datasets using either SVM-RFE or PDA-RFE. SVM-RCE identifies clusters of correlated genes that when considered together provide greater insight into the structure of the microarray data. Clustering genes for classification appears to result in some concomitant clustering of samples into subgroups.Our present implementation of SVM-RCE groups genes using the correlation metric. The success of the SVM-RCE method in classification suggests that gene interaction networks or other biologically relevant metrics that group genes based on functional parameters might also be useful.

Microarray experiments generate large datasets with expression values for thousands of genes but not more than a few dozens of samples. Accurate supervised classification of tissue samples in such high-dimensional problems is difficult but often crucial for successful diagnosis and treatment. A promising way to meet this challenge is by using boosting in conjunction with decision trees. We demonstrate that the generic boosting algorithm needs some modification to become an accurate classifier in the context of gene expression data. In particular, we present a feature preselection method, a more robust boosting procedure and a new approach for multi-categorical problems. This allows for slight to drastic increase in performance and yields competitive results on several publicly available datasets. Software for the modified boosting algorithms as well as for decision trees is available for free in R at http://stat.ethz.ch/~dettling/boosting.html.

Sequence databases and microarrays as tools for identifying prostate cancer biomarkers

A proposal for direct-ordering gene expression data by self-organising maps

A reliable and precise classification of tumors is essential for successful diagnosis and treatment of cancer. cDNA microarrays and high-density oligonucleotide chips are novel biotechnologies increasingly used in cancer research. By allowing the monitoring of expression levels in cells for thousands of genes simultaneously, microarray experiments may lead to a more complete understanding of the molecular variations among tumors and hence to a finer and more informative classification. The ability to successfully distinguish between tumor classes (already known or yet to be discovered) using gene expression data is an important aspect of this novel approach to cancer classification. This article compares the performance of different discrimination methods for the classification of tumors based on gene expression data. The methods include nearest-neighbor classifiers, linear discriminant analysis, and classification trees. Recent machine learning approaches, such as bagging and boosting, are also considered. The discrimination methods are applied to datasets from three recently published cancer gene expression studies.

BackgroundInferring a gene regulatory network (GRN) from high throughput biological data is often an under-determined problem and is a challenging task due to the following reasons: (1) thousands of genes are involved in one living cell; (2) complex dynamic and nonlinear relationships exist among genes; (3) a substantial amount of noise is involved in the data, and (4) the typical small sample size is very small compared to the number of genes. We hypothesize we can enhance our understanding of gene interactions in important biological processes (differentiation, cell cycle, and development, etc) and improve the inference accuracy of a GRN by (1) incorporating prior biological knowledge into the inference scheme, (2) integrating multiple biological data sources, and (3) decomposing the inference problem into smaller network modules.ResultsThis study presents a novel GRN inference method by integrating gene expression data and gene functional category information. The inference is based on module network model that consists of two parts: the module selection part and the network inference part. The former determines the optimal modules through fuzzy c-mean (FCM) clustering and by incorporating gene functional category information, while the latter uses a hybrid of particle swarm optimization and recurrent neural network (PSO-RNN) methods to infer the underlying network between modules. Our method is tested on real data from two studies: the development of rat central nervous system (CNS) and the yeast cell cycle process. The results are evaluated by comparing them to previously published results and gene ontology annotation information.ConclusionThe reverse engineering of GRNs in time course gene expression data is a major obstacle in system biology due to the limited number of time points. Our experiments demonstrate that the proposed method can address this challenge by: (1) preprocessing gene expression data (e.g. normalization and missing value imputation) to reduce the data noise; (2) clustering genes based on gene expression data and gene functional category information to identify biologically meaningful modules, thereby reducing the dimensionality of the data; (3) modeling GRNs with the PSO-RNN method between the modules to capture their nonlinear and dynamic relationships. The method is shown to lead to biologically meaningful modules and networks among the modules.