Identifying splits with clear separation: a new class discovery method for gene expression data

We present a new class discovery method for microarray gene expression data. Based on a collection of gene expression profiles from different tissue samples, the method searches for binary class distinctions in the set of samples that show clear separation in the expression levels of specific subsets of genes. Several mutually independent class distinctions may be found, which is difficult to obtain from most commonly used clustering algorithms. Each class distinction can be biologically interpreted in terms of its supporting genes. The mathematical characterization of the favored class distinctions is based on statistical concepts. By analyzing three data sets from cancer gene expression studies, we demonstrate that our method is able to detect biologically relevant structures, for example cancer subtypes, in an unsupervised fashion.     

Bayesian model averaging: development of an improved multi-class, gene selection and classification tool for microarray data

MOTIVATION: Selecting a small number of relevant genes for accurate classification of samples is essential for the development of diagnostic tests. We present the Bayesian model averaging (BMA) method for gene selection and classification of microarray data. Typical gene selection and classification procedures ignore model uncertainty and use a single set of relevant genes (model) to predict the class. BMA accounts for the uncertainty about the best set to choose by averaging over multiple models (sets of potentially overlapping relevant genes). RESULTS: We have shown that BMA selects smaller numbers of relevant genes (compared with other methods) and achieves a high prediction accuracy on three microarray datasets. Our BMA algorithm is applicable to microarray datasets with any number of classes, and outputs posterior probabilities for the selected genes and models. Our selected models typically consist of only a few genes. The combination of high accuracy, small numbers of genes and posterior probabilities for the predictions should make BMA a powerful tool for developing diagnostics from expression data. AVAILABILITY: The source codes and datasets used are available from our Supplementary website.     

Multiclass classification of microarray data with repeated measurements: application to cancer

Prediction of the diagnostic category of a tissue sample from its gene-expression profile and selection of relevant genes for class prediction have important applications in cancer research. We have developed the uncorrelated shrunken centroid (USC) and error-weighted, uncorrelated shrunken centroid (EWUSC) algorithms that are applicable to microarray data with any number of classes. We show that removing highly correlated genes typically improves classification results using a small set of genes.     

GO-function: deriving biologically relevant functions from statistically significant functions

In high-throughput studies of diseases, terms enriched with disease-related genes based on Gene Ontology (GO) are routinely found. However, most current algorithms used to find significant GO terms cannot handle the redundancy that results from the dependencies of GO terms. Simply based on some numerical considerations, current algorithms developed for reducing this redundancy may produce results that do not account for biologically interesting cases. In this article, we present several rules used to design a tool called GO-function for extracting biologically relevant terms from statistically significant GO terms for a disease. Using one gene expression profile for colorectal cancer, we compared GO-function with four algorithms designed to treat redundancy. Then, we validated results obtained in this data set by GO-function using another data set for colorectal cancer. Our analysis showed that GO-function can identify disease-related terms that are more statistically and biologically meaningful than those found by the other four algorithms.     

On the statistical assessment of classifiers using DNA microarray data

Background

In this paper we present a method for the statistical assessment of cancer predictors which make use of gene expression profiles. The methodology is applied to a new data set of microarray gene expression data collected in Casa Sollievo della Sofferenza Hospital, Foggia – Italy. The data set is made up of normal (22) and tumor (25) specimens extracted from 25 patients affected by colon cancer. We propose to give answers to some questions which are relevant for the automatic diagnosis of cancer such as: Is the size of the available data set sufficient to build accurate classifiers? What is the statistical significance of the associated error rates? In what ways can accuracy be considered dependant on the adopted classification scheme? How many genes are correlated with the pathology and how many are sufficient for an accurate colon cancer classification? The method we propose answers these questions whilst avoiding the potential pitfalls hidden in the analysis and interpretation of microarray data.

Results

We estimate the generalization error, evaluated through the Leave-K-Out Cross Validation error, for three different classification schemes by varying the number of training examples and the number of the genes used. The statistical significance of the error rate is measured by using a permutation test. We provide a statistical analysis in terms of the frequencies of the genes involved in the classification. Using the whole set of genes, we found that the Weighted Voting Algorithm (WVA) classifier learns the distinction between normal and tumor specimens with 25 training examples, providing e = 21% (p = 0.045) as an error rate. This remains constant even when the number of examples increases. Moreover, Regularized Least Squares (RLS) and Support Vector Machines (SVM) classifiers can learn with only 15 training examples, with an error rate of e = 19% (p = 0.035) and e = 18% (p = 0.037) respectively. Moreover, the error rate decreases as the training set size increases, reaching its best performances with 35 training examples. In this case, RLS and SVM have error rates of e = 14% (p = 0.027) and e = 11% (p = 0.019). Concerning the number of genes, we found about 6000 genes (p < 0.05) correlated with the pathology, resulting from the signal-to-noise statistic. Moreover the performances of RLS and SVM classifiers do not change when 74% of genes is used. They progressively reduce up to e = 16% (p < 0.05) when only 2 genes are employed. The biological relevance of a set of genes determined by our statistical analysis and the major roles they play in colorectal tumorigenesis is discussed.

Conclusions

The method proposed provides statistically significant answers to precise questions relevant for the diagnosis and prognosis of cancer. We found that, with as few as 15 examples, it is possible to train statistically significant classifiers for colon cancer diagnosis. As for the definition of the number of genes sufficient for a reliable classification of colon cancer, our results suggest that it depends on the accuracy required.     

Gene selection for cancer classification with the help of bees

Background

Development of biologically relevant models from gene expression data notably, microarray data has become a topic of great interest in the field of bioinformatics and clinical genetics and oncology. Only a small number of gene expression data compared to the total number of genes explored possess a significant correlation with a certain phenotype. Gene selection enables researchers to obtain substantial insight into the genetic nature of the disease and the mechanisms responsible for it. Besides improvement of the performance of cancer classification, it can also cut down the time and cost of medical diagnoses.

Methods

This study presents a modified Artificial Bee Colony Algorithm (ABC) to select minimum number of genes that are deemed to be significant for cancer along with improvement of predictive accuracy. The search equation of ABC is believed to be good at exploration but poor at exploitation. To overcome this limitation we have modified the ABC algorithm by incorporating the concept of pheromones which is one of the major components of Ant Colony Optimization (ACO) algorithm and a new operation in which successive bees communicate to share their findings.

Results

The proposed algorithm is evaluated using a suite of ten publicly available datasets after the parameters are tuned scientifically with one of the datasets. Obtained results are compared to other works that used the same datasets. The performance of the proposed method is proved to be superior.

Conclusion

The method presented in this paper can provide subset of genes leading to more accurate classification results while the number of selected genes is smaller. Additionally, the proposed modified Artificial Bee Colony Algorithm could conceivably be applied to problems in other areas as well.

     

Optimization based tumor classification from microarray gene expression data

Background

An important use of data obtained from microarray measurements is the classification of tumor types with respect to genes that are either up or down regulated in specific cancer types. A number of algorithms have been proposed to obtain such classifications. These algorithms usually require parameter optimization to obtain accurate results depending on the type of data. Additionally, it is highly critical to find an optimal set of markers among those up or down regulated genes that can be clinically utilized to build assays for the diagnosis or to follow progression of specific cancer types. In this paper, we employ a mixed integer programming based classification algorithm named hyper-box enclosure method (HBE) for the classification of some cancer types with a minimal set of predictor genes. This optimization based method which is a user friendly and efficient classifier may allow the clinicians to diagnose and follow progression of certain cancer types.

Methodology/Principal Findings

We apply HBE algorithm to some well known data sets such as leukemia, prostate cancer, diffuse large B-cell lymphoma (DLBCL), small round blue cell tumors (SRBCT) to find some predictor genes that can be utilized for diagnosis and prognosis in a robust manner with a high accuracy. Our approach does not require any modification or parameter optimization for each data set. Additionally, information gain attribute evaluator, relief attribute evaluator and correlation-based feature selection methods are employed for the gene selection. The results are compared with those from other studies and biological roles of selected genes in corresponding cancer type are described.

Conclusions/Significance

The performance of our algorithm overall was better than the other algorithms reported in the literature and classifiers found in WEKA data-mining package. Since it does not require a parameter optimization and it performs consistently very high prediction rate on different type of data sets, HBE method is an effective and consistent tool for cancer type prediction with a small number of gene markers.     

Shrunken methodology to genome-wide SNPs selection and construction of SNPs networks

Background

Recent development of high-resolution single nucleotide polymorphism (SNP) arrays allows detailed assessment of genome-wide human genome variations. There is increasing recognition of the importance of SNPs for medicine and developmental biology. However, SNP data set typically has a large number of SNPs (e.g., 400 thousand SNPs in genome-wide Parkinson disease data set) and a few hundred of samples. Conventional classification methods may not be effective when applied to such genome-wide SNP data.

Results

In this paper, we use shrunken dissimilarity measure to analyze and select relevant SNPs for classification problems. Examples of HapMap data and Parkinson disease (PD) data are given to demonstrate the effectiveness of the proposed method, and illustrate it has a potential to become a useful analysis tool for SNP data sets. We use Parkinson disease data as an example, and perform a whole genome analysis. For the 367440 SNPs with less than 1% missing percentage from all 22 chromosomes, we can select 357 SNPs from this data set. For the unique genes that those SNPs are located in, a gene-gene similarity value is computed using GOSemSim and gene pairs that has a similarity value being greater than a threshold are selected to construct several groups of genes. For the SNPs that involved in these groups of genes, a statistical software PLINK is employed to compute the pair-wise SNP-SNP interactions, and SNPs with significance of P < 0.01 are chosen to identify SNPs networks based on their P values. Here SNPs networks are constructed based on Gene Ontology knowledge, and therefore each SNP network plays a role in the biological process. An analysis shows that such networks have relationships directly or indirectly to Parkinson disease.

Conclusions

Experimental results show that our approach is suitable to handle genetic variations, and provide useful knowledge in a genome-wide SNP study.

     

Sample size planning for developing classifiers using high-dimensional DNA microarray data

Many gene expression studies attempt to develop a predictor of pre-defined diagnostic or prognostic classes. If the classes are similar biologically, then the number of genes that are differentially expressed between the classes is likely to be small compared to the total number of genes measured. This motivates a two-step process for predictor development, a subset of differentially expressed genes is selected for use in the predictor and then the predictor constructed from these. Both these steps will introduce variability into the resulting classifier, so both must be incorporated in sample size estimation. We introduce a methodology for sample size determination for prediction in the context of high-dimensional data that captures variability in both steps of predictor development. The methodology is based on a parametric probability model, but permits sample size computations to be carried out in a practical manner without extensive requirements for preliminary data. We find that many prediction problems do not require a large training set of arrays for classifier development.     

Gene Features Selection for Three-Class Disease Classification via Multiple Orthogonal Partial Least Square Discriminant Analysis and S-Plot Using Microarray Data

Motivation

DNA microarray analysis is characterized by obtaining a large number of gene variables from a small number of observations. Cluster analysis is widely used to analyze DNA microarray data to make classification and diagnosis of disease. Because there are so many irrelevant and insignificant genes in a dataset, a feature selection approach must be employed in data analysis. The performance of cluster analysis of this high-throughput data depends on whether the feature selection approach chooses the most relevant genes associated with disease classes.

Results

Here we proposed a new method using multiple Orthogonal Partial Least Squares-Discriminant Analysis (mOPLS-DA) models and S-plots to select the most relevant genes to conduct three-class disease classification and prediction. We tested our method using Golub’s leukemia microarray data. For three classes with subtypes, we proposed hierarchical orthogonal partial least squares-discriminant analysis (OPLS-DA) models and S-plots to select features for two main classes and their subtypes. For three classes in parallel, we employed three OPLS-DA models and S-plots to choose marker genes for each class. The power of feature selection to classify and predict three-class disease was evaluated using cluster analysis. Further, the general performance of our method was tested using four public datasets and compared with those of four other feature selection methods. The results revealed that our method effectively selected the most relevant features for disease classification and prediction, and its performance was better than that of the other methods.     

Integrating node embeddings and biological annotations for genes to predict disease-gene associations

Background

Predicting disease causative genes (or simply, disease genes) has played critical roles in understanding the genetic basis of human diseases and further providing disease treatment guidelines. While various computational methods have been proposed for disease gene prediction, with the recent increasing availability of biological information for genes, it is highly motivated to leverage these valuable data sources and extract useful information for accurately predicting disease genes.

Results

We present an integrative framework called N2VKO to predict disease genes. Firstly, we learn the node embeddings from protein-protein interaction (PPI) network for genes by adapting the well-known representation learning method node2vec. Secondly, we combine the learned node embeddings with various biological annotations as rich feature representation for genes, and subsequently build binary classification models for disease gene prediction. Finally, as the data for disease gene prediction is usually imbalanced (i.e. the number of the causative genes for a specific disease is much less than that of its non-causative genes), we further address this serious data imbalance issue by applying oversampling techniques for imbalance data correction to improve the prediction performance. Comprehensive experiments demonstrate that our proposed N2VKO significantly outperforms four state-of-the-art methods for disease gene prediction across seven diseases.

Conclusions

In this study, we show that node embeddings learned from PPI networks work well for disease gene prediction, while integrating node embeddings with other biological annotations further improves the performance of classification models. Moreover, oversampling techniques for imbalance correction further enhances the prediction performance. In addition, the literature search of predicted disease genes also shows the effectiveness of our proposed N2VKO framework for disease gene prediction.

     

Data-Fusion in Clustering Microarray Data: Balancing Discovery and Interpretability

While clustering genes remains one of the most popular exploratory tools for expression data, it often results in a highly variable and biologically uninformative clusters. This paper explores a data fusion approach to clustering microarray data. Our method, which combined expression data and Gene Ontology (GO)-derived information, is applied on a real data set to perform genome-wide clustering. A set of novel tools is proposed to validate the clustering results and pick a fair value of infusion coefficient. These tools measure stability, biological relevance, and distance from the expression-only clustering solution. Our results indicate that a data-fusion clustering leads to more stable, biologically relevant clusters that are still representative of the experimental data.     

An integrated feature selection and classification method to select minimum number of variables on the case study of gene expression data

This paper introduces a novel generic approach for classification problems with the objective of achieving maximum classification accuracy with minimum number of features selected. The method is illustrated with several case studies of gene expression data. Our approach integrates filter and wrapper gene selection methods with an added objective of selecting a small set of non-redundant genes that are most relevant for classification with the provision of bins for genes to be swapped in the search for their biological relevance. It is capable of selecting relatively few marker genes while giving comparable or better leave-one-out cross-validation accuracy when compared with gene ranking selection approaches. Additionally, gene profiles can be extracted from the evolving connectionist system, which provides a set of rules that can be further developed into expert systems. The approach uses an integration of Pearson correlation coefficient and signal-to-noise ratio methods with an adaptive evolving classifier applied through the leave-one-out method for validation. Datasets of gene expression from four case studies are used to illustrate the method. The results show the proposed approach leads to an improved feature selection process in terms of reducing the number of variables required and an increased in classification accuracy.     

The effect of the accumulation of disease resistance genes on the long-term association of a global sample of environments for testing spring bread wheat

CIMMYT (the International Maize and Wheat Improvement Center) has routinely conducted international wheat yield trials to study the adaptation of spring bread wheat. The first of these, the International Spring Wheat Yield Nursery (ISWYN), was conducted for 31 years from 1964 to 1994 inclusive (30 cycles were conducted as no nursery was distributed in 1993 because of Karnal Bunt). Recently, pattern analysis methods have been developed and a set of computer programs written, which enable retrospective analyses of such historical databases to appraise the relationships among test environments in a way that discriminates among genotypes. Such an analysis was conducted on the 30 years of yield data from ISWYN and the classification derived from these analyses was compared with an agroecological classification of spring wheat test environments derived by CIMMYT. The incidence of foliar diseases (stem rust, leaf rust, yellow rust, Septoria spp. and Fusarium spp.) was important in the distinction between the high-rainfall low-latitude (mega-environment 2) and the high-input-irrigated low-latitude (mega-environment 1) environment types. The accumulation of resistance genes for these diseases has been an objective of the CIMMYT wheat breeding program. It was hypothesized that, as the relevant resistance genes were successfully pyramided into the germplasm, the distinction between these two mega-environment types would disappear. The results of the retrospective analyses support this hypothesis. Received: 19 May 1999 / Accepted: 17 January 2000     

Molecular basis of the differences between normal and tumor tissues of gastric cancer

To be able to describe the differences between the normal and tumor tissues of gastric cancer at a molecular level would be essential in the study of the disease. We investigated the gene expression pattern in the two types of tissues from gastric cancer by performing expression profiling of 86 tissues on 17K complementary DNA microarrays. To select for the differentially expressed genes, class prediction algorithm was employed. For predictor selection, samples were first divided into a training (n=58), and a test set (n=28). A group of 894 genes was selected by a t-test in a training set, which was used for cross-validation in the training set and class (normal or tumor) prediction in the test set. Smaller groups of 894 genes were individually tested for their ability to correctly predict the normal or tumor samples based on gene expression pattern. The expression ratios of the 5 genes chosen from microarray data can be validated by real time RT-PCR over 6 tissue samples, resulting in a high level of correlation, individually or combined. When a representative predictor set of 92 genes was examined, pathways of 'focal adhesion' (with gene components of THBS2, PDGFD, MAPK1, COL1A2, COL6A3), 'ECM-receptor interaction' pathway (THBS2, COL1A2, COL6A3, FN1) and 'TGF-beta signaling' (THBS2, MAPK1, INHBA) represent some of the main differences between normal and tumor of gastric cancer at a molecular level.     

Meta-analysis of gene expression data: a predictor-based approach

MOTIVATION: With the increasing availability of cancer microarray data sets there is a growing need for integrative computational methods that evaluate multiple independent microarray data sets investigating a common theme or disorder. Meta-analysis techniques are designed to overcome the low sample size typical to microarray experiments and yield more valid and informative results than each experiment separately. RESULTS: We propose a new meta-analysis technique that aims at finding a set of classifying genes, whose expression level may be used to answering the classification question in hand. Specifically, we apply our method to two independent lung cancer microarray data sets and identify a joint core subset of genes which putatively play an important role in tumor genesis of the lung. The robustness of the identified joint core set is demonstrated on a third unseen lung cancer data set, where it leads to successful classification using very few top-ranked genes. Identifying such a set of genes is of significant importance when searching for biologically meaningful biomarkers. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.     

The optimal discovery procedure for large-scale significance testing, with applications to comparative microarray experiments

As much of the focus of genetics and molecular biology has shifted toward the systems level, it has become increasingly important to accurately extract biologically relevant signal from thousands of related measurements. The common property among these high-dimensional biological studies is that the measured features have a rich and largely unknown underlying structure. One example of much recent interest is identifying differentially expressed genes in comparative microarray experiments. We propose a new approach aimed at optimally performing many hypothesis tests in a high-dimensional study. This approach estimates the optimal discovery procedure (ODP), which has recently been introduced and theoretically shown to optimally perform multiple significance tests. Whereas existing procedures essentially use data from only one feature at a time, the ODP approach uses the relevant information from the entire data set when testing each feature. In particular, we propose a generally applicable estimate of the ODP for identifying differentially expressed genes in microarray experiments. This microarray method consistently shows favorable performance over five highly used existing methods. For example, in testing for differential expression between two breast cancer tumor types, the ODP provides increases from 72% to 185% in the number of genes called significant at a false discovery rate of 3%. Our proposed microarray method is freely available to academic users in the open-source, point-and-click EDGE software package.