Clustering of the SOM easily reveals distinct gene expression patterns: results of a reanalysis of lymphoma study

HykGene: a hybrid approach for selecting marker genes for phenotype classification using microarray gene expression data

MOTIVATION

Recent studies have shown that microarray gene expression data are useful for phenotype classification of many diseases. A major problem in this classification is that the number of features (genes) greatly exceeds the number of instances (tissue samples). It has been shown that selecting a small set of informative genes can lead to improved classification accuracy. Many approaches have been proposed for this gene selection problem. Most of the previous gene ranking methods typically select 50-200 top-ranked genes and these genes are often highly correlated. Our goal is to select a small set of non-redundant marker genes that are most relevant for the classification task.

RESULTS

To achieve this goal, we developed a novel hybrid approach that combines gene ranking and clustering analysis. In this approach, we first applied feature filtering algorithms to select a set of top-ranked genes, and then applied hierarchical clustering on these genes to generate a dendrogram. Finally, the dendrogram was analyzed by a sweep-line algorithm and marker genes are selected by collapsing dense clusters. Empirical study using three public datasets shows that our approach is capable of selecting relatively few marker genes while offering the same or better leave-one-out cross-validation accuracy compared with approaches that use top-ranked genes directly for classification.

AVAILABILITY

The HykGene software is freely available at http://www.cs.dartmouth.edu/~wyh/software.htm

CONTACT

wyh@cs.dartmouth.edu

SUPPLEMENTARY INFORMATION

Supplementary material is available from http://www.cs.dartmouth.edu/~wyh/hykgene/supplement/index.htm.

Information Visualization Techniques in Bioinformatics during the Postgenomic Era

Information visualization techniques, which take advantage of the bandwidth of human vision, are powerful tools for organizing and analyzing a large amount of data. In the postgenomic era, information visualization tools are indispensable for biomedical research. This paper aims to present an overview of current applications of information visualization techniques in bioinformatics for visualizing different types of biological data, such as from genomics, proteomics, expression profiling and structural studies. Finally, we discuss the challenges of information visualization in bioinformatics related to dealing with more complex biological information in the emerging fields of systems biology and systems medicine.

Census of orthologous genes and self-organizing maps of biologically relevant transcriptional patterns in chickens (Gallus gallus)

The launch of large-scale chicken expressed sequence tags (EST) projects has placed the chicken in the lead for the number of EST sequences in agriculturally important animals. More than 451,000 chicken ESTs derived from over 158 libraries have been deposited in the NCBI dbEST database as of December 2003. But how many genes these ESTs represent and how they are expressed in different chicken tissues/organs remain undetermined. In the present research, we developed a human gene-based strategy for census of chicken orthologous genes and identification of their expression patterns. Among 34,157 human coding genes used in the study, BLAST analysis revealed that 11,066 genes provisionally matched 248,628 chicken ESTs. Based on the average EST abundance of the orthologous genes, the current public repository of chicken ESTs could represent approximately 20,000 provisional genes. Analysis of gene expression in 14 single tissues/organs showed that approximately 15% of genes were expressed exclusively in single tissue/organ whereas the remaining approximately 85% of genes were co-expressed in two or more tissues/organs. A majority (91.15%) of genes expressed in chicken embryos were also expressed at post-hatch stages, indicating that most genes activated in chicken embryos could serve housekeeping functions. Self-organizing maps (SOM) analysis organized 8807 provisional genes in selected chicken tissues into 98 clusters with each cluster being indicative of common regulatory factors and pathways. A total of 969 provisional orthologous genes were identified as preferentially expressed genes (PEGs) in various chicken tissues/organs (LOD>3.0). No doubt, the present study on gene expression patterns will provide insight into dynamics of metabolic pathways and tissue/organ programming and reprogramming in chickens.

Tracking gene expression in primary immunodeficiencies

PURPOSE OF REVIEW

Extensive research on molecular genetics in recent decades has provided a wealth of information about the mechanisms of primary immunodeficiency diseases. Microarray technology enables the survey of the expression of thousands of genes simultaneously. This review focuses on the commonly used arrays and initial applications in the study of primary immunodeficiency diseases. The application of this technology has been found to accelerate the discovery rate of gene expression disturbances in primary immunodeficiency diseases and provide potential molecular diagnostic tools.

RECENT FINDINGS

The important role of microarray technology in functional genomic study has been demonstrated by the exponential growth in the number of scientific publications in the last few years. Microarray analysis has been used to study gene expression in several immunodeficiency diseases with known gene mutations as well as those with unknown causes. It has provided snapshots of gene expression and has presented the molecular phenotypes in the cells at defined times and under certain stimulation conditions. Studies comparing differential gene expression in patients and normal controls have allowed us to better understand the immunodeficiencies at the molecular level.

SUMMARY

Application of microarray technology in immunodeficiency study has facilitated tracking the expression of thousands of genes simultaneously. The molecular phenotypes obtained from microarray results can be used in diagnosis of diseases, supplemental to clinical phenotypes. It is a powerful survey tool that can detect disturbed gene expression in immunodeficiency diseases, which will provide clues for disease gene discovery and potential targets for drug development.

Mining OMIM for insight into complex diseases

Understanding clinical phenotypes through their corresponding genotypes is one of the principal goals of genetic research. Though achieving this goal is relatively simple with single gene syndromes, more complex diseases often consist of varied clinical phenotypes that may be the result of interactions among multiple genetic loci. Microarray technology has brought the phenotype -genotype relationship to the molecular level, using differently behaving cancers, for example, as the basis for comparing patterns of gene expression. With this feasibility study, we attempted to use similar methods of analysis at the clinical level, in order to evaluate our hypothesis that the clustering of clinical phenotypes would provide information that would be useful in elucidating their underlying genotypes. Because of its breadth of content and detailed descriptions, we used OMIM as our source material for phenotypic and genetic information. After processing the source material, we then performed self-organizing map and hierarchical clustering analysis on representative diseases by phenotypic category. Through pre-determined queries over this analysis, we made two findings of potential clinical significance, one concerning diabetes and another concerning progressive neurologic diseases. Our methods provide a formal approach to analyzing phenotypes among diverse diseases, and may help indicate fruitful areas for further research into their underlying genetic causes.

Tumor classification and marker gene prediction by feature selection and fuzzy c-means clustering using microarray data

BACKGROUND

Using DNA microarrays, we have developed two novel models for tumor classification and target gene prediction. First, gene expression profiles are summarized by optimally selected Self-Organizing Maps (SOMs), followed by tumor sample classification by Fuzzy C-means clustering. Then, the prediction of marker genes is accomplished by either manual feature selection (visualizing the weighted/mean SOM component plane) or automatic feature selection (by pair-wise Fisher's linear discriminant).

RESULTS

The proposed models were tested on four published datasets: (1) Leukemia (2) Colon cancer (3) Brain tumors and (4) NCI cancer cell lines. The models gave class prediction with markedly reduced error rates compared to other class prediction approaches, and the importance of feature selection on microarray data analysis was also emphasized.

CONCLUSIONS

Our models identify marker genes with predictive potential, often better than other available methods in the literature. The models are potentially useful for medical diagnostics and may reveal some insights into cancer classification. Additionally, we illustrated two limitations in tumor classification from microarray data related to the biology underlying the data, in terms of (1) the class size of data, and (2) the internal structure of classes. These limitations are not specific for the classification models used.

The design and analysis of microarray experiments: applications in parasitology

Microarray experiments can generate enormous amounts of data, but large datasets are usually inherently complex, and the relevant information they contain can be difficult to extract. For the practicing biologist, we provide an overview of what we believe to be the most important issues that need to be addressed when dealing with microarray data. In a microarray experiment we are simply trying to identify which genes are the most "interesting" in terms of our experimental question, and these will usually be those that are either overexpressed or underexpressed (upregulated or downregulated) under the experimental conditions. Analysis of the data to find these genes involves first preprocessing of the raw data for quality control, including filtering of the data (e.g., detection of outlying values) followed by standardization of the data (i.e., making the data uniformly comparable throughout the dataset). This is followed by the formal quantitative analysis of the data, which will involve either statistical hypothesis testing or multivariate pattern recognition. Statistical hypothesis testing is the usual approach to "class comparison," where several experimental groups are being directly compared. The best approach to this problem is to use analysis of variance, although issues related to multiple hypothesis testing and probability estimation still need to be evaluated. Pattern recognition can involve "class prediction," for which a range of supervised multivariate techniques are available, or "class discovery," for which an even broader range of unsupervised multivariate techniques have been developed. Each technique has its own limitations, which need to be kept in mind when making a choice from among them. To put these ideas in context, we provide a detailed examination of two specific examples of the analysis of microarray data, both from parasitology, covering many of the most important points raised.