Unsupervised feature selection is a critical step for efficient and accurate analysis of single-cell RNA-seq data. Previous benchmarks used two different criteria to compare feature selection methods: (i) proportion of ground-truth marker genes included in the selected features and (ii) accuracy of cell clustering using ground-truth cell types. Here, we systematically compare the performance of 11 feature selection methods for both criteria. We first demonstrate the discordance between these criteria and suggest using the latter. We then compare the distribution of selected genes in their means between feature selection methods. We show that lowly expressed genes exhibit seriously high coefficients of variation and are mostly excluded by high-performance methods. In particular, high-deviation- and high-expression-based methods outperform the widely used in Seurat package in clustering cells and data visualization. We further show they also enable a clear separation of the same cell type from different tissues as well as accurate estimation of cell trajectories.

SUMMARY: We present an R-Shiny package, netGO, for novel network-integrated pathway enrichment analysis. The conventional Fisher's exact test (FET) considers the extent of overlap between target genes and pathway gene-sets, while recent network-based analysis tools consider only network interactions between the two. netGO implements an intuitive framework to integrate both the overlap and networks into a single score, and adaptively resamples genes based on network degrees to assess the pathway enrichment. In benchmark tests for gene expression and genome-wide association study (GWAS) data, netGO captured the relevant gene-sets better than existing tools, especially when analyzing a small number of genes. Specifically, netGO provides user-interactive visualization of the target genes, enriched gene-set and their network interactions for both netGO and FET results for further analysis. For this visualization, we also developed a standalone R-Shiny package shinyCyJS to connect R-shiny and the JavaScript version of cytoscape. AVAILABILITY AND IMPLEMENTATION: netGO R-Shiny package is freely available from github, https://github.com/unistbig/netGO. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

SUMMARY: We present an accurate and fast web server, WegoLoc for predicting subcellular localization of proteins based on sequence similarity and weighted Gene Ontology (GO) information. A term weighting method in the text categorization process is applied to GO terms for a support vector machine classifier. As a result, WegoLoc surpasses the state-of-the-art methods for previously used test datasets. WegoLoc supports three eukaryotic kingdoms (animals, fungi and plants) and provides human-specific analysis, and covers several sets of cellular locations. In addition, WegoLoc provides (i) multiple possible localizations of input protein(s) as well as their corresponding probability scores, (ii) weights of GO terms representing the contribution of each GO term in the prediction, and (iii) a BLAST E-value for the best hit with GO terms. If the similarity score does not meet a given threshold, an amino acid composition-based prediction is applied as a backup method. AVAILABILITY: WegoLoc and User's guide are freely available at the website http://www.btool.org/WegoLoc CONTACT: [email protected]; [email protected] SUPPLEMENTARY INFORMATION: Supplementary data is available at http://www.btool.org/WegoLoc.

MOTIVATION: Group-wise pattern analysis of genes, known as gene-set analysis (GSA), addresses the differential expression pattern of biologically pre-defined gene sets. GSA exhibits high statistical power and has revealed many novel biological processes associated with specific phenotypes. In most cases, however, GSA relies on the invalid assumption that the members of each gene set are sampled independently, which increases false predictions. RESULTS: We propose an algorithm, termed DECO, to remove (or alleviate) the bias caused by the correlation of the expression data in GSAs. This is accomplished through the eigenvalue-decomposition of covariance matrixes and a series of linear transformations of data. In particular, moderate de-correlation methods that truncate or re-scale eigenvalues were proposed for a more reliable analysis. Tests of simulated and real experimental data show that DECO effectively corrects the correlation structure of gene expression and improves the prediction accuracy (specificity and sensitivity) for both gene- and sample-randomizing GSA methods. AVAILABILITY: The MATLAB codes and the tested data sets are available at ftp://deco.nims.re.kr/pub or from the author.

BACKGROUND: Uncovering subtypes of disease from microarray samples has important clinical implications such as survival time and sensitivity of individual patients to specific therapies. Unsupervised clustering methods have been used to classify this type of data. However, most existing methods focus on clusters with compact shapes and do not reflect the geometric complexity of the high dimensional microarray clusters, which limits their performance. RESULTS: We present a cluster-number-based ensemble clustering algorithm, called MULTI-K, for microarray sample classification, which demonstrates remarkable accuracy. The method amalgamates multiple k-means runs by varying the number of clusters and identifies clusters that manifest the most robust co-memberships of elements. In addition to the original algorithm, we newly devised the entropy-plot to control the separation of singletons or small clusters. MULTI-K, unlike the simple k-means or other widely used methods, was able to capture clusters with complex and high-dimensional structures accurately. MULTI-K outperformed other methods including a recently developed ensemble clustering algorithm in tests with five simulated and eight real gene-expression data sets. CONCLUSION: The geometric complexity of clusters should be taken into account for accurate classification of microarray data, and ensemble clustering applied to the number of clusters tackles the problem very well. The C++ code and the data sets tested are available from the authors.

Recently developed gene set analysis methods evaluate differential expression patterns of gene groups instead of those of individual genes. This approach especially targets gene groups whose constituents show subtle but coordinated expression changes, which might not be detected by the usual individual gene analysis. The approach has been quite successful in deriving new information from expression data, and a number of methods and tools have been developed intensively in recent years. We review those methods and currently available tools, classify them according to the statistical methods employed, and discuss their pros and cons. We also discuss several interesting extensions to the methods.

Brief Bioinform 2008;9:189–97. doi:10.1093/bib/bbn001. In this article, we used the term IGA (individual-gene analysis) for cutoff-based methods and GSA (gene-set analysis) for cutoff-free methods. However, we recently found that Breitling et al. (BMC Bioinformatics 2004;5:34) already used the acronym IGA for iterative group analysis which is, in fact, one of the cutoff-free gene set analysis methods. Thus, to avoid reader's confusion, we want to use a term SGA (single-gene analysis) instead of IGA (individual-gene analysis) to represent various cutoff-based methods.

MOTIVATION: Inferring genetic networks from time-series expression data has been a great deal of interest. In most cases, however, the number of genes exceeds that of data points which, in principle, makes it impossible to recover the underlying networks. To address the dimensionality problem, we apply the subset selection method to a linear system of difference equations. Previous approaches assign the single most likely combination of regulators to each target gene, which often causes over-fitting of the small number of data. RESULTS: Here, we propose a new algorithm, named LEARNe, which merges the predictions from all the combinations of regulators that have a certain level of likelihood. LEARNe provides more accurate and robust predictions than previous methods for the structure of genetic networks under the linear system model. We tested LEARNe for reconstructing the SOS regulatory network of Escherichia coli and the cell cycle regulatory network of yeast from real experimental data, where LEARNe also exhibited better performances than previous methods. AVAILABILITY: The MATLAB codes are available upon request from the authors.

MOTIVATION: Genes are typically expressed in modular manners in biological processes. Recent studies reflect such features in analyzing gene expression patterns by directly scoring gene sets. Gene annotations have been used to define the gene sets, which have served to reveal specific biological themes from expression data. However, current annotations have limited analytical power, because they are classified by single categories providing only unary information for the gene sets. RESULTS: Here we propose a method for discovering composite biological themes from expression data. We intersected two annotated gene sets from different categories of Gene Ontology (GO). We then scored the expression changes of all the single and intersected sets. In this way, we were able to uncover, for example, a gene set with the molecular function F and the cellular component C that showed significant expression change, while the changes in individual gene sets were not significant. We provided an exemplary analysis for HIV-1 immune response. In addition, we tested the method on 20 public datasets where we found many 'filtered' composite terms the number of which reached approximately 34% (a strong criterion, 5% significance) of the number of significant unary terms on average. By using composite annotation, we can derive new and improved information about disease and biological processes from expression data. AVAILABILITY: We provide a web application (ADGO: http://array.kobic.re.kr/ADGO) for the analysis of differentially expressed gene sets with composite GO annotations. The user can analyze Affymetrix and dual channel array (spotted cDNA and spotted oligo microarray) data for four species: human, mouse, rat and yeast. CONTACT: [email protected] SUPPLEMENTARY INFORMATION: http://array.kobic.re.kr/ADGO.