Information-Theoretic Inference of Large Transcriptional Regulatory Networks

The paper presents MRNET, an original method for inferring genetic networks from microarray data. The method is based on maximum relevance/minimum redundancy (MRMR), an effective information-theoretic technique for feature selection in supervised learning. The MRMR principle consists in selecting among the least redundant variables the ones that have the highest mutual information with the target. MRNET extends this feature selection principle to networks in order to infer gene-dependence relationships from microarray data. The paper assesses MRNET by benchmarking it against RELNET, CLR, and ARACNE, three state-of-the-art information-theoretic methods for large (up to several thousands of genes) network inference. Experimental results on thirty synthetically generated microarray datasets show that MRNET is competitive with these methods.     

TESE: generating specific protein structure test set ensembles

TESE is a web server for the generation of test sets of protein sequences and structures fulfilling a number of different criteria. At least three different use cases can be envisaged: (i) benchmarking of novel methods; (ii) test sets tailored for special needs and (iii) extending available datasets. The CATH structure classification is used to control structural/sequence redundancy and a variety of structural quality parameters can be used to interactively select protein subsets with specific characteristics, e.g. all X-ray structures of alpha-helical repeat proteins with more than 120 residues and resolution <2.0 A. The output includes FASTA-formatted sequences, PDB files and a clickable HTML index file containing images of the selected proteins. Multiple subsets for cross-validation are also supported. AVAILABILITY: The TESE server is available for non-commercial use at URL: http://protein.bio.unipd.it/tese/.     

Metagenomic microbial community profiling using unique clade-specific marker genes

Metagenomic shotgun sequencing data can identify microbes populating a microbial community and their proportions, but existing taxonomic profiling methods are inefficient for increasingly large data sets. We present an approach that uses clade-specific marker genes to unambiguously assign reads to microbial clades more accurately and >50× faster than current approaches. We validated our metagenomic phylogenetic analysis tool, MetaPhlAn, on terabases of short reads and provide the largest metagenomic profiling to date of the human gut. It can be accessed at http://huttenhower.sph.harvard.edu/metaphlan/.     

Improving the prediction of protein secondary structure in three and eight classes using recurrent neural networks and profiles

Secondary structure predictions are increasingly becoming the workhorse for several methods aiming at predicting protein structure and function. Here we use ensembles of bidirectional recurrent neural network architectures, PSI-BLAST-derived profiles, and a large nonredundant training set to derive two new predictors: (a) the second version of the SSpro program for secondary structure classification into three categories and (b) the first version of the SSpro8 program for secondary structure classification into the eight classes produced by the DSSP program. We describe the results of three different test sets on which SSpro achieved a sustained performance of about 78% correct prediction. We report confusion matrices, compare PSI-BLAST to BLAST-derived profiles, and assess the corresponding performance improvements. SSpro and SSpro8 are implemented as web servers, available together with other structural feature predictors at: http://promoter.ics.uci.edu/BRNN-PRED/.     

MBGD: microbial genome database for comparative analysis

MBGD is a workbench system for comparative analysis of completely sequenced microbial genomes. The central function of MBGD is to create an orthologous gene classification table using precomputed all-against-all similarity relationships among genes in multiple genomes. In MBGD, an automated classification algorithm has been implemented so that users can create their own classification table by specifying a set of organisms and parameters. This feature is especially useful when the user's interest is focused on some taxonomically related organisms. The created classification table is stored into the database and can be explored combining with the data of individual genomes as well as similarity relationships among genomes. Using these data, users can carry out comparative analyses from various points of view, such as phylogenetic pattern analysis, gene order comparison and detailed gene structure comparison. MBGD is accessible at http://mbgd.genome.ad.jp/.     

Visualization-based cancer microarray data classification analysis

MOTIVATION: Methods for analyzing cancer microarray data often face two distinct challenges: the models they infer need to perform well when classifying new tissue samples while at the same time providing an insight into the patterns and gene interactions hidden in the data. State-of-the-art supervised data mining methods often cover well only one of these aspects, motivating the development of methods where predictive models with a solid classification performance would be easily communicated to the domain expert. RESULTS: Data visualization may provide for an excellent approach to knowledge discovery and analysis of class-labeled data. We have previously developed an approach called VizRank that can score and rank point-based visualizations according to degree of separation of data instances of different class. We here extend VizRank with techniques to uncover outliers, score features (genes) and perform classification, as well as to demonstrate that the proposed approach is well suited for cancer microarray analysis. Using VizRank and radviz visualization on a set of previously published cancer microarray data sets, we were able to find simple, interpretable data projections that include only a small subset of genes yet do clearly differentiate among different cancer types. We also report that our approach to classification through visualization achieves performance that is comparable to state-of-the-art supervised data mining techniques. AVAILABILITY: VizRank and radviz are implemented as part of the Orange data mining suite (http://www.ailab.si/orange). SUPPLEMENTARY INFORMATION: Supplementary data are available from http://www.ailab.si/supp/bi-cancer.     

Gene selection for classification of microarray data based on the Bayes error

Background  

With DNA microarray data, selecting a compact subset of discriminative genes from thousands of genes is a critical step for accurate classification of phenotypes for, e.g., disease diagnosis. Several widely used gene selection methods often select top-ranked genes according to their individual discriminative power in classifying samples into distinct categories, without considering correlations among genes. A limitation of these gene selection methods is that they may result in gene sets with some redundancy and yield an unnecessary large number of candidate genes for classification analyses. Some latest studies show that incorporating gene to gene correlations into gene selection can remove redundant genes and improve classification accuracy.     

Identifying differentially expressed subnetworks with MMG

BACKGROUND: Mixture model on graphs (MMG) is a probabilistic model that integrates network topology with (gene, protein) expression data to predict the regulation state of genes and proteins. It is remarkably robust to missing data, a feature particularly important for its use in quantitative proteomics. A new implementation in C and interfaced with R makes MMG extremely fast and easy to use and to extend. AVAILABILITY: The original implementation (Matlab) is still available from http://www.dcs.shef.ac.uk/~guido/; the new implementation is available from http://wrightlab.group.shef.ac.uk/people_noirel.htm, from CRAN, and has been submitted to BioConductor, http://www.bioconductor.org/.     

Gene set enrichment analysis for multiple continuous phenotypes

Background

Gene set analysis (GSA) methods test the association of sets of genes with phenotypes in gene expression microarray studies. While GSA methods on a single binary or categorical phenotype abounds, little attention has been paid to the case of a continuous phenotype, and there is no method to accommodate correlated multiple continuous phenotypes.

Result

We propose here an extension of the linear combination test (LCT) to its new version for multiple continuous phenotypes, incorporating correlations among gene expressions of functionally related gene sets, as well as correlations among multiple phenotypes. Further, we extend our new method to its nonlinear version, referred as nonlinear combination test (NLCT), to test potential nonlinear association of gene sets with multiple phenotypes. Simulation study and a real microarray example demonstrate the practical aspects of the proposed methods.

Conclusion

The proposed approaches are effective in controlling type I errors and powerful in testing associations between gene-sets and multiple continuous phenotypes. They are both computationally effective. Naively (univariately) analyzing a group of multiple correlated phenotypes could be dangerous. R-codes to perform LCT and NLCT for multiple continuous phenotypes are available at http://www.ualberta.ca/~yyasui/homepage.html.

Electronic supplementary material

The online version of this article (doi:10.1186/1471-2105-15-260) contains supplementary material, which is available to authorized users.     

Prophet, a web-based tool for class prediction using microarray data

Sample classification and class prediction is the aim of many gene expression studies. We present a web-based application, Prophet, which builds prediction rules and allows using them for further sample classification. Prophet automatically chooses the best classifier, along with the optimal selection of genes, using a strategy that renders unbiased cross-validated errors. Prophet is linked to different microarray data analysis modules, and includes a unique feature: the possibility of performing the functional interpretation of the molecular signature found. Availability: Prophet can be found at the URL http://prophet.bioinfo.cipf.es/ or within the GEPAS package at http://www.gepas.org/ Supplementary information: http://gepas.bioinfo.cipf.es/tutorial/prophet.html.     

PowerCore: a program applying the advanced M strategy with a heuristic search for establishing core sets

MOTIVATION: Core sets are necessary to ensure that access to useful alleles or characteristics retained in genebanks is guaranteed. We have successfully developed a computational tool named 'PowerCore' that aims to support the development of core sets by reducing the redundancy of useful alleles and thus enhancing their richness. RESULTS: The program, using a new approach completely different from any other previous methodologies, selects entries of core sets by the advanced M (maximization) strategy implemented through a modified heuristic algorithm. The developed core set has been validated to retain all characteristics for qualitative traits and all classes for quantitative ones. PowerCore effectively selected the accessions with higher diversity representing the entire coverage of variables and gave a 100% reproducible list of entries whenever repeated. AVAILABILITY: PowerCore software uses the .NET Framework Version 1.1 environment which is freely available for the MS Windows platform. The files can be downloaded from http://genebank.rda.go.kr/powercore/. The distribution of the package includes executable programs, sample data and a user manual.     

A systematic strategy for large-scale analysis of genotype phenotype correlations: identification of candidate genes involved in African trypanosomiasis

It is increasingly common to combine Microarray and Quantitative Trait Loci data to aid the search for candidate genes responsible for phenotypic variation. Workflows provide a means of systematically processing these large datasets and also represent a framework for the re-use and the explicit declaration of experimental methods. In this article, we highlight the issues facing the manual analysis of microarray and QTL data for the discovery of candidate genes underlying complex phenotypes. We show how automated approaches provide a systematic means to investigate genotype-phenotype correlations. This methodology was applied to a use case of resistance to African trypanosomiasis in the mouse. Pathways represented in the results identified Daxx as one of the candidate genes within the Tir1 QTL region. Subsequent re-sequencing in Daxx identified a deletion of an amino acid, identified in susceptible mouse strains, in the Daxx-p53 protein-binding region. This supports recent experimental evidence that apoptosis could be playing a role in the trypanosomiasis resistance phenotype. Workflows developed in this investigation, including a guide to loading and executing them with example data, are available at http://workflows.mygrid.org.uk/repository/myGrid/PaulFisher/.     

Classification using partial least squares with penalized logistic regression

MOTIVATION: One important aspect of data-mining of microarray data is to discover the molecular variation among cancers. In microarray studies, the number n of samples is relatively small compared to the number p of genes per sample (usually in thousands). It is known that standard statistical methods in classification are efficient (i.e. in the present case, yield successful classifiers) particularly when n is (far) larger than p. This naturally calls for the use of a dimension reduction procedure together with the classification one. RESULTS: In this paper, the question of classification in such a high-dimensional setting is addressed. We view the classification problem as a regression one with few observations and many predictor variables. We propose a new method combining partial least squares (PLS) and Ridge penalized logistic regression. We review the existing methods based on PLS and/or penalized likelihood techniques, outline their interest in some cases and theoretically explain their sometimes poor behavior. Our procedure is compared with these other classifiers. The predictive performance of the resulting classification rule is illustrated on three data sets: Leukemia, Colon and Prostate.     

Gene selection via the BAHSIC family of algorithms

MOTIVATION: Identifying significant genes among thousands of sequences on a microarray is a central challenge for cancer research in bioinformatics. The ultimate goal is to detect the genes that are involved in disease outbreak and progression. A multitude of methods have been proposed for this task of feature selection, yet the selected gene lists differ greatly between different methods. To accomplish biologically meaningful gene selection from microarray data, we have to understand the theoretical connections and the differences between these methods. In this article, we define a kernel-based framework for feature selection based on the Hilbert-Schmidt independence criterion and backward elimination, called BAHSIC. We show that several well-known feature selectors are instances of BAHSIC, thereby clarifying their relationship. Furthermore, by choosing a different kernel, BAHSIC allows us to easily define novel feature selection algorithms. As a further advantage, feature selection via BAHSIC works directly on multiclass problems. RESULTS: In a broad experimental evaluation, the members of the BAHSIC family reach high levels of accuracy and robustness when compared to other feature selection techniques. Experiments show that features selected with a linear kernel provide the best classification performance in general, but if strong non-linearities are present in the data then non-linear kernels can be more suitable. AVAILABILITY: Accompanying homepage is http://www.dbs.ifi.lmu.de/~borgward/BAHSIC. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.     

Prediction of eukaryotic mRNA translational properties.

MOTIVATION: It is well known that eukaryotic mRNAs are translated at different levels depending on their sequence characteristics. Evaluation of mRNA translatability is of importance in prediction of the gene expression pattern by computer methods and to improve the recognition of mRNAs within cloned nucleotide sequences. It may also be used in biotechnological experiments to optimize the expression of foreign genes in transgenic organisms. RESULTS: The sets of 5' untranslated region characteristics, significantly different between mRNAs encoding abundant and scarce polypeptides, were determined for mammals, dicot plants and monocot plants, and collected in the LEADER_RNA database. Computer tools for the prediction of mRNA translatability are presented. AVAILABILITY: Programs for mRNA translatability prediction are available at http://wwwmgs.bionet.nsc. ru/programs/acts2/mo_mRNA.htm (for monocots), http://wwwmgs.bionet. nsc.ru/programs/acts2/di_mRNA.htm (for dicots) and http://wwwmgs. bionet.nsc.ru/programs/acts2/ma_mRNA.htm (for mammals). The LEADER_RNA database may be accessed at: http://wwwmgs.bionet.nsc. ru/systems/LeaderRNA/.     

A neural network method for identification of prokaryotic and eukaryotic signal peptides and prediction of their cleavage sites

We have developed a new method for the identification of signal peptides and their cleavage sites based on neural networks trained on separate sets of prokaryotic and eukaryotic sequences. The method performs significantly better than previous prediction schemes, and can easily be applied to genome-wide data sets. Discrimination between cleaved signal peptides and uncleaved N-terminal signal-anchor sequences is also possible, though with lower precision. Predictions can be made on a publicly available WWW server: http://www.cbs.dtu.dk/services/SignalP/.     

A Laboratory Information Management System (LIMS) for a high throughput genetic platform aimed at candidate gene mutation screening

High throughput mutation screening in an automated environment generates large data sets that have to be organized and stored reliably. Complex multistep workflows require strict process management and careful data tracking. We have developed a Laboratory Information Management Systems (LIMS) tailored to high throughput candidate gene mutation scanning and resequencing that respects these requirements. Designed with a client/server architecture, our system is platform independent and based on open-source tools from the database to the web application development strategy. Flexible, expandable and secure, the LIMS, by communicating with most of the laboratory instruments and robots, tracks samples and laboratory information, capturing data at every step of our automated mutation screening workflow. An important feature of our LIMS is that it enables tracking of information through a laboratory workflow where the process at one step is contingent on results from a previous step. AVAILABILITY: Script for MySQL database table creation and source code of the whole JSP application are freely available on our website: http://www-gcs.iarc.fr/lims/. SUPPLEMENTARY INFORMATION: System server configuration, database structure and additional details on the LIMS and the mutation screening workflow are available on our website: http://www-gcs.iarc.fr/lims/