BACKGROUND: Machine learning is a powerful approach for describing and predicting classes in microarray data. Although several comparative studies have investigated the relative performance of various machine learning methods, these often do not account for the fact that performance (e.g. error rate) is a result of a series of analysis steps of which the most important are data normalization, gene selection and machine learning. RESULTS: In this study, we used seven previously published cancer-related microarray data sets to compare the effects on classification performance of five normalization methods, three gene selection methods with 21 different numbers of selected genes and eight machine learning methods. Performance in term of error rate was rigorously estimated by repeatedly employing a double cross validation approach. Since performance varies greatly between data sets, we devised an analysis method that first compares methods within individual data sets and then visualizes the comparisons across data sets. We discovered both well performing individual methods and synergies between different methods. CONCLUSION: Support Vector Machines with a radial basis kernel, linear kernel or polynomial kernel of degree 2 all performed consistently well across data sets. We show that there is a synergistic relationship between these methods and gene selection based on the T-test and the selection of a relatively high number of genes. Also, we find that these methods benefit significantly from using normalized data, although it is hard to draw general conclusions about the relative performance of different normalization procedures.

BACKGROUND: Cluster analysis, and in particular hierarchical clustering, is widely used to extract information from gene expression data. The aim is to discover new classes, or sub-classes, of either individuals or genes. Performing a cluster analysis commonly involve decisions on how to; handle missing values, standardize the data and select genes. In addition, pre-processing, involving various types of filtration and normalization procedures, can have an effect on the ability to discover biologically relevant classes. Here we consider cluster analysis in a broad sense and perform a comprehensive evaluation that covers several aspects of cluster analyses, including normalization. RESULT: We evaluated 2780 cluster analysis methods on seven publicly available 2-channel microarray data sets with common reference designs. Each cluster analysis method differed in data normalization (5 normalizations were considered), missing value imputation (2), standardization of data (2), gene selection (19) or clustering method (11). The cluster analyses are evaluated using known classes, such as cancer types, and the adjusted Rand index. The performances of the different analyses vary between the data sets and it is difficult to give general recommendations. However, normalization, gene selection and clustering method are all variables that have a significant impact on the performance. In particular, gene selection is important and it is generally necessary to include a relatively large number of genes in order to get good performance. Selecting genes with high standard deviation or using principal component analysis are shown to be the preferred gene selection methods. Hierarchical clustering using Ward's method, k-means clustering and Mclust are the clustering methods considered in this paper that achieves the highest adjusted Rand. Normalization can have a significant positive impact on the ability to cluster individuals, and there are indications that background correction is preferable, in particular if the gene selection is successful. However, this is an area that needs to be studied further in order to draw any general conclusions. CONCLUSIONS: The choice of cluster analysis, and in particular gene selection, has a large impact on the ability to cluster individuals correctly based on expression profiles. Normalization has a positive effect, but the relative performance of different normalizations is an area that needs more research. In summary, although clustering, gene selection and normalization are considered standard methods in bioinformatics, our comprehensive analysis shows that selecting the right methods, and the right combinations of methods, is far from trivial and that much is still unexplored in what is considered to be the most basic analysis of genomic data.

MOTIVATION: We describe algorithms implemented in a new software package, RNAbor, to investigate structures in a neighborhood of an input secondary structure S of an RNA sequence s. The input structure could be the minimum free energy structure, the secondary structure obtained by analysis of the X-ray structure or by comparative sequence analysis, or an arbitrary intermediate structure. RESULTS: A secondary structure T of s is called a delta-neighbor of S if T and S differ by exactly delta base pairs. RNAbor computes the number (N(delta)), the Boltzmann partition function (Z(delta)) and the minimum free energy (MFE(delta)) and corresponding structure over the collection of all delta-neighbors of S. This computation is done simultaneously for all delta < or = m, in run time O (mn3) and memory O(mn2), where n is the sequence length. We apply RNAbor for the detection of possible RNA conformational switches, and compare RNAbor with the switch detection method paRNAss. We also provide examples of how RNAbor can at times improve the accuracy of secondary structure prediction. AVAILABILITY: http://bioinformatics.bc.edu/clotelab/RNAbor/. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

BACKGROUND: In the last few decades there has been a great deal of discussion concerning whether or not noncoding RNA sequences (ncRNAs) fold in a more well-defined manner than random sequences. In this paper, we investigate several existing measures for how well an RNA sequence folds, and compare the behaviour of these measures over a large range of Rfam ncRNA families. Such measures can be useful in, for example, identifying novel ncRNAs, and indicating the presence of alternate RNA foldings. RESULTS: Our analysis shows that ncRNAs, but not mRNAs, in general have lower minimal free energy (MFE) than random sequences with the same dinucleotide frequency. Moreover, even when the MFE is significant, many ncRNAs appear to not have a unique fold, but rather several alternative folds, at least when folded in silico. Furthermore, we find that the six investigated measures are correlated to varying degrees. CONCLUSION: Due to the correlations between the different measures we find that it is sufficient to use only two of them in RNA folding studies, one to test if the sequence in question has lower energy than a random sequence with the same dinucleotide frequency (the Z-score) and the other to see if the sequence has a unique fold (the average base-pair distance, D).

BACKGROUND: Proteochemometrics is a new methodology that allows prediction of protein function directly from real interaction measurement data without the need of 3D structure information. Several reported proteochemometric models of ligand-receptor interactions have already yielded significant insights into various forms of bio-molecular interactions. The proteochemometric models are multivariate regression models that predict binding affinity for a particular combination of features of the ligand and protein. Although proteochemometric models have already offered interesting results in various studies, no detailed statistical evaluation of their average predictive power has been performed. In particular, variable subset selection performed to date has always relied on using all available examples, a situation also encountered in microarray gene expression data analysis. RESULTS: A methodology for an unbiased evaluation of the predictive power of proteochemometric models was implemented and results from applying it to two of the largest proteochemometric data sets yet reported are presented. A double cross-validation loop procedure is used to estimate the expected performance of a given design method. The unbiased performance estimates (P2) obtained for the data sets that we consider confirm that properly designed single proteochemometric models have useful predictive power, but that a standard design based on cross validation may yield models with quite limited performance. The results also show that different commercial software packages employed for the design of proteochemometric models may yield very different and therefore misleading performance estimates. In addition, the differences in the models obtained in the double CV loop indicate that detailed chemical interpretation of a single proteochemometric model is uncertain when data sets are small. CONCLUSION: The double CV loop employed offer unbiased performance estimates about a given proteochemometric modelling procedure, making it possible to identify cases where the proteochemometric design does not result in useful predictive models. Chemical interpretations of single proteochemometric models are uncertain and should instead be based on all the models selected in the double CV loop employed here.