Summary: Precision-recall (PR) and receiver operating characteristic (ROC) curves are valuable measures of classifier performance. Here, we present the R-package PRROC, which allows for computing and visualizing both PR and ROC curves. In contrast to available R-packages, PRROC allows for computing PR and ROC curves and areas under these curves for soft-labeled data using a continuous interpolation between the points of PR curves. In addition, PRROC provides a generic plot function, for generating publication-quality graphics of PR and ROC curves. Availability: PRROC is available from CRAN and is licensed under

Data and text mining PRROC: computing and visualizing precision-recall and receiver operating characteristic curves in R

Data and text mining PRROC: computing and visualizing precision-recall and receiver operating characteristic curves in R

Background: The understanding of mechanisms and functions of microRNAs (miRNAs) is fundamental for the study of many biological processes and for the elucidation of the pathogenesis of many human diseases. Technological advances represented by high-throughput technologies, such as microarray and next-generation sequencing, have significantly aided miRNA research in the last decade. Nevertheless, the identification of true miRNA targets and the complete elucidation of the rules governing their functional targeting remain nebulous. Computational tools have been proven to be fundamental for guiding experimental validations for the discovery of new miRNAs, for the identification of their targets and for the elucidation of their regulatory mechanisms. Description: ComiRNet (Co-clustered miRNA Regulatory Networks) is a web-based database specifically designed to provide biologists and clinicians with user-friendly and effective tools for the study of miRNA-gene target interaction data and for the discovery of miRNA functions and mechanisms. Data in ComiRNet are produced by a combined computational approach based on: 1) a semi-supervised ensemble-based classifier, which learns to combine miRNA-gene target interactions (MTIs) from several prediction algorithms, and 2) the biclustering algorithm HOCCLUS2, which exploits the large set of produced predictions, with the associated probabilities, to identify overlapping and hierarchically organized biclusters that represent miRNA-gene regulatory networks

*To whom correspondence should be addressed. Motivation: Gene regulatory network (GRN) inference based on genomic data is one of the most actively pursued computational biological problems. Because different types of biological data usu-ally provide complementary information regarding the underlying GRN, a model that integrates big data of diverse types is expected to increase both the power and accuracy of GRN inference. Towards this goal, we propose a novel algorithm named iRafNet: integrative random forest for gene regulatory network inference. Results: iRafNet is a flexible, unified integrative framework that allows information from heteroge-neous data, such as protein–protein interactions, transcription factor (TF)-DNA-binding, gene knock-down, to be jointly considered for GRN inference. Using test data from the DREAM4 and DREAM5 challenges, we demonstrate that iRafNet outperforms the original random forest based network inference algorithm (GENIE3), and is highly comparable to the community learning ap-proach. We apply iRafNet to construct GRN in Saccharomyces cerevisiae and demonstrate that it improves the performance in predicting TF-target gene regulations and provides additional func-tional insights to the predicted gene regulations. Availability and implementation: The R code of iRafNet implementation and a tutorial are available

Background: The identification and characterisation of differentially methylated regions (DMRs) between phenotypes in the human genome is of prime interest in epigenetics. We present a novel method, DMRcate, that fits replicated methylation measurements from the Illumina HM450K BeadChip (or 450K array) spatially across the genome using a Gaussian kernel. DMRcate identifies and ranks the most differentially methylated regions across the genome based on tunable kernel smoothing of the differential methylation (DM) signal. The method is agnostic to both genomic annotation and local change in the direction of the DM signal, removes the bias incurred from irregularly spaced methylation sites, and assigns significance to each DMR called via comparison to a null model. Results: We show that, for both simulated and real data, the predictive performance of DMRcate is superior to those of Bumphunter and Probe Lasso, and commensurate with that of comb-p. For the real data, we validate all array-derived DMRs from the candidate methods on a suite of DMRs derived from whole-genome bisulfite sequencing called from the same DNA samples, using two separate phenotype comparisons. Conclusions: The agglomeration of genomically localised individual methylation sites into discrete DMRs is currently best served by a combination of DM-signal smoothing and subsequent threshold specification. The findings also suggest the design of the 450K array shows preference for CpG sites that are more likely to be differentially methylated, but its overall coverage does not adequately reflect the depth and complexity of methylation signatures afforded by sequencing. For the convenience of the research community we have created a user-friendly R software package called DMRcate, downloadable from Bioconductor and compatible with existing preprocessing packages, which allows others to apply the same DMR-finding method on 450K array data.

The task of gene regulatory network reconstruction from high-throughput data is receiving increasing attention in recent years. As a consequence, many inference methods for solving this task have been proposed in the literature. It has been recently observed, however, that no single inference method performs optimally across all datasets. It has also been shown that the integration of predictions from multiple inference methods is more robust and shows high performance across diverse datasets. Inspired by this research, in this paper, we propose a machine learning solution which learns to combine predictions from multiple inference methods. While this approach adds additional complexity to the inference pro-cess, we expect it would also carry substantial benefits. These would come from the auto-matic adaptation to patterns on the outputs of individual inference methods, so that it is possible to identify regulatory interactions more reliably when these patterns occur. This article demonstrates the benefits (in terms of accuracy of the reconstructed networks) of the proposed method, which exploits an iterative, semi-supervised ensemble-based algorithm. The algorithm learns to combine the interactions predicted by many different inference methods in the multi-view learning setting. The empirical evaluation of the proposed algo-rithm on a prokaryotic model organism (E. coli) and on a eukaryotic model organism (S. cer-evisiae) clearly shows improved performance over the state of the art methods. The results indicate that gene regulatory network reconstruction for the real datasets is more difficult for S. cerevisiae than for E. coli. The software, all the datasets used in the experiments and all the results are available for download at the following link: