SVMicrO is a 2-stage SVM based new miRNA target prediction algorithm. It assumes a 2-stage structure including a site support vector machine (SVM) followed by a UTR-SVM. SMVicrO makes prediction based on 21 optimal site features and 18 optimal UTR features, selected by training from a comprehensive collection of 113 site and 30 UTR features.
RamseyHAc (Histone acetylation) is a package of MATLAB M-files and data files is provided. The data files contain the feature tracks used for predicting TF binding sites, and the “ground truth” binding location data used to train the prediction model (both in MATLAB “.mat” file format). Also included is the file “GenomeRegions.bed” (in UCSC BED format) which describes the genome regions analyzed in this study. The M-files are the functions used to predict transcription factor binding, train the prediction model, and test the prediction model in a cross-validation framework.
CpGProD (CpG Island Promoter Detection) is an application for identifying mammalian promoter regions associated with CpG islands in large genomic sequences. Although it is strictly dedicated to this particular promoter class corresponding to ≈50% of the genes, CpGProD exhibits a higher sensitivity and specificity than other tools used for promoter prediction. Notably, CpGProD uses different parameters according to species (human, mouse) studied. Moreover, CpGProD predicts the promoter orientation on the DNA strand.
The GenemiR software application is a tool aimed at biologists and bioinformaticians who wish to find prediction and expression patterns in sets of microRNAs and genes. The program works with mouse and human target prediction and expression data.