1 - 3 of 3 results


A predictor for identifying the location of DNase I hypersensitive sites (DHSs) in human genome. iDHS-EL was formed by fusing three individual RF (Random Forest) classifiers into an ensemble predictor. The three RF operators were respectively based on the three special modes of the general pseudo nucleotide composition (PseKNC): (1) kmer, (2) reverse complement kmer, and (3) pseudo dinucleotide composition. It has been demonstrated that the new predictor remarkably outperforms the relevant state-of-the-art methods in both accuracy and stability.

DHSpred / DNase I hypersensitive sites prediction

Predicts DNase I hypersensitive sites (DHSs). DHSpred is based on a support vector machine (SVM) method. It can assist in discovery of functional DNA elements from noncoding sequences. This tool combines various informative features from multiple sources, including k-mer, dinucleotide physicochemical properties (DPCP), and trinucleotide physicochemical properties (TPCP). It is applicable to other classification problems in structural bioinformatics, such as for the plant genome DHSs prediction.

DHC-MEGE / DNase Hypersensitivity Connectivity Motif Enrichment in GeneExpression

A program for the identification of enriched motifs in gens found to be differentially expressed in a microarray or RNA-seq experiment. DHC-MEGE is able to identify distal elements such as enhancers, which are often overlooked with standard promoter motif analysis. This program uses list of up- and down-regulated gene symbols for motif analysis. It also requires a DNase Hypersensitivity (DH) connectivity maps which describes the interaction between a promoter and distal element together with the connection correlation coefficient.