Softaware from QDMR: a quantitative method for identification of differentially methylated regions by entropy.Zhang Y, Liu H, , Xiao X, Zhu J, Liu X, Su J, Li X, Wu Q, Wang F & Cui Y
Allows users to quantify methylation difference and identify differentially methylated regions (DMRs) across multiple samples. QDMR is a quantitative approach genome-wide quantitative comparisons of DNA methylation among multiple samples based on Shannon entropy. The software can be used as an effective tool for the quantification of methylation difference and identification of DMRs across multiple samples.
Softaware from Systematic identification and annotation of human methylation marks based on bisulfite sequencing methylomes reveals distinct roles of cell type-specific hypomethylation in the regulation of cell identity genes.Liu H, Liu X, Zhang S, , Li S, Shang S, Jia S, Wei Y, Wang F, Su J, Wu Q & Zhang Y
Detects the cell type-specific methylation marks by integrating multiple methylomes from human cell lines and tissues. SMART is an entropy-based framework focused on integrating of a large number of DNA methylomes for the de novo identification of cell type-specific MethyMarks. To facilitate the specific methylation analysis, this method dynamically integrates multiple methylomes and identifies the cell type-specific methylation marks.
Allows user to download MEDLINE, a database for scientific text mining, information extraction, natural language processing, algorithm training and reference searches. MEDOC is a Python program designed to download data on an FTP and to load all extracted information into a local mySQL database. The indexed relational database permits user to build complex and rapid queries. All fields can also be searched for desired information.
Software from Feature Selection with the R Package MXM: Discovering Statistically-Equivalent Feature Subsets., &
Provides implementations of constraint-based feature selection algorithms. MXM contains a Bayesian network algorithm, named statistically equivalent signature (SES), and assists in identification of predictive feature subsets. It can handle several data analysis tasks, namely classification, regression and survival analysis. It can be applied on different types of outcome (continuous, time-to-event, categorical) and predictors (continuous, categorical, mixed).