This package aims at creating a predictive model of regulatory sequences used to score unknown sequences based on the content of DNA motifs, next-generation sequencing (NGS) peaks and signals and other numerical scores of the sequences using supervised classification. The package contains a workflow based on the support vector machine (SVM) algorithm that maps features to sequences, optimize SVM parameters and feature number and creates a model that can be stored and used to score the regulatory potential of unknown sequences.
|Author||Elodie Darbo, Denis Seyres, Aitor Gonzalez|
|Bioconductor views||ChIPSeq Classification MotifAnnotation Sequencing Software SupportVectorMachine|
|Date of publication||None|
|Maintainer||Aitor Gonzalez <email@example.com>|
|License||MIT | file LICENSE|
createModel: Create the model with the optimal features
crm.features: This is data to be included in my package
evaluateModelPerformance: Evaluate model performances
feature.ranking: This is data to be included in my package
LedPred: Creates an SVM model given a feature matrix
mapFeaturesToCRMs: R interface to bed_to_matrix REST in server
mcTune: Tuning the SVM parameters
rankFeatures: Ranking the features according to their importance
scoreData: Predicting new regulatory regions
tuneFeatureNb: Selecting the optimal number of features
Add the following code to your website.
For more information on customizing the embed code, read Embedding Snippets.