classificationModelSignalTrans {gene2pathway}R Documentation

Hierarchical Classification Model for Signaling Transduction Pathways and Pathway Components

Description

This file contains the hierarchical classification model to predict KEGG signaling pathways and pathway components for genes. The model contains only pathway components, to which a specified minimum number of genes could be mapped in the training phase (see retrain.signaltrans). Important: There exists one separate model file for each organism.

Format

List of class "model", where each model has the following entries:

W
learned decision hyperplane normal vector
C
dictionary of label vectors, which can be predicted individually or which can be used to predict combinations of them
detectors
SVM models trained to separate one specific pathway branch from the rest of the hierarchy
used_domains
InterPro domains used by the classifier to separate the specific branch from the rest of the hierarchy
alldomains
all InterPro domains used to build feature vectors
allpathways
hierarchy branches, which can be predicted
treesizes"
relative size of hierarchy below the corresponding branch
parentPaths
a list with information on all higher hierarchy branches for each pathway
elemIDs
a list of KEGG element IDs mapping to each pathway component - may be used to highlight pathway components with color.pathway.by.elements.

Author(s)

Holger Froehlich

See Also

classificationModel


[Package gene2pathway version 1.0 Index]