Improved supervised prediction of aging-related genes via weighted dynamic network analysis

BMC Bioinformatics

Table 3 The selected best predictive model for each (sub)network with respect to the GenAge-based aging- and non-aging-related gene labels, and when using HPRD

The model is represented as “X+Y+Z”, where X represents the selected feature, Y represents the selected dimensionality reduction choice (i.e., None or PCA), and Z represents the selected classifier. For dimensionality reduction choices, “None” means the selected feature is in its full version, and “PCA” means the selected feature is in its PCA-reduced version. For the best predictive models when using BioGRID instead of HPRD, see Additional file 1: Table S3

ISSN: 1471-2105