Skip to main content
Fig. 6 | BioData Mining

Fig. 6

From: Transition-transversion encoding and genetic relationship metric in ReliefF feature selection improves pathway enrichment in GWAS

Fig. 6

Pathway detection comparison of AM-AM ReliefF and GRM-AM ReliefF. Bars count the number of genes that overlap the given pathway – Axon Guidance (light blue), Neuronal System (dark blue), and G protein-coupled receptor (GPCR) (green) – from the top 500 genes from each feature selection method. The methods are AM-AM (ReliefF with AM-based nearest neighbors (Eqs. 5 and 9) and AM attribute diff (Eq. 5)), GRM-AM (ReliefF with GRM-based nearest neighbors (Eq. 10) and AM attribute diff (Eq. 5)), where AM is allele mismatch and GRM is genetic relationship metric. In addition to ReliefF methods, we compare with Lasso with principal component covariates, Random Forest, and Random Genes (random sampling of 500 genes averaged over 100 replicates). AM-AM and GRM-AM have a similar pattern to and better performance than Random Forest. GRM-AM finds the most Axon and GPCR genes, and AM-AM finds the most Neuronal genes

Back to article page

BioData Mining

ISSN: 1756-0381