Skip to main content
Fig. 5 | BioData Mining

Fig. 5

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

Fig. 5

Pathway detection comparison of standard ReliefF (GM-GM) and ReliefF with GRM nearest neighbors (GRM-GM). 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 GM-GM (standard ReliefF with GM-based nearest neighbors (Eqs. 4 and 9) and GM attribute diff (Eq. 4)), GRM-GM (ReliefF with GRM-based nearest neighbors (Eq. 10) and standard GM attribute diff (Eq. 4)), where GM is genotype mismatch and GRM is genetic relationship metric. In addition to ReliefF methods, we compare with Lasso corrected for principal components, Random Forest, and Random Genes (random sampling of 500 genes averaged over 100 replicates). GRM-GM detects more genes than other methods with the exception of GM-GM and Random Forest finding more Axon genes

Back to article page