Add to Favourites
To login click here
This article presents a machine learning approach, EAML, to identify genes underlying late-onset Alzheimer’s disease (LOAD). The approach included nine separate machine learning methods and used EA scores and the homo- or heterozygous status of coding variants of subjects to measure how well each gene could separate patients from controls. After trying multiple aggregation metrics, 98 genes met a significance cutoff and the top gene was APOE. Label propagation in biological networks was used to assess the 98 EAML candidate genes and compared to the random genes with equivalent connectivity, the 97 EAML candidates diffused significantly to twenty-five LOAD-associated genes from GWAS.
