Machine learning nominates the inositol pathway and novel genes in Parkinson’s disease

Abstract

Abstract There are 78 loci associated with Parkinson’s disease (PD) in the most recent genome-wide association study (GWAS), yet the specific genes driving these associations are mostly unknown. Herein, we aimed to nominate the top candidate gene from each PD locus, and identify variants and pathways potentially involved in PD. We trained a machine learning model to predict PD-associated genes from GWAS loci using genomic, transcriptomic, and epigenomic data from brain tissues and dopaminergic neurons. We nominated candidate genes in each locus, identified novel pathways potentially involved in PD, such as the inositol phosphate biosynthetic pathway (INPP5F, IP6K2, ITPKB, PPIP5K2). Specific common coding variants in SPNS1 and MLX may be involved in PD, and burden tests of rare variants further support that CNIP3, LSM7, NUCKS1 and the polyol/inositol phosphate biosynthetic pathway are associated with PD. Functional studies are needed to further analyze the involvements of these genes and pathways in PD.