Machine learning and burden analyses highlight novel genes in Parkinson's Disease
Journal:
medRxiv
Published Date:
Jan 23, 2026
Abstract
Background Genome-wide association studies (GWAS) have identified numerous risk loci for Parkinson's disease, yet identifying causal genes and mechanisms remains challenging due to non-coding associations and complex linkage disequilibrium. Methods We prioritized genes within 147 GWAS loci using an XGBoost machine-learning model trained on 285 multi-omic features, including brain-specific eQTLs and single-cell expression. Prioritized candidates underwent gene- and domain-level rare variant burden analysis via optimal sequenced kernel association test (SKAT-O) across the Accelerating Medicines Partnership for Parkinson's Disease and UK Biobank cohorts (N case = 6,435, N proxy = 13,889, N control = 343,160). Findings The model prioritized 406 genes with 48 features contributing to the prioritization. Meta-analysis of rare variants at the gene and domain levels replicated established associations (GBA1, LRRK2) and identified six novel potential risk genes ANKRD27 driven by p.Arg21Cys, UBXN2A, FAM171A1, ERCC8, BNC2, and ADNP. Domain-level analysis uniquely uncovered a significant association in the zinc-finger domain of ADNP, which was masked in gene-level tests. Additionally, at cohort-level, one novel gene was nominated: LRRC45 driven by p.Met607ArgfsTer57. Interpretation Integrating machine-learning prioritization with gene- and domain-level burden testing identified novel genes potentially involved in Parkinson's disease, with further validation needed to elucidate causality and mechanisms. FundingThis study was supported by grants from the Galen and Hilary Weston Foundation, the Michael J. Fox Foundation, the Canadian Consortium on Neurodegeneration in Aging (CCNA), the Canada First Research Excellence Fund (CFREF). Lastly, the study received contributions from the G-Can (GBA1-Canada) Initiative. G-Can is supported by The Hilary and Galen Weston Foundation, Silverstein Foundation, and J. Sebastian van Berkom and Ghislaine Saucier. S.C.P. is supported by a Canadian Institutes of Health Research (CIHR) Canada Graduate Scholarship - Doctoral (CGS-D) award. Z.G.-O. holds a Fonds de recherche du Quebec - Sante (FRQS) Chercheurs-boursiers award and is a William Dawson Scholar.
