Background PD is a complex polygenic disorder. In recent years, several genes from the endocytic membrane‐trafficking pathway have been suggested to contribute to disease etiology. However, a systematic analysis of pathway‐specific genetic risk factors is yet to be performed. Objectives To comprehensively study the role of the endocytic membrane‐trafficking pathway in the risk of PD. Methods Linkage disequilibrium score regression was used to estimate PD heritability explained by 252 genes involved in the endocytic membrane‐trafficking pathway including genome‐wide association studies data from 18,869 cases and 22,452 controls. We used pathway‐specific single‐nucleotide polymorphisms to construct a polygenic risk score reflecting the cumulative risk of common variants. To prioritize genes for follow‐up functional studies, summary‐data based Mendelian randomization analyses were applied to explore possible functional genomic associations with expression or methylation quantitative trait loci. Results The heritability estimate attributed to endocytic membrane‐trafficking pathway was 3.58% (standard error = 1.17). Excluding previously nominated PD endocytic membrane‐trafficking pathway genes, the missing heritability was 2.21% (standard error = 0.42). Random heritability simulations were estimated to be 1.44% (standard deviation = 0.54), indicating that the unbiased total heritability explained by the endocytic membrane‐trafficking pathway was 2.14%. Polygenic risk score based on endocytic membrane‐trafficking pathway showed a 1.25 times increase of PD risk per standard deviation of genetic risk. Finally, Mendelian randomization identified 11 endocytic membrane‐trafficking pathway genes showing functional consequence associated to PD risk. Conclusions We provide compelling genetic evidence that the endocytic membrane‐trafficking pathway plays a relevant role in disease etiology. Further research on this pathway is warranted given that critical effort should be made to identify potential avenues within this biological process suitable for therapeutic interventions. © 2019 International Parkinson and Movement Disorder Society

Personalized medicine promises individualized disease prediction and treatment. The convergence of machine learning (ML) and available multimodal data is key moving forward. We build upon previous work to deliver multimodal predictions of Parkinson’s disease (PD) risk and systematically develop a model using GenoML, an automated ML package, to make improved multi-omic predictions of PD, validated in an external cohort. We investigated top features, constructed hypothesis-free disease-relevant networks, and investigated drug–gene interactions. We performed automated ML on multimodal data from the Parkinson’s progression marker initiative (PPMI). After selecting the best performing algorithm, all PPMI data was used to tune the selected model. The model was validated in the Parkinson’s Disease Biomarker Program (PDBP) dataset. Our initial model showed an area under the curve (AUC) of 89.72% for the diagnosis of PD. The tuned model was then tested for validation on external data (PDBP, AUC 85.03%). Optimizing thresholds for classification increased the diagnosis prediction accuracy and other metrics. Finally, networks were built to identify gene communities specific to PD. Combining data modalities outperforms the single biomarker paradigm. UPSIT and PRS contributed most to the predictive power of the model, but the accuracy of these are supplemented by many smaller effect transcripts and risk SNPs. Our model is best suited to identifying large groups of individuals to monitor within a health registry or biobank to prioritize for further testing. This approach allows complex predictive models to be reproducible and accessible to the community, with the package, code, and results publicly available.

Although over 90 independent risk variants have been identified for Parkinson's disease using genome-wide association studies, all studies have been performed in just one population at the time. Here we performed the first large-scale multi-ancestry meta-analysis of Parkinson's disease with 49,049 cases, 18,785 proxy cases, and 2,458,063 controls including individuals of European, East Asian, Latin American, and African ancestry. In a single joint meta-analysis, we identified 78 independent genome-wide significant loci including 12 potentially novel loci (MTF2, RP11-360P21.2, ADD1, SYBU, IRS2, USP8:RP11-562A8.5, PIGL, FASN, MYLK2, AJ006998.2, Y_RNA, PPP6R2) and finemapped 6 putative causal variants at 6 known PD loci. By combining our results with publicly available eQTL data, we identified 23 genes near these novel loci whose expression is associated with PD risk. This work lays the groundwork for future efforts aimed at identifying PD loci in non-European populations.