Year: 2022
Type: article
Abstract: 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.
Source: npj Parkinson s Disease
Authors: Mary B. Makarious, Hampton L. Leonard, Dan Vitale, Hirotaka Iwaki, Lana Sargent, Anant Dadu, Ivo Violich, Elizabeth Hutchins, David Saffo, Sara Bandres-Ciga, Jonggeol Jeff Kim, Yeajin Song, Melina Maleknia, Matt Bookman, Willy Nojopranoto, Roy H. Campbell, Sayed Hadi Hashemi, Juan A. Botia, John F. Carter, David W. Craig, Kendall Van Keuren-Jensen, Huw R. Morris, John A. Hardy, Cornelis Blauwendraat, Andrew B. Singleton, Faraz Faghri, Mike A. Nalls
Institutions: National Institutes of Health, National Institute on Aging, UCL Queen Square Institute of Neurology, University College London, German Center for Neurodegenerative Diseases, Data Tecnica International (United States), Virginia Commonwealth University, University of Illinois Urbana-Champaign, University of Southern California, Translational Genomics Research Institute, Northeastern University, Queen Mary University of London, Georgia Institute of Technology, Verily Life Sciences LLC (United States), Universidad de Murcia, Hong Kong University of Science and Technology, UK Dementia Research Institute
Language: English
Subfield: Clinical Neurology
Field: Medicine
Domain: Health Sciences
Open Access status: gold
Estimated APC paid: $3,190
Funders: Foundation for the National Institutes of Health, U.S. Department of Health and Human Services, Michael J. Fox Foundation for Parkinson's Research, Pfizer, Sanofi, Celgene, Verily Life Sciences, National Institutes of Health, National Institute on Aging, National Institute of Neurological Disorders and Stroke
Awards: G1339849980, Large Scale Biomarker Discovery and Validation for Parkinsons Disease, G341098579, Johns Hopkins Medicine Biomarker Discovery in Parkinson's Disease, G4721042799, Unbiased Approaches to Novel Biomarker Discovery in Parkinson's Disease, Biomarkers for early intervention in Parkinson disease, Multimodal MRI markers of nigrostriatal pathology in Parkinson's disease, G6307761199, Mentorship Program Patient-Oriented Research on Aging, Diagnostic and prognostic biomarkers for Parkinsons disease, G775008420, G8098035348, G8694191853, G8764830727, Genome wide SNP analysis in Parkinson's disease, Biospecimen Exchange for Neurological Disorders (BioSEND)
OpenAlex ID: W4226256732