Interaction-Based Feature Selection Algorithm Outperforms Polygenic Risk Score in Predicting Parkinson’s Disease Status
| Autor: | Jörn Klinger, Marco F. Schmidt, Justin L. Cope, Erwin Boettinger, Hannes A. Baukmann, Stefan Konigorski, Charles N. J. Ravarani |
|---|---|
| Rok vydání: | 2021 |
| Předmět: |
epistasis
Candidate gene Computer science Mechanism (biology) Hasso-Plattner-Institut für Digital Engineering gGmbH Feature selection QH426-470 machine learning feature selection Missing heritability problem ddc:570 parkinson's disease Genetics Feature (machine learning) Molecular Medicine Observational study PPMI (parkinson’s progression markers initiative) Data pre-processing Algorithm Genetics (clinical) Predictive modelling Original Research |
| Zdroj: | Frontiers in Genetics Frontiers in Genetics, Vol 12 (2021) |
| ISSN: | 1664-8021 |
| DOI: | 10.3389/fgene.2021.744557 |
| Popis: | Polygenic risk scores (PRS) aggregating results from genome-wide association studies are the state of the art in the prediction of susceptibility to complex traits or diseases, yet their predictive performance is limited for various reasons, not least of which is their failure to incorporate the effects of gene-gene interactions. Novel machine learning algorithms that use large amounts of data promise to find gene-gene interactions in order to build models with better predictive performance than PRS. Here, we present a data preprocessing step by using data-mining of contextual information to reduce the number of features, enabling machine learning algorithms to identify gene-gene interactions. We applied our approach to the Parkinson’s Progression Markers Initiative (PPMI) dataset, an observational clinical study of 471 genotyped subjects (368 cases and 152 controls). With an AUC of 0.85 (95% CI = [0.72; 0.96]), the interaction-based prediction model outperforms the PRS (AUC of 0.58 (95% CI = [0.42; 0.81])). Furthermore, feature importance analysis of the model provided insights into the mechanism of Parkinson’s disease. For instance, the model revealed an interaction of previously described drug target candidate genesTMEM175andGAPDHP25. These results demonstrate that interaction-based machine learning models can improve genetic prediction models and might provide an answer to the missing heritability problem. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|