- author = "Alena Orlenko and Daniel Kofink and Leo-Pekka Lyytikainen and Kjell Nikus and Pashupati Mishra and Pekka Kuukasjarvi and Pekka J Karhunen and Mika Kaehoenen and Jari O Laurikka and Terho Lehtimaki and Folkert W Asselbergs and Jason H Moore",
- title = "Model selection for metabolomics: predicting diagnosis of coronary artery disease using automated machine learning",
- journal = "Bioinformatics",
- year = "2020",
- volume = "36",
- number = "6",
- pages = "1772--1778",
- month = "15 " # mar,
- keywords = "genetic algorithms, genetic programming, TPOT, Gene Expression",
- ISSN = "1367-4803",
-
URL = "
https://doi.org/10.1093/bioinformatics/btz796",
-
URL = "
https://academic.oup.com/bioinformatics/article-pdf/36/6/1772/32915481/btz796.pdf",
-
DOI = "
doi:10.1093/bioinformatics/btz796",
-
code_url = "https://github.com/EpistasisLab/tpot",
- size = "7 pages",
-
abstract = "Selecting the optimal machine learning (ML) model for
a given dataset is often challenging. Automated ML
(AutoML) has emerged as a powerful tool for enabling
the automatic selection of ML methods and parameter
settings for the prediction of biomedical endpoints.
Here, we apply the tree-based pipeline optimization
tool (TPOT) to predict angiographic diagnoses of
coronary artery disease (CAD). With TPOT, ML models are
represented as expression trees and optimal pipelines
discovered using a stochastic search method called
genetic programing. We provide some guidelines for
TPOT-based ML pipeline selection and optimization-based
on various clinical phenotypes and high-throughput
metabolic profiles in the Angiography and Genes Study
(ANGES).
Results:
We analyzed nuclear magnetic resonance-derived lipoprotein and metabolite profiles in the ANGES cohort with a goal to identify the role of non-obstructive CAD patients in CAD diagnostics. We performed a comparative analysis of TPOT-generated ML pipelines with selected ML classifiers, optimized with a grid search approach, applied to two phenotypic CAD profiles. As a result, TPOT-generated ML pipelines that outperformed grid search optimized models across multiple performance metrics including balanced accuracy and area under the precision-recall curve. With the selected models, we demonstrated that the phenotypic profile that distinguishes non-obstructive CAD patients from no CAD patients is associated with higher precision, suggesting a discrepancy in the underlying processes between these phenotypes.
TPOT is freely available via http://epistasislab.github.io/tpot/ Supplementary data are available at Bioinformatics online.",
-
notes = "Presented at GECCO 2020
Also known as \cite{10.1093/bioinformatics/btz796}
Department of Biostatistics, Epidemiology and Informatics, Institute for Biomedical Informatics, University of Pennsylvania, Philadelphia, PA, USA",
