Toward the Automated Analysis of Complex Diseases in Genome-wide Association Studies Using Genetic Programming

Created by W.Langdon from gp-bibliography.bib Revision:1.7630

@InProceedings{Sohn:2017:GECCO,

• author = "Andrew Sohn and Randal S. Olson and Jason H. Moore",
• title = "Toward the Automated Analysis of Complex Diseases in Genome-wide Association Studies Using Genetic Programming",
• booktitle = "Proceedings of the Genetic and Evolutionary Computation Conference",
• series = "GECCO '17",
• year = "2017",
• isbn13 = "978-1-4503-4920-8",
• address = "Berlin, Germany",
• pages = "489--496",
• size = "8 pages",
• URL = "http://doi.acm.org/10.1145/3071178.3071212",
• DOI = "doi:10.1145/3071178.3071212",
• URL = "https://arxiv.org/abs/1702.01780",
• acmid = "3071212",
• publisher = "ACM",
• publisher_address = "New York, NY, USA",
• keywords = "genetic algorithms, genetic programming, TPOT, automated machine learning, bioinformatics, genetics, multifactor dimensionality reduction, python",
• month = "15-19 " # jul,
• abstract = "Machine learning has been gaining traction in recent years to meet the demand for tools that can efficiently analyse and make sense of the ever-growing databases of biomedical data in health care systems around the world. However, effectively using machine learning methods requires considerable domain expertise, which can be a barrier of entry for bioinformaticians new to computational data science methods. Therefore, off-the-shelf tools that make machine learning more accessible can prove invaluable for bioinformaticians. To this end, we have developed an open source pipeline optimization tool (TPOT-MDR) that uses genetic programming to automatically design machine learning pipelines for bioinformatics studies. In TPOT-MDR, we implement Multifactor Dimensionality Reduction (MDR) as a feature construction method for modelling higher-order feature interactions, and combine it with a new expert knowledge-guided feature selector for large biomedical data sets. We demonstrate TPOT-MDR's capabilities using a combination of simulated and real world data sets from human genetics and find that TPOT-MDR significantly outperforms modern machine learning methods such as logistic regression and eXtreme Gradient Boosting (XGBoost). We further analyse the best pipeline discovered by TPOT-MDR for a real world problem and highlight TPOT-MDR's ability to produce a high-accuracy solution that is also easily interpretable.",
• notes = "Also known as \cite{Sohn:2017:TAA:3071178.3071212} GECCO-2017 A Recombination of the 26th International Conference on Genetic Algorithms (ICGA-2017) and the 22nd Annual Genetic Programming Conference (GP-2017)",

}

Genetic Programming entries for Andrew Sohn Randal S Olson Jason H Moore

Citations