Toward the automated analysis of complex diseases in genome-wide association studies using genetic programming


== Abstract ==

Machine learning has been gaining traction in recent years to meet the demand for tools that can efficiently analyze 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 modeling 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 analyze 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.

Comment: 9 pages, 4 figures, submitted to GECCO 2017 conference and currently under review


== Original document ==

The different versions of the original document can be found in:

* [http://arxiv.org/abs/1702.01780 http://arxiv.org/abs/1702.01780]

* [http://dl.acm.org/ft_gateway.cfm?id=3071212&type=pdf http://dl.acm.org/ft_gateway.cfm?id=3071212&type=pdf]

* [http://dl.acm.org/ft_gateway.cfm?id=3071212&ftid=1892778&dwn=1 http://dl.acm.org/ft_gateway.cfm?id=3071212&ftid=1892778&dwn=1],
: [http://dx.doi.org/10.1145/3071178.3071212 http://dx.doi.org/10.1145/3071178.3071212] under the license http://www.acm.org/publications/policies/copyright_policy#Background

* [https://arxiv.org/abs/1702.01780 https://arxiv.org/abs/1702.01780],
: [https://dblp.uni-trier.de/db/journals/corr/corr1702.html#SohnOM17 https://dblp.uni-trier.de/db/journals/corr/corr1702.html#SohnOM17],
: [https://dl.acm.org/citation.cfm?id=3071178.3071212 https://dl.acm.org/citation.cfm?id=3071178.3071212],
: [https://ui.adsabs.harvard.edu/abs/2017arXiv170201780S/abstract https://ui.adsabs.harvard.edu/abs/2017arXiv170201780S/abstract],
: [https://dl.acm.org/citation.cfm?id=3071212 https://dl.acm.org/citation.cfm?id=3071212],
: [http://dblp.uni-trier.de/db/journals/corr/corr1702.html#SohnOM17 http://dblp.uni-trier.de/db/journals/corr/corr1702.html#SohnOM17],
: [https://academic.microsoft.com/#/detail/2586298664 https://academic.microsoft.com/#/detail/2586298664]