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

TL;DR

This paper introduces TPOT-MDR, an open source tool that uses genetic programming to automatically optimize machine learning pipelines for complex disease analysis in genomics, improving accuracy and interpretability.

Contribution

The paper presents TPOT-MDR, a novel pipeline optimization tool integrating MDR and expert-guided feature selection for bioinformatics, enhancing automation and performance.

Findings

TPOT-MDR outperforms logistic regression and XGBoost in genetic data analysis.

It produces high-accuracy, interpretable models for complex disease prediction.

Demonstrated effectiveness on simulated and real-world genetic datasets.

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.