A Framework for Implementing Machine Learning on Omics Data
This work addresses the problem of making -omics data more accessible for machine learning applications in clinical settings, but it is incremental as it builds on existing techniques for data integration.
The authors tackled the challenge of applying machine learning to -omics data by developing a framework for combining datasets and handling high dimensionality, demonstrating it on 3,533 breast cancers to predict patient survival with higher accuracy and lower variance than existing methods.
The potential benefits of applying machine learning methods to -omics data are becoming increasingly apparent, especially in clinical settings. However, the unique characteristics of these data are not always well suited to machine learning techniques. These data are often generated across different technologies in different labs, and frequently with high dimensionality. In this paper we present a framework for combining -omics data sets, and for handling high dimensional data, making -omics research more accessible to machine learning applications. We demonstrate the success of this framework through integration and analysis of multi-analyte data for a set of 3,533 breast cancers. We then use this data-set to predict breast cancer patient survival for individuals at risk of an impending event, with higher accuracy and lower variance than methods trained on individual data-sets. We hope that our pipelines for data-set generation and transformation will open up -omics data to machine learning researchers. We have made these freely available for noncommercial use at www.ccg.ai.