Deep Learning of Representations for Transcriptomics-based Phenotype Prediction

The ability to predict health outcomes from gene expression would catalyze a revolution in molecular diagnostics. This task is complicated because expression data are high dimensional whereas each experiment is usually small (e.g., ~20,000 genes may be measured for ~100 subjects). However, thousands of transcriptomics experiments with hundreds of thousands of samples are available in public repositories. Can representation learning techniques leverage these public data to improve predictive performance on other tasks? Here, we report a comprehensive analysis using different gene sets, normalization schemes, and machine learning methods on a set of 24 binary and multiclass prediction problems and 26 survival analysis tasks. Methods that combine large numbers of genes outperformed single gene methods, but neither unsupervised nor semi-supervised representation learning techniques yielded consistent improvements in out-of-sample performance across datasets. Our findings suggest that using l2-regularized regression methods applied to centered log-ratio transformed transcript abundances provide the best predictive analyses.

Enter your email address to download paper.

Click the link to begin download.
Oops! Something went wrong while submitting the form.

Embracing Innovation to Move Forward

White Papers

Example White Paper


Your Digital Twin - UnlearnAI

A fascinating approach to the problem of how to make clinical trials more efficient, and understand more about what may be possible with more and better patient data.
At Unlearn, our goal is to use the data available from historical trials, to generate new evidence to inform and advance research.