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.
White Papers

Incorporating External Control Arms into Clinical Trials

White Papers

Applications of Digital Twins in Clinical Trials for Alzheimer’s Disease

Press

Unlearn.AI named to the 2021 CB Insights AI 100 List of Most Innovative Artificial Intelligence Startups

The AI 100 is CB Insights' annual list of the 100 most promising private AI companies in the world.
How Digital Twins make it possible to design and run more efficient clinical trials with well-defined statistical properties.
Synthetic Controls and Digital Twins both increase power, but only Digital Twins are robust to known as well as unknown confounders.