Learning Clinical Outcomes from Heterogeneous Genomic Data Sources

TL;DR

This paper presents a neural network approach utilizing multi-task and adversarial learning to predict clinical outcomes from diverse genomic data, addressing data scarcity and censorship in cancer genomics.

Contribution

It introduces a novel neural network framework that combines heterogeneous genomic data sources for improved clinical outcome prediction.

Findings

Neural networks can effectively predict clinical outcomes from heterogeneous genomic data.

Multi-task and adversarial learning improve model robustness and generalization.

The method mitigates data scarcity and censorship issues in cancer genomics.

Abstract

Translating the vast data generated by genomic platforms into reliable predictions of clinical outcomes remains a critical challenge in realizing the promise of genomic medicine largely due to small number of independent samples. In this paper, we show that neural networks can be trained to predict clinical outcomes using heterogeneous genomic data sources via multi-task learning and adversarial representation learning, allowing one to combine multiple cohorts and outcomes in training. We compare our proposed method to two baselines and demonstrate that it can be used to help mitigate the data scarcity and clinical outcome censorship in cancer genomics learning problems.