Gaussian process regression for survival time prediction with genome-wide gene expression

TL;DR

This paper introduces a Gaussian process accelerated failure time model for predicting cancer patient survival times using high-dimensional gene expression data, effectively handling censored data and integrating multiple -omics data types.

Contribution

It presents a novel Gaussian process-based survival prediction model that jointly imputes censored data and estimates effects without variable selection, applicable to various censored outcomes.

Findings

Outperforms existing methods in simulations and real data.

Successfully predicts survival times for kidney cancer patients.

Handles diverse censored data and integrates multiple -omics datasets.

Abstract

Predicting the survival time of a cancer patient based on his/her genome-wide gene expression remains a challenging problem. For certain types of cancer, the effects of gene expression on survival are both weak and abundant, so identifying nonzero effects with reasonable accuracy is difficult. As an alternative to methods that use variable selection, we propose a Gaussian process accelerated failure time model to predict survival time using genome-wide or pathway-wide gene expression data. Using a Monte Carlo EM algorithm, we jointly impute censored log-survival time and estimate model parameters. We demonstrate the performance of our method and its advantage over existing methods in both simulations and real data analysis. The real data that we analyze were collected from 513 patients with kidney renal clear cell carcinoma and include survival time, demographic/clinical variables, and expression of more than 20,000 genes. Our method is widely applicable as it can accommodate right, left, and interval censored outcomes; and provides a natural way to combine multiple types of high-dimensional -omics data. An R package implementing our method is available online.