A Multi-Modal Graph-Based Semi-Supervised Pipeline for Predicting Cancer Survival

TL;DR

This paper introduces a multi-modal, graph-based semi-supervised learning pipeline that leverages unlabeled data and data fusion to improve cancer survival prediction from RNA-seq profiles, addressing high-dimensionality and limited labeled samples.

Contribution

The paper proposes a novel pipeline combining manifold learning, graph-based semi-supervised learning, and model fusion to enhance cancer survival prediction from multi-modal transcriptomic data.

Findings

Fusion of multiple modalities improves prediction accuracy.

Semi-supervised learning effectively utilizes unlabeled data.

Promising results on two cancer datasets.

Abstract

Cancer survival prediction is an active area of research that can help prevent unnecessary therapies and improve patient's quality of life. Gene expression profiling is being widely used in cancer studies to discover informative biomarkers that aid predict different clinical endpoint prediction. We use multiple modalities of data derived from RNA deep-sequencing (RNA-seq) to predict survival of cancer patients. Despite the wealth of information available in expression profiles of cancer tumors, fulfilling the aforementioned objective remains a big challenge, for the most part, due to the paucity of data samples compared to the high dimension of the expression profiles. As such, analysis of transcriptomic data modalities calls for state-of-the-art big-data analytics techniques that can maximally use all the available data to discover the relevant information hidden within a significant amount of noise. In this paper, we propose a pipeline that predicts cancer patients' survival by exploiting the structure of the input (manifold learning) and by leveraging the unlabeled samples using Laplacian support vector machines, a graph-based semi supervised learning (GSSL) paradigm. We show that under certain circumstances, no single modality per se will result in the best accuracy and by fusing different models together via a stacked generalization strategy, we may boost the accuracy synergistically. We apply our approach to two cancer datasets and present promising results. We maintain that a similar pipeline can be used for predictive tasks where labeled samples are expensive to acquire.