Geometric graph neural networks on multi-omics data to predict cancer survival outcomes Journal Article
| Authors: | Zhu, J.; Oh, J. H.; Simhal, A. K.; Elkin, R.; Norton, L.; Deasy, J. O.; Tannenbaum, A. |
| Article Title: | Geometric graph neural networks on multi-omics data to predict cancer survival outcomes |
| Abstract: | The advance of sequencing technologies has enabled a thorough molecular characterization of the genome in human cancers. To improve patient prognosis predictions and subsequent treatment strategies, it is imperative to develop advanced computational methods to analyze large-scale, high-dimensional genomic data. However, traditional machine learning methods face a challenge in handling the high-dimensional, low-sample size problem that is shown in most genomic data sets. To address this, our group has developed geometric network analysis techniques on multi-omics data in connection with prior biological knowledge derived from protein-protein interactions (PPIs) or pathways. Geometric features obtained from the genomic network, such as Ollivier-Ricci curvature and the invariant measure of the associated Markov chain, have been shown to be predictive of survival outcomes in various cancers. In this study, we propose a novel supervised deep learning method called geometric graph neural network (GGNN) that incorporates such geometric features into deep learning for enhanced predictive power and interpretability. More specifically, we utilize a state-of-the-art graph neural network with sparse connections between the hidden layers based on known biology of the PPI network and pathway information. Geometric features along with multi-omics data are then incorporated into the corresponding layers. The proposed approach utilizes a local–global principle in such a manner that highly predictive features are selected at the front layers and fed directly to the last layer for multivariable Cox proportional-hazards regression modeling. The method was applied to multi-omics data from the CoMMpass study of multiple myeloma and ten major cancers in The Cancer Genome Atlas (TCGA). In most experiments, our method showed superior predictive performance compared to other alternative methods. © 2023 Elsevier Ltd |
| Keywords: | proteins; geometry; forecasting; patient treatment; diseases; cancer genome; tcga; survival prediction; learning systems; the cancer genome atlas; markov processes; ricci curvature; deep learning; multi-omics; optimal transport; multilayer neural networks; geometric graph neural network; ollivier-ricci curvature; 'omics'; geometric graphs; graph neural networks; multi-omic |
| Journal Title: | Computers in Biology and Medicine |
| Volume: | 163 |
| ISSN: | 0010-4825 |
| Publisher: | Pergamon-Elsevier Science Ltd |
| Date Published: | 2023-09-01 |
| Start Page: | 107117 |
| Language: | English |
| DOI: | 10.1016/j.compbiomed.2023.107117 |
| PROVIDER: | scopus |
| PUBMED: | 37329617 |
| PMCID: | PMC10638676 |
| DOI/URL: | |
| Notes: | The MSK Cancer Center Support Grant (P30 CA008748) is acknowledged in the PDF -- Source: Scopus |
Altmetric
Citation Impact
BMJ Impact Analytics
Related MSK Work