Cancer prognosis prediction using somatic point mutation and copy number variation data: a comparison of gene-level and pathway-based models

Abstract

Background Genomic profiling of solid human tumors by projects such as The Cancer Genome Atlas (TCGA) has provided important information regarding the somatic alterations that drive cancer progression and patient survival. Although researchers have successfully leveraged TCGA data to build prognostic models, most efforts have focused on specific cancer types and a targeted set of gene-level predictors. Less is known about the prognostic ability of pathway-level variables in a pan-cancer setting. To address these limitations, we systematically evaluated and compared the prognostic ability of somatic point mutation (SPM) and copy number variation (CNV) data, gene-level and pathway-level models for a diverse set of TCGA cancer types and predictive modeling approaches. Results We evaluated gene-level and pathway-level penalized Cox proportional hazards models using SPM and CNV data for 29 different TCGA cohorts. We measured predictive accuracy as the concordance index for predicting survival outcomes. Our comprehensive analysis suggests that the use of pathway-level predictors did not offer superior predictive power relative to gene-level models for all cancer types but had the advantages of robustness and parsimony. We identified a set of cohorts for which somatic alterations could not predict prognosis, and a unique cohort LGG, for which SPM data was more predictive than CNV data and the predictive accuracy is good for all model types. We found that the pathway-level predictors provide superior interpretative value and that there is often a serious collinearity issue for the gene-level models while pathway-level models avoided this issue. Conclusion Our comprehensive analysis suggests that when using somatic alterations data for cancer prognosis prediction, pathway-level models are more interpretable, stable and parsimonious compared to gene-level models. Pathway-level models also avoid the issue of collinearity, which can be serious for gene-level somatic alterations. The prognostic power of somatic alterations is highly variable across different cancer types and we have identified a set of cohorts for which somatic alterations could not predict prognosis. In general, CNV data predicts prognosis better than SPM data with the exception of the LGG cohort.

Characterization and clinical relevance of PDGFRA pathway copy number variation gains across human cancers

“…As an important form of genetic structural variation, CNVs result from gains or losses of DNA segments larger than 1 kb in the human genome (Shao et al 2019 ). Recently, Zheng et al showed that CNV data had a higher validity in predicting cancer prognosis than SPM data (Zheng et al 2020 ). Furthermore, the relationship between CNVs and gene expression is crucial for the prevention, diagnosis, and treatment of cancer (Shao et al 2019 ).…”

Computational approaches for predicting variant impact: An overview from resources, principles to applications

“…‘Collinearity’ refers to the circumstance in which significant correlation between two or more feature variables resulting in independent regression coefficients estimation problems and leading to redundancy in the set of variables ( Bayman and Dexter, 2021 ). This situation might be mitigated via feature selection and estimator modification ( Zheng et al, 2020 ; Chan et al, 2022 ). From another perspective, “collinearity” should not be a problem because more complicated machine learning algorithms including SVM, Random Forest, and Neural Network, can handle large-scale and multi-collinear datasets in a better way ( Dong et al, 2015 ; Perez-Enciso and Zingaretti, 2019 ).…”

CNV Analysis of the Correlation between Preoperative Lymph Node Metastasis and Prognosis of Early Tongue Cancer

“…TNFRSF10C is a member of the TNF receptor superfamily, and studies have shown that TNFRSF10C CNV is related to distant metastatic disease 8 . To date, genomic analyses of solid human tumors through projects such as the Tumor Cancer Genome Atlas (TCGA) have been conducted, providing important information about somatic changes that drive cancer progression and patient survival 9 . A gene expression profile analysis found that MFAP5 and TNNC1 may serve as potential markers for predicting the prognosis of occult cervical LNM and oral tongue cancer 10 .…”