Tutorial: guidelines for survival analysis with omics data

The identification of genomic, molecular and clinical markers predictive of patient survival is important for developing personalized disease prevention, diagnostic and treatment approaches. Modern omics technologies have made it possible to investigate the prognostic impact of markers at multiple molecular levels, including genomics, epigenomics (e.g. DNA methylation), transcriptomics, proteomics and metabolomics, and how these potential risk factors complement clinical characterization of patients for survival prognosis. However, the massive sizes of the omics data sets pose challenges for studying relationships between the molecular information and patients' survival outcomes. We present a general workflow for survival analysis, with emphasis on dealing with high-dimensional omics data as inputs when identifying survival-associated omics features and validating survival models. In particular, we focus on commonly used Cox-type penalized regressions and hierarchical Bayesian models for feature selection in survival analysis, but the framework and pipeline are applicable more generally. In cases where multi-omics data are available for survival modelling, an extra caution is needed to account for the underlying structure both within and between the omics data sets and features. A step-by-step R tutorial using The Cancer Genome Atlas survival and omics data for the execution and evaluation of survival models has been made available at \url{https://ocbe-uio.github.io/survomics/survomics.html}.