Prediction of cancer prognosis with the genetic basis of transcriptional variations

Phenotypes of diseases, including prognosis, are likely to have complex etiologies and be derived from interactive mechanisms, including genetic and protein interactions. Many computational methods have been used to predict survival outcomes without explicitly identifying interactive effects, such as the genetic basis for transcriptional variations. We have therefore proposed a classification method based on the interaction between genotype and transcriptional expression features (CORE-F). This method considers the overall “genetic architecture,” referring to genetically based transcriptional alterations that influence prognosis.In comparing the performance of CORE-F with the ensemble tree, the best-performing method predicting patient survival, we found that CORE-F outperformed the ensemble tree (mean AUC, 0.85 vs. 0.72). Moreover, the trained associations in the CORE-F successfully identified the genetic mechanisms underlying survival outcomes at the interaction-network level. Details of the learning algorithm are available in the online supplementary materials located at http://www.biosoft.kaist.ac.kr/coref.

Research highlights► The classification of disease survival outcomes using genetic architecture model. ► Class labeling of survival times for predicting prognosis by individual survival time. ► Suggest genetic model for phenotype variation via training of genetic interactions. ► Higher performance comparing previous tree-based approach.