Breast Cancer Prognostics Using Multi-Omics Data

Breast cancer affects one in eight women in America and is a leading cause of death from cancer worldwide. In the current study, four types of Omics data including copy number variation, gene expression, proteome and phosphoproteome were collected from seventy-seven breast cancer patients. Individual types of Omics data were used to separately construct predictive models to predict ten-year survival, an important clinical hallmark. The predictive models constructed with proteome data achieved decent predictivity (mean AUC = 0.725) and outperforms the models constructed with other types of Omics data. This indicates that high quality, large scale protein data is more effective for survival prediction compared to other types of omics data. Further, we experimented with ten different data fusion techniques (generic and Multi-kernel learning based) to test whether combining multi-Omics data can result in improved predictive performance. None of the data fusion techniques tested in the current study outperforms the predictive models built with the proteome data.