Title: HC-fused: A versatile R-package for multi-omics hierarchical ensemble clustering
Authors: Bastian Pfeifer - Medical University of Graz (Austria) [presenting]
Michael Georg Schimek - Medical University of Graz (Austria)
Abstract: An important application of multi-omics clustering methods is the stratification of patients into sub-groups of similar molecular characteristics. In recent years many advancements in such methods have been developed, that provide a deeper understanding of cancer progression and may facilitate oncological treatment. However, due to the high diversity of cancer-related data, a single method may not perform sufficiently well in different scenarios. We offer a versatile framework for multi-omics hierarchical ensemble clustering, implemented within the R-package HC-fused. HC-fused allows for building hierarchical clustering ensembles suitable for the available data and research goals. In addition, a data fusion approach, developed by us, combines the clustering results from different ensemble methods and/or omics data sets, and at the same time allows the user to track the individual contribution of each single-omic and/or method to the data fusion process. Survival analyses for data from The Cancer Genome Atlas (TCGA) indicate that our proposed ensembles provide more robust, and thus more reliable results than state-of-the-art approaches. The mentioned methodology is implemented in the R-package HC-fused freely available from GitHub (https://github.com/pievos101/HC-fused).