A survey on data integration for multi-omics sample clustering

Due to the current high availability of omics, data-driven biology has greatly expanded, and several papers have reviewed state-of-the-art technologies. Nowadays, two main types investigation are available for a multi-omics dataset: extraction relevant features meaningful biological interpretation clustering samples. In latter case, few reviews refer some outdated or no longer methods, whereas others lack description metrics compare approaches. This work provides general overview major techniques in this area, divided into four groups: graph, dimensionality reduction, statistical neural-based. Besides, eight tools been tested both on synthetic real dataset. An extensive performance comparison provided using evaluation scores: Peak Signal-to-Noise Ratio (PSNR), Davies-Bouldin(DB) index, Silhouette value harmonic mean cluster purity efficiency. The best results were obtained by either explicitly implicitly, as neural architecture.