AI tool for the future precision medicine and precision health.
Due to the rapid advances in high-throughput technologies, massive amounts of biological data are currently available in public repositories for many diseases. These biological data include various omics profiles such as genomic, transcriptomic, metabolomic, and proteomic data, each of which describes different aspects of cellular mechanisms. Understanding the mechanism of action for a given disease from these vast resources and subsequently identifying reliable biomarkers that can predict the patients' clinical outcomes has become a major challenge. Through multi-graphs model can effectively integrate multi-omics data to generate cross-omics network for comprehensively underlying disease mechanisms and identifying useful biomarkers.
In: multi-omics data / Out: Cross-Omics Networks of interesting disease
Single-Cell RNA sequencing (scRNA-seq) enables researchers to study gene expression at a cellular resolution. However, high dimension and noise may obstruct analyses, so scalable denoising methods for increasingly huge scRNA-seq data are needed. Using graph technology could effectively reduce dimension and fast construct gene-gene associations atlas to predict cell types and gene regulatory networks.
In: scRNA-Seq files / Out: Cell type and Gene signatures