A Machine-Learning Tool Concurrently Models Single Omics and Phenome Data for Functional Subtyping and Personalized Cancer Medicine

摘要

Tumours are heterogeneous that reflect variable patient prognosis and treatment responses (phenotypes). Since these variable phenotypes are outcomes of genomics, it is essential to integrate genome and phenome jointly. In this study, we report the development and application of a new machine learning tool (Phenotypic Mapping; PhenMap) to identify unsupervised clinically-relevant (functional) subtypes and biomarkers by simultaneously integrating clinical phenotypes and single omics data, mainly, transcriptome. This integrative analysis provides the opportunity to simultaneously identify robust and context-specific subtypes and associated phenotypes (that biologically explain each subtype) without statistically losing information. We demonstrate its utility using breast cancer cell lines and patient samples to identify functional subtypes associated with specific drug responses (including CD4/6 inhibitor) and prognosis. These subtypes may potentially predict clinical outcomes with further validation. This tool can be applied to other omics data such as methylomics, genomics and radiomics along with any phenotypic data.