Risk Assessment Population IDentification (RAPID) is an unsupervised, machine learning algorithm that identifies single cell phenotypes and assesses clinical risk stratification as a continuous variable.
This repository contains the code for the computational workflow as well as example data from 2018 Davis et al. (https://www.ncbi.nlm.nih.gov/pubmed/29505032)
RAPID identifies single cell phenotypes and assesses clinical risk stratification as a continuous variable. (a) Graphic of tumor processing and computational workflow. (b) Glioblastoma cells were identified from 28 patients and computationally pooled for a t-SNE analysis. Cell subsets were automatically identified by FlowSOM and were systematically assessed for association with patient overall or progression-free survival. 43 glioblastoma cell subsets were identified and were color-coded based on hazard ratio of death and p-values (HR>1, red; HR<1, blue) Cell density, FlowSOM cluster, and cluster significance are depicted on t-SNE plots.