HDirect-MAP: projection-free single-cell modeling of response to checkpoint immunotherapy. Issue 2 (17th January 2022)

• Record Type: Journal Article
• Authors: Lu, Yong; Xue, Gang; Zheng, Ningbo; Han, Kun; Yang, Wenzhong; Wang, Rui-Sheng; Wu, Lingyun; Miller, Lance D; Pardee, Timothy; Triozzi, Pierre L; Lo, Hui-Wen; Watabe, Kounosuke; Wong, Stephen T C; Pasche, Boris C; Zhang, Wei; Jin, Guangxu
• Is Part Of: Briefings in bioinformatics. Volume 23:Issue 2(2022)
• Publication Date: 2022-01-17
• Subjects: single-cell RNA sequencing (scRNA-seq) -- single-cell mass cytometry (CyTOF) -- Pareto optimization -- projection-free single-cell modeling -- response to immune checkpoint blockade; Genetics -- Data processing -- Periodicals; Molecular biology -- Data processing -- Periodicals; Genomes -- Data processing -- Periodicals; 572.80285
• DOI: 10.1093/bib/bbab575
• Languages: English
• ISSNs: 1467-5463

Abstract

Abstract: There is a lack of robust generalizable predictive biomarkers of response to immune checkpoint blockade in multiple types of cancer. We develop hDirect-MAP, an algorithm that maps T cells into a shared high-dimensional (HD) expression space of diverse T cell functional signatures in which cells group by the common T cell phenotypes rather than dimensional reduced features or a distorted view of these features. Using projection-free single-cell modeling, hDirect-MAP first removed a large group of cells that did not contribute to response and then clearly distinguished T cells into response-specific subpopulations that were defined by critical T cell functional markers of strong differential expression patterns. We found that these grouped cells cannot be distinguished by dimensional-reduction algorithms but are blended by diluted expression patterns. Moreover, these identified response-specific T cell subpopulations enabled a generalizable prediction by their HD metrics. Tested using five single-cell RNA-seq or mass cytometry datasets from basal cell carcinoma, squamous cell carcinoma and melanoma, hDirect-MAP demonstrated common response-specific T cell phenotypes that defined a generalizable and accurate predictive biomarker.