HDirect-MAP: Projection-free single-cell modeling of response to checkpoint immunotherapy

Yong Lu, Gang Xue, Ningbo Zheng, Kun Han, Wenzhong Yang, Rui Sheng Wang, Lingyun Wu, Lance D. Miller, Timothy Pardee, Pierre L. Triozzi, Hui Wen Lo, Kounosuke Watabe, Stephen T.C. Wong, Boris C. Pasche, Wei Zhang, Guangxu Jin

Research output: Contribution to journalArticlepeer-review


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.

Original languageEnglish (US)
Article numberbbab575
JournalBriefings in bioinformatics
Issue number2
StatePublished - Mar 1 2022


  • Pareto optimization
  • Single-cell RNA sequencing (scRNA-seq)
  • projection-free single-cell modeling
  • response to immune checkpoint blockade
  • single-cell mass cytometry (CyTOF)

ASJC Scopus subject areas

  • Information Systems
  • Molecular Biology


Dive into the research topics of 'HDirect-MAP: Projection-free single-cell modeling of response to checkpoint immunotherapy'. Together they form a unique fingerprint.

Cite this