Integrative Analysis and Machine Learning Based Characterization of Single Circulating Tumor Cells

We collated publicly available single-cell expression profiles of circulating tumor cells (CTCs) and showed that CTCs across cancers lie on a near-perfect continuum of epithelial to mesenchymal (EMT) transition. Integrative analysis of CTC transcriptomes also highlighted the inverse gene expression pattern between PD-L1 and MHC, which is implicated in cancer immunotherapy. We used the CTCs expression profiles in tandem with publicly available peripheral blood mononuclear cell (PBMC) transcriptomes to train a classifier that accurately recognizes CTCs of diverse phenotype. Further, we used this classifier to validate circulating breast tumor cells captured using a newly developed microfluidic system for label-free enrichment of CTCs.

Keywords: high-throughput sequencing; rare cell type; single-cell; RNA-seq; machine learning; CTC; blood

Recommended citation: Iyer A, Gupta K, Sharma S, Hari K, Lee YF, Ramalingam N, Yap YS, West J, Bhagat AA, Subramani BV, et al. Integrative Analysis and Machine Learning Based Characterization of Single Circulating Tumor Cells. Journal of Clinical Medicine. 2020; 9(4):1206. https://doi.org/10.3390/jcm9041206 https://www.mdpi.com/2077-0383/9/4/1206