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

• Main Authors: Arvind Iyer, Krishan Gupta, Shreya Sharma, Kishore Hari, Yi Fang Lee, Neevan Ramalingam, Yoon Sim Yap, Jay West, Ali Asgar Bhagat, Balaram Vishnu Subramani, Burhanuddin Sabuwala, Tuan Zea Tan, Jean Paul Thiery, Mohit Kumar Jolly, Naveen Ramalingam, Debarka Sengupta
• Format: Article
• Language: English
• Published: MDPI AG 2020-04-01
• Series: Journal of Clinical Medicine
• Subjects: high-throughput sequencing; rare cell type; single-cell; RNA-seq; machine learning; CTC
• Online Access: https://www.mdpi.com/2077-0383/9/4/1206
• ISSN: 2077-0383

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.