An integrated flow cytometry-based platform for isolation and molecular characterization of circulating tumor single cells and clusters

Abstract

Comprehensive molecular analysis of rare circulating tumor cells (CTCs) and cell clusters is often hampered by low throughput and purity, as well as cell loss. To address this, we developed a fully integrated platform for flow cytometry-based isolation of CTCs and clusters from blood that can be combined with whole transcriptome analysis or targeted RNA transcript quantification. Downstream molecular signature can be linked to cell phenotype through index sorting. This newly developed platform utilizes in-line magnetic particle-based leukocyte depletion, and acoustic cell focusing and washing to achieve >98% reduction of blood cells and non-cellular debris, along with >1.5 log-fold enrichment of spiked tumor cells. We could also detect 1 spiked-in tumor cell in 1 million WBCs in 4/7 replicates. Importantly, the use of a large 200μm nozzle and low sheath pressure (3.5 psi) minimized shear forces, thereby maintaining cell viability and integrity while allowing for simultaneous recovery of single cells and clusters from blood. As proof of principle, we isolated and transcriptionally characterized 63 single CTCs from a genetically engineered pancreatic cancer mouse model (n = 12 mice) and, using index sorting, were able to identify distinct epithelial and mesenchymal sub-populations based on linked single cell protein and gene expression.

Figure 1

Schematic of integrated platform and workflow. (a) Pre-enrichment platform is connected in-line with the BD Influx™ cell sorter. (b) Whole blood is labeled with antibodies against CTC markers as well as magnetic microparticles that bind unwanted blood cells. The sample then passes through a magnetic depletion step that removes >98% of unwanted blood cells followed by an in-line acoustic focusing and washing step, which removes debris and concentrates the sample prior to cell sorting. The sample can be interrogated based on cell markers and single cell or bulk populations of interest can be easily index-sorted for correlation of flow phenotype with molecular profile. WBC – White blood cell, RBC – Red blood cell, CTC – Circulating tumor cell, PZT – lead zirconate titanate.

Figure 2

Performance characteristics of platform. (a) YFP+ PD7591 cell line cells were spiked into normal mouse blood and processed through BD Influx™ only (no pre-enrichment; left) or together with the pre-enrichment workflow (with pre-enrichment; right). (b) Percent removal of CD45+ WBCs and non-cellular debris with pre-enrichment platform as compared to without pre-enrichment (n = 5, mean ± SD). (c) Average calculated cell recovery using linear regression analysis (n = 3–9).

Figure 3

Sample processing has minimal effects on gene expression, cell phenotype and viability. (a) Correlation matrix comparing gene expression profiles as determined by whole transcriptome RNA sequencing. PD798 cells were sorted through the pre-enrichment workflow (Pre-enriched), sorted through Influx only (FACS-only), analyzed prior to sorting (Pre-FACS), or were incubated in buffer only on the bench (Mock). Scale refers to Pearson correlation coefficient. (n = 3). 13845 genes were considered in the analysis. (b) The PD483 and PD798 cell lines were processed by FACS-only or with pre-enrichment to determine the processing effects on cell surface protein expression of EPCAM and ECAD. (MFI – mean fluorescence intensity) (c) Viability was assessed by Trypan Blue exclusion in the same two cell lines, PD483 and PD798, and was not significantly different at the end of the pre-enrichment workflow as compared to before sorting. Wilcoxon paired signed-rank test as well as a linear mixed-effects model was performed to determine statistical differences.

Figure 4

Optimized workflow preserves integrity of cell clusters. (a) Distribution of cell clusters before and after being sorted through (a) standard 100 μm nozzle and (b) 200 μm nozzle, and following pre-enrichment. Use of 100 μm nozzle results in a significant decrease in frequency of large clusters (>5 cells) and a corresponding increase in number of single cells whereas use of 200 μm nozzle maintains integrity of cell clusters. A negative binomial generalized linear model was used to determine statistical significance (n = 4) (c) Representative images of cells from (a) and (b). (d) Circulating cell clusters recovered from blood of a tumor-bearing KPCY mouse in which pancreatic tumor cells are labeled with YFP. Scale bar: 100 μm.

Figure 5

Whole transcriptome analysis of sorted single and pooled cells. (a) RNA sequencing was conducted on single cells (n = 11), 10-cell (n = 12) and 100-cell (N = 6) pools, and bulk RNA (n = 2) from PD798 cells pre-enriched and sorted from whole blood. Expression of selected hematopoietic lineage genes is extremely low or undetectable in all sorted cell populations, indicating high purity. Scale refers to log 2 TPM (transcripts per million). (b) Principal component analysis of gene expression of the 1,000 most variable genes in the different sorted cell populations or bulk RNA. (c) Correlation matrix comparing gene expression profile (13,817 genes) of single cells to the sum of all profiles (Synth 10) and the average of 10 cell pools (Ave 10). Scale refers to Pearson correlation coefficient. SC: Single cell.

Figure 6

Integration of single cell sorting with BD Precise™ assay. (a) Heat map showing unsupervised hierarchical clustering of Molecular Index (MI) counts of 88 transcripts representing 78 genes in PD798, PD483, and WBCs. For visualization purposes, genes with total counts lower than 64 MI (1 SD below mean) were filtered out. Scale bar refers to log 2 MI counts. Expression of EPCAM and ECAD protein, as detected by flow cytometry, is denoted above heat map. (b) t-SNE analysis of gene expression of PD798 (triangle), PD483 (circle) and WBCs (inverted triangle) colored by log 10 mean fluorescence intensity (MFI) of CD45 (upper left), ECAD (upper right), EPCAM (lower left), and YFP (lower right). (c) t-SNE plots colored by expression of cell cycle genes Bub1, Ccnb1, Mcm6, Rrm2, Rrm2.1 (designates alternate Rrm2 transcript), and Plk1 (starting with upper left and moving clockwise). Scale bar refers to log 2 MI counts.

Figure 7

Single cell analysis of sorted CTCs and tumor cells from KPCY mice. (a) Comparison of EPCAM and ECAD expression by flow cytometry for CTCs and matched tumor cells. Gates are based on fluorescence minus one (FMO) controls. Percent of YFP+ CTCs and tumor cells expressing EPCAM or ECAD are quantified at right. (b) Expression of EMT genes in matched CTCs and tumor cells sorted from KPCY mice. (i) Epithelial (E) cluster (ii) Mesenchymal (M) cluster (iii) Hybrid (E/M) cluster. Scale bar refers to log 2 MI counts.