Self-digitization chip for single-cell genotyping of cancer-related mutations

Abstract

Cancer is a heterogeneous disease, and patient-level genetic assessments can guide therapy choice and impact prognosis. However, little is known about the impact of genetic variability within a tumor, intratumoral heterogeneity (ITH), on disease progression or outcome. Current approaches using bulk tumor specimens can suggest the presence of ITH, but only single-cell genetic methods have the resolution to describe the underlying clonal structures themselves. Current techniques tend to be labor and resource intensive and challenging to characterize with respect to sources of biological and technical variability. We have developed a platform using a microfluidic self-digitization chip to partition cells in stationary volumes for cell imaging and allele-specific PCR. Genotyping data from only confirmed single-cell volumes is obtained and subject to a variety of relevant quality control assessments such as allele dropout, false positive, and false negative rates. We demonstrate single-cell genotyping of the NPM1 type A mutation, an important prognostic indicator in acute myeloid leukemia, on single cells of the cell line OCI-AML3, describing a more complex zygosity distribution than would be predicted via bulk analysis.

Fig 1. Genetically distinct clonal population frequencies in AML with respect to FLT3-ITD and NPM1.

(a) Using the assumptions of heterozygosity and serial clonal expansions, bulk data for patients 1 and 2 from our previous study would suggest fairly simple clonal structures with either 2 or 3 clonal populations (circle area is proportional to the contribution to the total population of that clone). (b) However, when analyzing these patient samples using single-cell genotyping for these two loci, clonal distributions of NPM1 and FLT3-ITD insertions are very different than the predicted structure (W: wild type, H: heterozygous, or M: homozygous mutant for the locus, bubble area is proportional to the percentage of cells in the total population of analyzed cells with the indicated joint NPM1/FLT3-ITD genotype). Via our previous approach to targeted single cell genotyping via macro-scale fragment analysis, we demonstrated with high statistical confidence that all possible zygosity combinations occur, though at variable frequencies.

Fig 2. Single-cell analysis quality control statistic types.

Single-cell sequencing or genotyping platforms are subject to multiple types of errors that are far more challenging to address than more traditional, bulk approaches. Single-cell assays thus require significant, specialized validation with these issues in mind. The general categories into which these statistics fall include: true positive (accurate data from one cell), false positive (data is erroneously obtained from an assay volume that does not contain a cell), false negative (a cell is present, but data is not obtained), doublet+ rate (more than one cell is present in an assay volume, but data is indistinguishable from that obtained from a single cell), allele dropout (an allele is present in an assay volume yet erroneously not detected in the data), and finally locus dropout (failure of a genetic locus to be represented in the dataset from a given cell). The impact of the failure rates in particular on the interpretation of the resulting single-cell data can be significant when describing the clonal composition in an unknown human specimen.

Fig 3. Overview of the single-cell SD genotyping chip workflow.

(a) The chip is composed of PDMS bonded to a microscope slide with a bonded glass coverslip over the array and surrounding oil channel to prevent sample evaporation. (b) Cell-PCR mix suspension is pipetted directly into the inlet reservoir flows into the wells of the array by applying vacuum to the outlet port. Once the sample volume is loaded into the wells, the main channel is flushed with oil to fully digitize each 8nL volume. The arrays are imaged to identify wells containing single (or more) cells. PCR is performed in the digitized volumes by thermalcycling of the entire chip, and fluorescence is quantified at endpoint in three fluorescence channels (FAM for the amplification probe, HEX for the mutant allele-specific probe and Cy5 for the wild-type-specific probe). In wells containing a single-cell and with amplification probe fluorescence above a set threshold, as well as allele-specific probe fluorescence above their respective thresholds, we can generate QC statistics for the array and determine zygosities of single cells.

Fig 4. Method quality statistics.

(a) Based on cell and endpoint PCR imaging, wells can be categorized as true positive (TP), false positive (FP), false negative (FN), and true negative (TN). These counts allow us to calculate a false positive and false negative rate for each array to assess performance. (b) Images show two wells of the SD chip before (top) and after (bottom) PCR. A single OCI-AML3 cell was identified in the right well, and the well was PCR positive after thermalcycling. The scale bar is 100 μm. (c) For the 12 SD chip arrays used for genotyping single OCI-AML3 cells, colored bars represent the fraction of filled wells that fall into each category described in panel A. Wells with more than one cell (doublet+) are also reported. (d) False positive rates and false negative rates were calculated for each OCI-AML3 or KG1a single-cell genotyping SD chip array. The average rate between arrays is reported for arrays with KG1a cells (blue) and arrays with OCI-AML3 cells (yellow). Scale bar represents standard deviation (N = 12 arrays with OCI-AML3 cells, N = 4 arrays with KG1a cells). (e) The fraction of wells containing no cells, one cell, or more than one cell (doublet+) was quantified from images of cells in arrays of the SD chip. Using Poisson’s equation, we calculated a predicted number of wells (black circle) that would be expected to contain one cell or more than one cell using the number of wells containing zero cells. For arrays containing either KG1a cells (blue) or OCI-AML3 cells (yellow), the actual number of wells with one cell was below the predicted number while the number of multiple cell wells was higher.

Fig 5. Single-cell genotyping results.

(a) Scatterplots for each SD chip replicate containing OCI-AML3 cells are shown as 12 panels. The fluorescence intensity in the mutant probe channel is plotted vs. the wild-type channel intensity for single-cell containing wells. Thresholds in each channel (green) separate single-cell wells into mutant, heterozygous, wild-type, or false negative (FN). (b) For the same twelve SD chip replicates, bar plots show the frequency of single cells in the population that were assigned as wild-type, heterozygous, or mutant. (c) A representative map of wells in a single replicate shows the results from cell imaging for each well. Each dot represents one well of the device, which are categorized as having no cells, a single cell, or multiple cells (doublet+). (d) For the same array, a map of zygosity shows the location of wells categorized as wild-type, heterozygous, mutant, empty of aqueous solution (Empty), no amplification probe fluorescence (NonAmp), or having positive amplification probe fluorescence but negative allele-specific probe fluorescence (UNCALLED).

Fig 6. Mean actual observed zygosity of OCI-AML3 cells compared to zygosity predicted from variant allele frequency.

Colored bars represent the mean zygosity frequency measured in single cells (847 single-cell measurements total). White bars with black outline represent the predicted mean zygosity frequency we expect our method to report for a sample for which all single cells are heterozygous. Actual genotype data is for N = 12 arrays of OCI-AML3 cells. Predicted genotype data is from measurements of single plasmids with one copy of each wild-type and mutant allele. Predicted genotype data are for N = 6 arrays of these heterozygous plasmids. In each case, genotype frequencies were quantified in each array; reported means were calculated between arrays. Error bars represent standard deviations of these measurements.