Clonal evolution in breast cancer revealed by single nucleus genome sequencing

Abstract

Sequencing studies of breast tumour cohorts have identified many prevalent mutations, but provide limited insight into the genomic diversity within tumours. Here we developed a whole-genome and exome single cell sequencing approach called nuc-seq that uses G2/M nuclei to achieve 91% mean coverage breadth. We applied this method to sequence single normal and tumour nuclei from an oestrogen-receptor-positive (ER(+)) breast cancer and a triple-negative ductal carcinoma. In parallel, we performed single nuclei copy number profiling. Our data show that aneuploid rearrangements occurred early in tumour evolution and remained highly stable as the tumour masses clonally expanded. In contrast, point mutations evolved gradually, generating extensive clonal diversity. Using targeted single-molecule sequencing, many of the diverse mutations were shown to occur at low frequencies (<10%) in the tumour mass. Using mathematical modelling we found that the triple-negative tumour cells had an increased mutation rate (13.3×), whereas the ER(+) tumour cells did not. These findings have important implications for the diagnosis, therapeutic treatment and evolution of chemoresistance in breast cancer.

Extended Data Figure 1. Nuc-Seq Method

a, Nuclear suspensions were prepared and stained with DAPI for flow-sorting, showing distributions of ploidy. The G2/M distribution was gated and single nuclei were deposited into wells. b, Cells were lysed and incubated with the Φ29 polymerase to perform multiple-displacement-amplification for a limited isothermal time-frame. Sequence libraries were prepared using one of two methods: c, Tn5 tagmentation, or d, low-input TA ligation cloning (see methods section). e, exome capture was optionally performed to isolate gDNA in exonic regions f, libraries were sequenced on the Illumina HiSeq2000 system. g, somatic mutations were detected using a custom processing pipeline (methods).

Extended Data Figure 2. Evaluation of WGA Efficiency Using Chromosome-Specific Primers

Whole genome amplified DNA from each single cell was used to perform PCR quality control experiments to determine WGA efficiency. For each cell, 22 reactions were performed using primer pairs that target each autosome and the resulting 200bp PCR product were separated by gel electrophoresis (methods). a, Two single nuclei were flow-sorted from the G2/M gate and amplified to WGA followed by PCR using 22 primer pairs b, Two single nuclei were flow-sorted from the G1/0 gate and subject to WGA followed by PCR using 22 primer pairs. PCR products that failed to amplify are marked with an ‘x’ on the gel.

Extended Data Figure 3. Clustered Heatmaps of Single Cell Copy Number Profiles

Single cell segmented copy number profiles were clustered and used to build heatmaps, showing amplifications in red and deletions in blue. a, Copy number profiles of 50 single cells from the ER breast tumor. b, Copy number profiles of 50 single cells from the TNBC patient.

Extended Data Figure 4. Duplex Single-Molecule Targeted Deep-Sequencing

a, Experimental protocol for generating duplex libraries from bulk tumor DNA for custom capture and targeted ultra-deep sequencing. b, Data processing pipeline for duplex data to generate single-molecule data and detect mutation frequencies. c, Distribution of unique molecule tag duplicates for the ER breast cancer patient d, Distribution of unique molecule tag duplicates for the TNBC e, single-molecule coverage depth distribution for the ER+ tumor data f, single-molecule coverage depth distribution for the TNBC data.

Extended Data Figure 5. TNBC Multi-dimensional Scaling and Protein Prediction Plots

a, Multi-dimensional scaling plot of the nonsynonymous mutations from the single-nuclei exome sequencing data in the TNBC b, Polyphen and SIFT protein impact prediction scores for the subclonal mutations in the TNBC patient.

Extended Data Figure 6. Models of Clonal Evolution in Breast Cancer

a, Clonal evolution in the ER breast tumor inferred from single cell exome and copy number data. b, Clonal evolution in the TNBC inferred from single cell exome and copy number data.

Figure 1. Method Performance in a Monoclonal Cell Line

a, Coverage breadth for single cells (SK1, SK2) sequenced by Nuc-Seq, a single cell SNS library and a SK-BR-3 population sample. b, Heatmap of 50 single cell SK-BR-3 copy number profiles. c, Circos plot of variants detected by sequencing populations of SK-BR-3 cells d, Lorenz curve of coverage uniformity for the single SK-BR-3 cells sequenced by Nuc-Seq, a cell sequenced by SNS, a population of SK-BR-3 cells, and a cell sequenced by MALBAC. e, Coverage depth for the SK-BR-3 population sample and the SK1 and SK2 single cells.

Figure 2. Single Cell and Population Sequencing of an ER Tumor

a, Frozen ER tumor specimen. b, Flow-sorting histogram of ploidy distributions. c, Circos plot of mutations and CNAs detected in the population of aneuploid tumor cells. Cancer genes are on the outer ring d, Neighbor-joining tree of integer copy number profiles from single diploid and aneuploid cells, rooted by the diploid node. e, Circos plots of whole-genome single cell sequencing data showing mutations detected in two or more cells. f, Heatmap of coding mutations detected by single-nuclei exome sequencing. Mutations detected by whole genome sequencing (pop) and exome sequencing (ex) are also displayed.

Figure 3. Single Cell and Population Sequencing of a TNBC

a, Frozen TNBC specimen. b, Circos plot of mutations and CNAs detected by population sequencing of the TNBC, with cancer genes on the outer ring. c, Flow-sorting histogram of ploidy distributions, showing three major subpopulations: diploid (D), hypodiploid (H) and aneuploid (A). d, Neighbor-joining tree of 50 single cell integer copy number profiles, rooted by the diploid node. e, Clustered heatmap of the nonsynonymous point mutations detected by single nuclei exome sequencing and population sequencing (P). Mutations detected in one cell are excluded.

Figure 4. Duplex Mutation Frequencies and Mutation Rates

a, ER duplex mutation frequencies from targeted deep-sequencing of the bulk tumor tissue b, TNBC duplex mutation frequencies from deep-sequencing of the bulk tumor tissue. c–e, Mathematical modeling of mutation rates compared to experimental data. c, ER single-nuclei exome and modeling data at 0.6 mutation rate d, ER whole-genome single nuclei and modeling data at 0.9 mutation rate e, TNBC single nuclei exome and modeling data at mutation rate of 8. f, mutation frequencies shared by 2 or more cells in the ER tumor g, mutation frequencies shared by 2 or more cells in the TNBC f, CNAs shared by two or more cells in the ER tumor h, CNAs shared by two or more cells in the TNBC.