Amplification of whole tumor genomes and gene-by-gene mapping of genomic aberrations from limited sources of fresh-frozen and paraffin-embedded DNA

Abstract

Sufficient quantity of genomic DNA can be a bottleneck in genome-wide analysis of clinical tissue samples. DNA polymerase Phi29 can be used for the random-primed amplification of whole genomes, although the amplification may introduce bias in gene dosage. We have performed a detailed investigation of this technique in archival fresh-frozen and formalin-fixed/paraffin-embedded tumor DNA by using cDNA microarray-based comparative genomic hybridization. Phi29 amplified DNA from matched pairs of fresh-frozen and formalin-fixed/paraffin-embedded tumor samples with similar efficiency. The distortion in gene dosage representation in the amplified DNA was nonrandom and reproducibly involved distinct genomic loci. Regional amplification efficiency was significantly linked to regional GC content of the template genome. The biased gene representation in amplified tumor DNA could be effectively normalized by using amplified reference DNA. Our data suggest that genome-wide gene dosage alterations in clinical tumor samples can be reliably assessed from a few hundred tumor cells. Therefore, this amplification method should lend itself to high-throughput genetic analyses of limited sources of tumor, such as fine-needle biopsies, laser-microdissected tissue, and small paraffin-embedded specimens.

Figure 1

Phi29-based amplification of fresh-frozen and FFPE tumor DNA. a: Graphical depiction of the relationship between genomic template and amplification product. The amplification of as low as ∼250 pg of template DNA both from matching fresh-frozen (f) and FFPE (p) glioblastoma (GBM) generated μg quantities of amplification product, whereas negligible amounts (<5%) of product were generated by Phi29 without added DNA template. Sets of three independent amplifications were performed for each sample with overnight 16-hour incubation at 30°C to evaluate the consistency in the amount of generated DNA. In each of the tumor samples there was high concordance with regard to the yield of amplified DNA between independent experiments. Comparable yields of amplification product were obtained with corresponding amounts of starting genomic template from fresh-frozen and FFPE tumor. Higher amounts of template DNA resulted in negligible increases in amplified DNA output, suggesting either limited primer availability or decreasing polymerase activity during the course of the amplification reaction. b: Graph displaying the amplification level corresponding to the data of a. A steady decrease in fold-amplification, as measured by the fold-change of amplified to template DNA, was noted as the amount of starting genomic template was increased both in the fresh-frozen and FFPE tumor. c: Analysis by gel electrophoresis of DNA from a matched pair of fresh-frozen and FFPE tumors with and without amplification. Fresh-frozen and FFPE DNA demonstrated a comparable average molecular weight as did nonamplified tumor DNA and the amplification product (>12 kb).

Figure 2

Array-CGH-based genome-wide assessment of gene dosage representation in Phi29-amplified DNA. a: Graph depicting the signal intensity ratios of a nonamplified male genomic versus nonamplified female genomic DNA array-CGH experiment. Signal intensity ratios were generated by hybridizing equal amounts of DpnII-digested, purified, and fluorescent dye-labeled nonamplified template and amplification product to a 43,000-element microarray. Each dot signified the raw intensity ratio for a single clone on the microarray, which in turn indicated how this clone was represented in the amplified DNA relative to the nonamplified DNA. Ratios were plotted against the order of the genes in the human genome, starting from chromosome 1 to chromosome Y. b: Array-CGH result of a corresponding nonamplified versus amplified (a) fresh-frozen glioblastoma (GBM) DNA, the latter having been amplified 3750-fold. The considerably more profound scatter of the ratios from the ideal 1.0 value, as compared to a, indicated significant misrepresentations of many clones in the amplified DNA. Red and blue lines indicate genomic regions of higher-than-average underrepresentation and overrepresentation, respectively, as evidenced by clusters of clones aligned as vertical upward and downward peaks at the same chromosome map coordinates. c: Signal intensity ratios in a nonamplified versus amplified DNA hybridization experiments of the same GBM as in b, in which the amplification product had been amplified 250-fold. Although the scatter of the ratios was less than in the experiment plotted in b, compared to a, considerable clonal misrepresentation was apparent with distinct genomic regions demonstrating more distortion in representation than others. d to f: Histogram plots of log₂ ratio distributions of data points corresponding to the experiments shown in a to c. g: CaryoScope plots comparing clonal representations for chromosomes 3, 4, and 11 of the experiments shown in b and c. Red and green bars indicate that a clone is overrepresented and underrepresented in the amplified DNA, respectively. Despite a 15-fold difference in the amplification level between the two experiments, the regional pattern of misrepresentation was highly consistent.

Figure 3

Pattern of regional misrepresentation and GC content in amplified DNA. a to c: Graph interrelating the genome-wide pattern of misrepresentation along the chromosomes in an amplified (a) glioblastoma (GBM) DNA versus nonamplified GBM DNA array-CGH experiment and as displayed as a moving average by CaryoScope analysis (symmetric five-nearest neighbors) (a); corresponding raw intensity ratios for underrepresented clones plotted against the genomic order of genes (b); and average GC content measurements in selected terminal chromosomal regions (c). Clusters of highly underrepresented clones in the raw-intensity-ratio diagram were linkable to ∼50% of terminal chromosomal regions. Six chromosomal termini demonstrating maximal underrepresentation in the amplified DNA are circled in orange (5p_ter, 7p_ter, 9q_ter, 16p_ter, 17q_ter, 20q_ter). Six chromosomal termini with normo-representation are circled in blue (1q_ter, 3q_ter, 4q_ter, 12p_ter, 18p_ter, 20p_ter). Comparative assessment of the fractional GC content of these 12 chromosomal ends within a terminal length of 2.5 Mb revealed a significant difference in average GC content between the normo-represented (42.3%; range, 39 to 45%) and underrepresented (54.7%; range, 51 to 57%) termini (P = 0.002, two-sample Wilcoxon test), with the average genomic GC content of 41% indicated by the brown line. d: Comparison of terminal chromosomal and intrachromosomal clonal representations of selected regions in an amplified normal male DNA versus nonamplified female DNA and an amplified tumor DNA versus nonamplified tumor DNA array-CGH experiment, exemplifying the high concordance in the representational patterns of amplified normal and amplified tumor DNA.

Figure 4

Graphical portrayal of regional GC content heterogeneity versus regional amplification efficiency on chromosomes 3, 16, and 20, which were exemplarily selected because of their varying clonal representation pattern toward the chromosomal ends. a: Gene-by-gene display of regional amplification efficiency as depicted by the moving average ratios of amplified versus nonamplified normal human genomic DNA. b: Color-coded, fixed-length, moving-window plot depicting the variation in GC content across 100-kb windows. Substantial variation in GC levels between these windows was apparent, with particularly high GC content toward the end of chromosomal arms 16p, 16q, and 20q. Notably, regional underrepresentation along the chromosomes—and thus regional amplification efficiency—closely followed regional GC levels. Toward the end of chromosomal arms 16p, 16q, and 20q, where gene density is greatest, both clonal underrepresentation in the amplified DNA as well as GC content reached a maximum.

Figure 5

Compensation for representational distortion in amplified DNA. a to c: CaryoScope plots (moving window size, five clones) showing three independent array-CGH experiments using normal genomic DNA, including nonamplified male DNA versus nonamplified female DNA, amplified (a) male DNA versus nonamplified female DNA, and amplified male DNA versus amplified female DNA hybridizations, respectively. d to f: CaryoScope plots showing corresponding hybridization experiments with male glioblastoma (GBM) DNA, specifically nonamplified tumor DNA versus nonamplified normal female DNA, amplified tumor DNA versus nonamplified female DNA, and amplified tumor DNA versus amplified female DNA, respectively. As internal control, the ratio values for X-linked genes indicated the expected 0.5 dosage of these genes in the male test DNA versus the female reference DNA. The hybridization of either amplified normal DNA or amplified tumor DNA against nonamplified reference DNA revealed a reproducible pattern of misrepresentation, as indicated by a considerable difference in the clonal representation profiles between a and b and between d and e, respectively. As evidenced by almost similar representation profiles between a and c and between d and f, the use of reference DNA, amplified under exactly identical experimental conditions, remarkably compensated for clonal misrepresentations in the amplified study DNA by balancing out regional differences in amplification efficiency.

Figure 6

Representation of genetic alterations in amplified tumor cell line, fresh-frozen, and FFPE (p) tumor DNA. a to c: Scatter plots interrelating the moving average log₂ hybridization ratios of independent experiments in which tumor and reference DNA were either both amplified (y axis) or both nonamplified (a) (x axis). In addition to showing the correlation between all genes on the microarray, signature genetic alterations—including the ERBB2/TOP2A amplicon on chromosome 17q11-22 in BT474 cells and the Platelet-derived growth factor receptor A (PDGFRA) amplicon on chromosome 4q12 in the glioblastoma (GBM)—are indicated separately. A strong concordance for all genes between the nonamplified and amplified experiments was apparent. Clones that belonged to one amplicon closely clustered together. d: CaryoScope plot depiction of the high degree of preservation of major genetic alterations—both gene amplifications and deletions—in the amplified DNA in tumor cell lines and fresh-frozen and FFPE tumor. Concordances between the two data sets for signature changes on chromosomes 17, 9p, and 20q in BT474 and on chromosome 4 in fresh-frozen and FFPE tumor were R² = 0.96, R² = 0.91, R² = 0.92, R² = 0.94, and R² = 0.90, respectively.

Figure 7

Confidence limits after compensation for representational distortion. a and b: Comparative signal intensity ratio-to-genome position plots of two array-CGH experiments in which either both a nonamplified male and female DNA (a) or both amplified (a) male and female DNA (b) were hybridized against each other. Moving average signal intensity ratios were ordered according to genome position. Ratio values for X-linked genes signified the expected 0.5 dosage of these genes in the male DNA. Confidence limits for 99.9% of data for autosomal genes expressed as linear ratios are indicated by horizontal lines. The confidence bounds calculated for both experiments were almost identical (0.763 and 1.273 and 0.782 and 1.271, respectively). c: Graphical display of clone-by-clone comparison of intensity ratios in experiments shown in a and b, expressed as a ratio of five-nearest neighbor averaged intensity ratios of the nonamplified experiment versus intensity ratios of the amplified experiment. The resultant ratio for each clone therefore indicated the representation of that clone in the amplified experiment relative to the nonamplified experiment. The calculated 99.9% confidence limits (0.741 and 1.329) were similar to those of the separate nonamplified and amplified experiment plots. d and e: Same graphical model as c, for corresponding nonamplified glioblastoma (GBM) DNA versus nonamplified reference DNA and amplified GBM DNA versus amplified reference DNA array-CGH experiments in fresh-frozen (d) and FFPE (p) tumor (e). The confidence bounds for 99.9% of data for both the fresh-frozen tumor (0.719 and 1.325) and FFPE tumor (0.663 and 1.349) experiments were comparable to those of the corresponding normal DNA experiments. f: Probability density estimate plots showing similar distribution spreads of data points corresponding to graphs a to e.