Analytical and Clinical Validation of a Digital Sequencing Panel for Quantitative, Highly Accurate Evaluation of Cell-Free Circulating Tumor DNA

Abstract

Next-generation sequencing of cell-free circulating solid tumor DNA addresses two challenges in contemporary cancer care. First this method of massively parallel and deep sequencing enables assessment of a comprehensive panel of genomic targets from a single sample, and second, it obviates the need for repeat invasive tissue biopsies. Digital Sequencing™ is a novel method for high-quality sequencing of circulating tumor DNA simultaneously across a comprehensive panel of over 50 cancer-related genes with a simple blood test. Here we report the analytic and clinical validation of the gene panel. Analytic sensitivity down to 0.1% mutant allele fraction is demonstrated via serial dilution studies of known samples. Near-perfect analytic specificity (> 99.9999%) enables complete coverage of many genes without the false positives typically seen with traditional sequencing assays at mutant allele frequencies or fractions below 5%. We compared digital sequencing of plasma-derived cell-free DNA to tissue-based sequencing on 165 consecutive matched samples from five outside centers in patients with stage III-IV solid tumor cancers. Clinical sensitivity of plasma-derived NGS was 85.0%, comparable to 80.7% sensitivity for tissue. The assay success rate on 1,000 consecutive samples in clinical practice was 99.8%. Digital sequencing of plasma-derived DNA is indicated in advanced cancer patients to prevent repeated invasive biopsies when the initial biopsy is inadequate, unobtainable for genomic testing, or uninformative, or when the patient's cancer has progressed despite treatment. Its clinical utility is derived from reduction in the costs, complications and delays associated with invasive tissue biopsies for genomic testing.

Fig 1. Workflow for the Guardant360 cell-free circulating DNA NGS genomic profile.

(a) cfDNA is extracted from a routine blood draw. (b) 5.0–30 ng of DNA undergoes digital library preparation including oligonucleotide barcoding of each strand in each individual DNA fragment. Complete sequencing of 512 exons in 54 cancer-related genes is conducted with the HiSeq 2500 (Illumina). Multi-analyte algorithms and bioinformatics are used to reconstruct the progenitor cfDNA fragment sequences without false positives. (c) Sequence data are processed using a customized analysis pipeline designed to accurately detect the four major classes of genomic alterations. (d) Mutant allele fractions are reported quantitatively for somatic single nucleotide variants of clinical significance and distinguished from germline single nucleotide variants (SNVs) by reference to the COSMIC and dbSNP databases, as well as their concentrations.

Fig 2. Fig 2A illustrates output from Illumina HiSeq using standard library prep on cell-free DNA sample spiked with samples from ten cell lines with known single nucleotide variant (SNV) mutations. Germline single nucleotide polymorphisms (SNPs) (green dots) at either 50% (heterozygous) or 100% (homozygous) mutant allele fractions (MAF). In contrast, the ten somatic SNVs (red dots) are quantitated at much lower MAF typically encountered with cell-free circulating tumor DNA, and are obscured by the false positive “noise” associated with low DNA concentrations. The larger the targeted region, the more false positive signals are encountered. In this actual sample, sequencing the long targeted region (78 kbp) required for the 54-gene panel results in 224 false positives at the 0.1% to 10% MAFs, making accurate sequencing of ctDNA unworkable. Fig 2B utilizes the same sample as in Fig 2A but was analyzed with Digital Sequencing technology. Molecular techniques in the pre-analytic/pre-sequencing phase and bioinformatics in the post-sequencing phase are employed to eliminate the “noise” in a process analogous to the signal transduction processing-enabled conversion of analog voice and television signals to digital signals. The result is sensitivity to the level of 1–2 mutated DNA fragment molecules in up to 1,000 wild type (mostly leukocyte-derived) DNA fragments overlapping the same nucleotide base position, essentially eliminating the false positives normally encountered at low MAFs when sequencing large targeted regions.

Fig 3. Analytic Specificity and Sensitivity, and Diagnostic Accuracy of the Guardant360 cell-free circulating tumor DNA assay.

The matrix illustrates that a targeted region of 78 kbp was sequenced in each of 20 samples to identify single nucleotide variants at approximately 2.0–5.0% MAF (heterozygous) in circulating cfDNA. Green dots represent concordant single nucleotide variant (SNV) calls for digital sequencing of 10 ng cfDNA to calls made by whole exome sequencing of 2 μg of genomic (leukocyte) DNA from the same sample. The red dot represents the single false positive result in a cumulative 1.56 million bases sequenced. The far right-hand column illustrates the number of SNVs per sample identified with exome sequencing, and the penultimate column with digital sequencing, for a total of 365 and 366 SNVs, respectively.

Fig 4. Analytic Sensitivity of the Guardant360 digital sequencing method.

Twenty nine SNV samples were diluted serially until they could no longer be measured with the assay. Each column represents successively greater serial dilutions of a given sample. The limit of detection (LOD) was 0.25% mutant allele frequency or fraction) (MAF), defined as the percentage at which > 80% of samples were detected. Note that almost 30% of samples were additionally detected at 0.1% MAF or lower, where 0.1% represents a single mutated DNA fragment out of 999 wild-type (leukocyte-derived) DNA fragments overlapping the same nucleotide base.

Fig 5. Guardant360 samples stressed by prolonged storage time and high temperature cycling do not impact performance.

A) Extent of genomic DNA (gDNA from leukocytes) contamination in the control cell-free DNA (cfDNA) samples compared to prolonged temperature cycled samples sets represented as the ratio of gDNA (> 500 bps) to cfDNA (< 500 bps). Temperature cycled samples were incubated at 37°C for 8 hours followed by 16 hours at room temperature daily for 5 days. Control samples were processed immediately upon receipt at the laboratory. Center lines show the medians; box limits indicate the 25^th and 75^th percentiles as determined by R software; whiskers extend 1.5 times the interquartile range from the 25^th and 75^th percentiles, outliers are represented by dots. N = 10 sample points. B) Concordance of control sample set with prolonged temperature cycled sample set shown by a correlation plot of all mutant allele frequencies (MAFs) of the single nucleotide variants (SNVs) from the control sample set versus the corresponding SNV MAFs in the temperature cycled sample set. The total number of different SNVs plotted is 24. The inset shows the correlation of MAFs at less than or equal to 2% between the two data sets, showing excellent correlation even when SNVs are as low as 2.5%.

Fig 6. Frequency distribution of single nucleotide variant (SNV) mutant allele fractions (MAFs) for the first 1,000 consecutive patients tested in clinical practice (broad range of non-hematologic malignancies).

On the left the three peaks represent kernel distribution density plots of the frequencies of somatic and germline mutant allele fractions. By their low concentrations, somatic mutations (far left-hand small peak) can be generally distinguished from heterozygous germline SNVs around 50% MAF (middle peak) and homozygous germline SNVs around 100% MAF (right-hand peak). Cell-free DNA is both leukocyte-derived and tumor-derived, with the germline DNA generally representing the bulk of the cfDNA. On the Guardant360 panel the molecular tumor board filters out the germline SNVs and only the somatic mutations are reported. The red curve in the right-hand figure shows the frequency distribution of the MAFs for the somatic SNVs only. The long tail reflects the rare patients with a somatic mutation at high MAF.

Fig 7. Fig 7A is a comparison of tissue NGS results biopsied at five outside institutions compared to cfDNA sequencing at Guardant Health on 165 paired plasma samples from stage III-IV solid tumor cancer patients. Data summarizes diagnostic test performance for all 54 mutated tumor suppressor and oncogenes. The most commonly mutated genes were ALK, APC, BRAF, CDKN2A, CTNNB1, FBXW7, KRAS, NRAS, PIK3CA, PTEN, and TP53. Sensitivity, specificity and diagnostic accuracy are shown with 95% confidence intervals.Fig 7B illustrates the two by two contingency tables corresponding to Fig 7A. On the left cfDNA NGS results are compared to tissue-based NGS as the reference standard. On the right tissue-based NGS results are compared to cfDNA findings as the reference standard. All gene mutations found in cfDNA and tissue DNA based on NGS of 54 genes are shown in S2 Table. Both methods demonstrate similarly high sensitivity and near-perfect specificity. For cfDNA, sensitivity is limited by the amount of tumor DNA shed into circulation and for tissue, sensitivity is likely limited by sampling error related to intra-or inter-tumor heterogeneity. The sampling error on tissue samples may be related to sub-sampling of tumor heterogeneity by needle or surgical biopsy.