A somatic reference standard for cancer genome sequencing

Abstract

Large-scale multiplexed identification of somatic alterations in cancer has become feasible with next generation sequencing (NGS). However, calibration of NGS somatic analysis tools has been hampered by a lack of tumor/normal reference standards. We thus performed paired PCR-free whole genome sequencing of a matched metastatic melanoma cell line (COLO829) and normal across three lineages and across separate institutions, with independent library preparations, sequencing, and analysis. We generated mean mapped coverages of 99X for COLO829 and 103X for the paired normal across three institutions. Results were combined with previously generated data allowing for comparison to a fourth lineage on earlier NGS technology. Aggregate variant detection led to the identification of consensus variants, including key events that represent hallmark mutation types including amplified BRAF V600E, a CDK2NA small deletion, a 12 kb PTEN deletion, and a dinucleotide TERT promoter substitution. Overall, common events include >35,000 point mutations, 446 small insertion/deletions, and >6,000 genes affected by copy number changes. We present this reference to the community as an initial standard for enabling quantitative evaluation of somatic mutation pipelines across institutions.

Figure 1. Overview of data generation and collection.

*Illumina acquired extracted DNA from ATCC for library construction, sequencing, and analysis.

Figure 2. Construction of a somatic truth set for COLO829.

(A) Identification of somatic reference SNVs. The total numbers of coding SNVs present in each truth set are shown. (B) Final somatic reference standard. Selected events are shown. Somatic coding SNVs are shown as black tick marks within the outermost ring. Consensus CNV gains are shown in green and consensus CNV losses are shown in red in the innermost circle.

Figure 3. Meta-analysis of the COLO829 somatic reference.

(A) Mutational signature of all SNVs. All substitutions are referred to by the pyrimidine context of the mutated base pair. (B) Genomic evolution of COLO829. A schematic of unique somatic alterations across each truth set is shown. Separate lobes reflect the level of divergence demonstrated by each truth set as measured by the number of unique somatic SNVs and indels for that data set. Examples of unique events are shown. The Pleasance sample did not demonstrate unique coding SNVs or indels (chromosomal coordinates of unique intronic events are shown).