Mutational processes contributing to the development of multiple myeloma

Abstract

To gain insight into multiple myeloma (MM) tumorigenesis, we analyzed the mutational signatures in 874 whole-exome and 850 whole-genome data from the CoMMpass Study. We identified that coding and non-coding regions are differentially dominated by distinct single-nucleotide variant (SNV) mutational signatures, as well as five de novo structural rearrangement signatures. Mutational signatures reflective of different principle mutational processes-aging, defective DNA repair, and apolipoprotein B editing complex (APOBEC)/activation-induced deaminase activity-characterize MM. These mutational signatures show evidence of subgroup specificity-APOBEC-attributed signatures associated with MAF translocation t(14;16) and t(14;20) MM; potentially DNA repair deficiency with t(11;14) and t(4;14); and aging with hyperdiploidy. Mutational signatures beyond that associated with APOBEC are independent of established prognostic markers and appear to have relevance to predicting high-risk MM.

Fig. 1. De novo structural rearrangements signatures.

a Five de novo structural rearrangement signatures (RSs) extracted in multiple myeloma. b Cumulative mutational contribution of the structural rearrangements across 850 whole-genome sequencing (WGS) samples. Del: deletions; tds: tandem duplications; inv: inversions; trans: translocations

Fig. 2. Relationship between replication and transcription in mutational processes.

a Mutation rates across different DNA replication timing bins for single-nucleotide variants (SNVs). Whole-genome sequencing (WGS) mutation rate (blue) was estimated from low-coverage WGS data (6–12×). Whole-exome sequencing (WES) mutation rate (orange) was estimated from high-coverage WES data (120–150×) with variants called by at least two variant callers. b Proportion of mutations on leading and lagging strands per signature based on WGS data. Asterisks indicate significant asymmetry (Q < 0.05 and strand imbalances >30%). c Relationship between transcriptional level and mutation rate. The range of number of genes across all samples included in each FPKM category (from low to high gene expression) are category 1: 4062–6800 (median 4209); category 2: 1323–4062 (median 3914); category 3: 4060–4062 (median 4061); category 4: 4060–4061 (median 4061); category 5: 4062. Error bars represent the 95% confidence intervals. d Proportion of mutations on transcribed and non-transcribed strands across major signatures based on WES data. WGS: whole-genome sequencing; WES: whole-exome sequencing; SNVs: single-nucleotide variants; FPKM: fragments per kilobase of exons per million reads. Flat signatures include COSMIC signatures 3, 5, and 8

Fig. 3

Contribution of each single-nucleotide variant mutational signature in coding (blue) and non-coding (orange) regions. Flat signatures include COSMIC signatures 3, 5, and 8

Fig. 4. Mutational signatures associated with driver genes.

a Cumulative mutational contribution of mutational signatures across 50 multiple myeloma (MM) driver genes^– (blue, 1679 mutations in total) and other exonic mutations (orange). b Normalized cumulative mutational contribution of signatures with top ten contribution for most frequently mutated MM driver genes (+) vs. other mutations (−) in tumors with the corresponding driver gene being mutated: KRAS (n = 247), NRAS (n = 204), DIS3 (n = 104), TRAF3 (n = 83), CCND1 (n = 78), BRAF (n = 70), FAM46C (n = 70), EGR1 (n = 65), TP53 (n = 52), SP140 (n = 30), PRDM1 (n = 26), and ATM (n = 19); n: number of mutations. Flat signatures include COSMIC signatures 3, 5, and 8

Fig. 5. Integrative clusters based on mutational signatures and patient prognosis.

a Heatmap showing proportions of rearrangement signatures and major COSMIC (Catalog of Somatic Mutations in Cancer) signatures in unsupervised hierarchical clusters. Flat signatures include COSMIC signatures 3, 5, and 8. The lower panel shows distribution of translocations, prognostic chromosome-arm events, and TP53 non-synonymous mutations across all samples. b Progression-free survival and c overall survival across different cluster groups. The global P values across all cluster groups were calculated to assess whether there is survival difference between groups

Fig. 6. Contribution of major mutational processes operative in multiple myeloma.

This model represents differential contribution of various identified mutational processes in myeloma. For early mutational processes, activation-induced deaminase (AID) has the overall largest contribution to mutational processes across all subgroups represented by a larger oval. For late mutational processes, major mutational processes with known etiologies associated with aging, apolipoprotein B editing complex (APOBEC), DNA repair deficiency (DRD), and AID are depicted. Larger oval sizes indicate larger relative contribution of the mutational process