Tissue-specific mutation accumulation in human adult stem cells during life

Abstract

The gradual accumulation of genetic mutations in human adult stem cells (ASCs) during life is associated with various age-related diseases, including cancer. Extreme variation in cancer risk across tissues was recently proposed to depend on the lifetime number of ASC divisions, owing to unavoidable random mutations that arise during DNA replication. However, the rates and patterns of mutations in normal ASCs remain unknown. Here we determine genome-wide mutation patterns in ASCs of the small intestine, colon and liver of human donors with ages ranging from 3 to 87 years by sequencing clonal organoid cultures derived from primary multipotent cells. Our results show that mutations accumulate steadily over time in all of the assessed tissue types, at a rate of approximately 40 novel mutations per year, despite the large variation in cancer incidence among these tissues. Liver ASCs, however, have different mutation spectra compared to those of the colon and small intestine. Mutational signature analysis reveals that this difference can be attributed to spontaneous deamination of methylated cytosine residues in the colon and small intestine, probably reflecting their high ASC division rate. In liver, a signature with an as-yet-unknown underlying mechanism is predominant. Mutation spectra of driver genes in cancer show high similarity to the tissue-specific ASC mutation spectra, suggesting that intrinsic mutational processes in ASCs can initiate tumorigenesis. Notably, the inter-individual variation in mutation rate and spectra are low, suggesting tissue-specific activity of common mutational processes throughout life.

Extended Data Figure 1. Cataloguing somatic mutation loads in human ASCs.

a, Schematic overview of the experimental setup to determine somatic mutations in individual human ASCs. Colon, small intestine and liver biopsies were cultured in bulk for 1-2 week(s) before single cells were sorted and clonally expanded until enough DNA could be isolated for WGS analysis. WGS of the clonal organoid culture allows for cataloguing of somatic variants in the original ASCs that gave rise to the clonal cultures that were acquired during life and the first 7–14 days of culturing. Biopsy or blood was sequenced as a reference sample. b, Filter steps to obtain somatic mutations in ASCs. c, Number of point mutations that pass each corresponding filter step in a for each ASC culture of donors 5 and 6. d, Independent validations of mutations that were filtered out by amplicon-based resequencing. The asterisk indicates a position that is not located in the surveyed areas of the assessed ASCs in the original experiment, which is corrected for in all analyses. e, Independent validations of mutations that passed all filters by amplicon-based re-sequencing. Confirmed positions are defined as those with a call in the indicated ASC with a VAF ≥ 0.3 and without a call in the corresponding reference sample. f, Qualification of unconfirmed positions based on manual inspection. True-positive positions are positions that were correctly called, but for which the VAF threshold was not met in the validation experiment. False-positive positions are positions without evidence in the validation experiment or are noisy. ‘Missed in germline’ are positions that were called in the reference sample in the validation experiment.

Extended Data Figure 2. Variant allele frequency distribution plot for each assessed ASC.

A distribution plot of the VAFs of all somatic mutations that remain before filtering for the VAF in filter step 6 (Extended Data Fig. 1b). Clonal heterozygous somatic mutations form a peak around VAF = 0.5. A threshold of VAF ≥ 0.3 was used to obtain somatic mutations that were clonal in the organoid cultures and therefore present in the original cloned ASCs (see Methods). Mutations acquired after the single ASC expansion step are subclonal (that is, not present in all cells of the clonal culture) and have lower VAFs. Two samples (donor 14, ASC 14-b and donor 17, ASC 17-c) showed a shift in the main VAF peak to the left, indicating that these cultures did not arise from a single ASC and were therefore excluded from the study.

Extended Data Figure 3. Confirmation rate of somatic point mutations.

a, Overlap of somatic point mutations between the clonal organoid cultures and corresponding subcloned cultures depicted in Extended Data Fig. 6. b, Confirmation rate of point mutations, which were observed in the original cloned culture, in the corresponding subcloned culture. Data are represented as the mean percentage of confirmed point mutations over all clone–subclone pairs indicated in a (n = 10) and error bars represent s.d.

Extended Data Figure 4. Somatic mutation loads in consensus-surveyed area and overlap of point mutations between ASCs from the same donor.

a, Correlation of the number of somatic point mutations per ASC, which were observed in the genomic regions that were surveyed (for example, a base coverage of at least 20× in both the clonal culture and the reference sample; Methods) in all the ASCs, with the age of the donors per tissue indicated. This consensus-surveyed area comprises 38.2% of the non-N autosomal genome. Each data point represents a single ASC. Indicated are the P values of the age effects in the linear mixed model (two-tailed t-test) for each tissue. The sample sizes for colon, small intestine and liver are 6, 9 and 5 donors and 21, 14 and 10 ASCs, respectively. b, Somatic mutation accumulation rate per tissue as estimated by the linear mixed models in a. Error bars represent the 95% confidence intervals of the slope estimates. c, Relative contribution of the indicated mutation types to the point mutation spectra in the consensus-surveyed area per tissue type. Data are represented as the mean relative contribution of each mutation type over all ASCs per tissue type (n = 21, 14 and 10 for colon, small intestine and liver, respectively); error bars represent s.d. The total number of identified somatic point mutations per tissue is shown. d, Overlap of the somatic point mutations between ASCs of the same donor. The number of point mutations, observed in the total surveyed area per ASC, that are shared between the assessed ASCs of the same donor is indicated.

Extended Data Figure 5. Point-mutation spectrum per donor.

Relative contribution of the different types of point mutation to the spectrum of each donor. Data are represented as the mean relative contribution of each mutation type when multiple ASCs were measured per donor (the number n of ASC per donor is depicted for each donor) and error bars represent standard deviation. Indicated are the age of the donors, the total number of point mutations used to determine each spectrum and the tissue type.

Extended Data Figure 6. Mutation patterns associated with long-term in vitro expansion of ASCs.

a, Schematic overview of the experimental setup to catalogue mutations associated with the organoid culture system. Clonal small intestinal and liver organoid cultures (Extended Data Fig. 1a) were cultured for 3–5 months. A second clonal expansion step was subsequently performed, followed by WGS analysis, to catalogue all the mutations that were present in the subcloned ASCs. To obtain mutations that were specifically acquired during culturing, mutations in the original clonal cultures were subtracted from those observed in the corresponding second subcloned cultures. b, Relative contribution of the indicated mutation types to the point mutation spectra specifically observed in vitro per tissue type. Data are represented as the mean relative contribution of each mutation type over all subcloned ASCs per tissue type (n = 6 and 4 for small intestine and liver, respectively) and error bars represent s.d. Indicated are the total number of identified somatic point mutations, which were specifically acquired between the two clonal expansion steps indicated in a, per tissue. c, Relative contribution of the mutational signatures depicted in Fig. 2a, which explain the mutation spectra depicted in b.

Extended Data Figure 7. Non-random distribution of mutational signatures throughout the genome.

a, Context- and replication-timing-dependent mutation spectrum of the three mutational signatures depicted in Fig. 2a. Indicated is the contribution of each trinucleotide to the signatures (order is similar as in ref. 11), subdivided into the fraction of the trinucleotide-change present in early, intermediate or late replicating genomic regions. b, log₂ ratio of the observed and expected number of mutations per indicated base substitution (summed over all trinucleotides) in early-, intermediate- and late-replicating genomic regions for each of the signatures depicted in a. log₂ ratio indicates the effect size of the bias and asterisks indicate significant DNA-replication-timing bias (P < 0.05, binomial test). c, log₂ ratio of the total number of observed and expected mutations in early-, intermediate- and late-replicating genomic regions for each signature depicted in a. log₂ ratio indicates the effect-size of the bias and asterisks indicate significant DNA replication timing bias (P < 0.05, binomial test). d, Context- and transcriptional-strand-dependent mutation spectrum of the three mutational signatures depicted in Fig. 2a. Indicated is the contribution of each trinucleotide to the signatures (order is similar to that in ref. 11), subdivided into the fraction of the trinucleotide-change present on the transcribed and untranscribed strand. e, log₂ ratio of the number of mutations on the transcribed and untranscribed strand per indicated base substitution for each signature depicted in d. log₂ ratio indicates the effect size of the bias and asterisks indicate significant transcriptional strand bias (P < 0.05, binomial test). f, The dN/dS ratio for all protein-coding somatic point mutations observed in all ASCs per tissue type. Error bars indicate 95% confidence intervals (likelihood ratio test).

Extended Data Figure 8. Comparison of mutation loads between intestinal ASCs derived from human and mouse.

a, Mutation frequency in mouse intestinal ASCs is compared to the linear fit, describing the relationship between the mutation frequency in human intestinal ASCs and age of the donor. Indicated by the dotted lines are the mean mutation frequencies over all ASCs per mouse (n = 3) and the corresponding age of human linear fit. b, Relative contribution of the indicated mutation types to the point mutation spectra for all assessed human intestinal ASCs and for each mouse. Data are represented as the mean relative contribution of each mutation type over all the ASCs per indicated category (n = 14, 3 and 3 for human, mouse 1 and mouse 2, respectively), error bars indicate s.d.

Figure 1. Age-associated accumulation of somatic point mutations in human ASCs.

a, Correlation of the number of somatic point mutations in each ASC type examined (extrapolated to the whole autosomal genome) with age of the donors per tissue. Each data point represents a single ASC. The P values of the age effects in the linear mixed model (two-tailed t-test) are indicated for each tissue. The sample sizes for colon, small intestine and liver ASCs are 6, 9 and, 5 donors, with, in total, 21, 14 and 10 ASCs, respectively. b, Somatic mutation accumulation rate per tissue as estimated by the linear mixed models in a. Error bars represent the 95% confidence intervals of the slope estimates. c, Relative contribution of the indicated mutation types to the point mutation spectrum for each tissue type. Data are represented as the mean relative contribution of each mutation type over all ASCs per tissue type (n = 21, 14 and 10 for colon, small intestine and liver, respectively) and error bars represent standard deviation. The total number of identified somatic point mutations per tissue is indicated.

Figure 2. Signatures of mutational processes in human ASCs and their tissue-specific contribution.

a, Contribution of context-dependent mutation types to the three mutational signatures that were identified by non-negative matrix factorization (NMF) analysis of the somatic mutation collection observed in the ASCs across all assessed tissues. The contribution of each trinucleotide (order is similar to that in ref. 11) to each signature is shown. For each signature, the presence of transcriptional-strand bias, DNA-replication-timing bias and/or association with the culture system is indicated. b, Absolute contribution of each mutational signature type (extrapolated to the whole autosomal genome) plotted against the age of the donors for each tissue. Each data point represents a single ASC. The P values of the age effects per tissue are shown (linear mixed model, two-tailed t-test). c, Signature-specific mutation rate per year per genome for each tissue as estimated by the linear mixed model in b. Error bars represent the 95% confidence intervals of the slope estimates.

Figure 3. Non-random genomic distribution of somatic point mutations in ASCs.

a, Enrichment and depletion of somatic point mutations in the indicated genomic regions for each tissue. The log₂ ratio of the number of observed and expected point mutations indicates the effect size of the enrichment or depletion in each region. *P < 0.05, one-sided binomial test. b, Distribution of DNA replication timing for all genomic positions and the somatic point mutations detected in human ASCs per tissue. c, Relative contribution of each point-mutation type on the transcribed and untranscribed strand for each tissue. *P < 0.05, two-sided Poisson test.

Figure 4. Cancer-associated mutation spectra in driver genes and structural variation in normal ASCs.

a, Spectrum of point mutations in cancer driver genes APC, TP53, SMAD4 and CTNNB1 identified in colorectal and liver cancer. The total number of somatic point mutations per gene per cancer type is indicated. b, Read-depth analysis indicating a relatively small deletion (~90 kb) located within a common fragile site (FRA2I) in intestinal ASC 11-a. Each point represents the log₂ value of the GC-corrected read-depth ratio per 5-kb window. Dashed lines indicate breakpoint regions; a schematic representation of the identified structural variant with associated genomic and breakpoint features is depicted below. c, Two large (>1 Mb) tandem duplications identified in liver ASC 14-a with microhomology at the breakpoints; duplications are indicated in the schematic representation of the identified structural variants below the graph. d, A complex structural variation (an unbalanced translocation involving 3 chromosomes) identified in colon ASCs 4-b and 4-e. Coloured lines in the schematic below show the predicted derivative chromosomes. e, Read-depth analysis indicating a trisomy of chromosome 13 in colon ASC 3-c. Each data point represents the median chromosome copy number per 500-kb bin plotted over the genome, with alternating colours for each successive chromosome.