eccDNAs are apoptotic products with high innate immunostimulatory activity

Abstract

Extrachromosomal circular DNA elements (eccDNAs) have been described in the literature for several decades, and are known for their broad existence across different species^1,2. However, their biogenesis and functions are largely unknown. By developing a new circular DNA enrichment method, here we purified and sequenced full-length eccDNAs with Nanopore sequencing. We found that eccDNAs map across the entire genome in a close to random manner, suggesting a biogenesis mechanism of random ligation of genomic DNA fragments. Consistent with this idea, we found that apoptosis inducers can increase eccDNA generation, which is dependent on apoptotic DNA fragmentation followed by ligation by DNA ligase 3. Importantly, we demonstrated that eccDNAs can function as potent innate immunostimulants in a manner that is independent of eccDNA sequence but dependent on eccDNA circularity and the cytosolic DNA sensor Sting. Collectively, our study not only revealed the origin, biogenesis and immunostimulant function of eccDNAs but also uncovered their sensing pathway and potential clinical implications in immune response.

Extended Data Fig. 1.. Selective binding of eccDNAs to beads and high sensitivity of DNA detection by SYBR Gold staining

a, Representative gel image showing selective binding of circular DNA to magnetic silica beads in solution A. The assay was tested with 200× (mass) linear DNA (lane 4 and 6) and 1X (mass) DNA circles (lane 5 and 6). Lanes 1–3 indicate the input DNAs. Lane 1, 0.5% of input linear DNA for lane 4 was loaded; lane 2, equal amount of input circular DNAs for lane 5 were loaded; lane 3, 0.5% of input linear DNA and equal amount of input circular DNAs for lane 6 were loaded. Lanes 4–6 were DNAs recovered from Solution A. lane 4, 200× (mass) linear DNA alone undergone purification by solution A; lane 5, 1× (mass) DNA circles undergone purification by solution A; lane 6 mixture of 200× (mass) linear DNA and 1× (mass) DNA circles undergone purification by solution A. Note, only circular DNAs were recovered. The recovery rate is very high, particularly for the smaller circular DNAs. b, High sensitivity of DNA detection using vertical agarose gel electrophoresis and SYBR Gold staining. 0.2 μl commercial DNA ladder (total of 10 ng) was undergone 5× series dilutions and fractionated by 1% vertical agarose gel electrophoresis, stained by SYBR Gold, DNA in lane-4 were 125× diluted of that in lane-1, and could still be visualized. The detection limit is estimated as 5–10 pg/band. Results in a–b are representative of three independent experiments.

Extended Fig. 2.. Summary of the nanopore sequencing data.

a, Diagram of nanopore long read sequencing of eccDNA. Tandem copies of eccDNAs were self-concatenated to long molecule by rolling cycle amplification (RCA), and directly read through by Oxford Nanopore. Each copy of eccDNA molecule in a single long molecule was sequenced multiple times. “S”: split site. b, Summary of mESC eccDNA long reads from an Oxford Nanopore MinION flow cell. c, Diagram showing how the eccDNA full-length sequence is called and categorized. Nanopore reads from (a), the dashed box, were aligned to a single locus (Continuous) or to multiple loci (Non-continuous) in genome. Continuous: an example of six sub-regions of a long nanopore read repeatedly aligned to a single locus, where full length sequence of eccDNA was presented with only one split site (S); Non-continuous: an example of eight sub-regions of a single long read sequentially aligned to two separate loci (Locus-1 and Locus-2), representing an eccDNA ligated by two genomic fragments (2f ecc) with two split sites (S1 and S2). d, Criteria for eccDNA calling. EccDNAs were called based on their number of full passes aligned to the genome. Long reads with less than two full passes were discarded (left and middle panel). Left, Nanopore read that hits genome only once either fails to designate the genomic start and end site of eccDNA (up panel), or miss the middle region (bottom panel) that may or may not include in the original eccDNA molecule (Uncertain); Middle, because of potential sequencing error of Oxford Nanopore, reads that hit genome more than once but less than twice (1 full pass) were also discarded due to the lack of confirmation in eccDNA calling, particularly on designating the start and end site of eccDNA. Right, eccDNA molecules were called from long reads when covered at least twice (>=2 full pass) on their aligned loci.

Extended Data Fig. 3.. Summary of Illumina short read sequencing and Chromosomal distribution of eccDNA fragments.

a, Summary of eccDNA short read sequencing without RCA. Purified eccDNA was directly tagmented with Tn5 (Illumina Nextera), and sequenced with Illumina Hiseq 2500 in PE150 mode. b, Chromosomal distribution of eccDNA short reads.

Extended Data Fig. 4.. Effects of Endonuclease G, DNase γ, and DNA ligases knockout on apoptosis and eccDNA generation

a, Quantification of eccDNA from cells of the indicated treatment. EccDNA production were presented as nanogram per 10 million cells; ud, under detection limit. Bars indicate mean ± SEM of three independent experiments. b, Diagram illustration and PCR confirmation of the EndoG knockout mESC line. Gene structure of EndoG, sgRNAs (red arrows), two sets of screen primers for internal sites (black arrowhead, “n” =negative knockout cell line) and external sites (red arrowhead, “p” =positive knockout cell line) were shown. c, Diagram illustration and PCR confirmation of the DNase γ knockout mESC lines. Gene structure of DNase γ, sgRNAs (red arrows), two sets of screen primers for internal sites (black arrowhead, “n” =negative knockout cell line) and external sites (red arrowhead, “p” =positive knockout cell line) were shown. d, Cell viability is not affected by EndoG or DNase γ KO. Cell viability was evaluated by flow cytometry, after staining with Far Red Live/Dead Cell Stain Kit, FSC-A/SSC-A and FSC-A/FSC-H were sequentially used to exclude debris and gate on singlets, respectively, then gate on APC+ as dead cells. Bars indicate mean ± SEM. of dead cell ratio from three independent experiments. e, Deficiency of DNase 𝛾 or EndoG in mESC do not significantly alter UV-induced cell death. Cell death was measured by flow cytometry, after staining with Far Red Live/Dead Cell Stain Kit, FSC-A/SSC-A and FSC-A/FSC-H were sequentially used to exclude debris and gate on singlets, respectively, then gate on APC+ as dead cells. Bar indicate mean ± SEM. of dead cell ratio of 3 independent experiments. f, Quantification of eccDNAs presented in Fig. 3d. EccDNAs below the mtDNA band were quantified by densitometry (by Image J 1.53e) and presented as relative levels to that in WT cells of parallel eccDNA purifications. Bars indicate mean ± SEM. of three independent experiments. g, Quantification of eccDNA below the mtDNA band by densitometry (by Image J 1.53e). Data is presented as relative levels to that purified from WT cells of parallel eccDNA purifications (Fig. 3g), bars indicate mean ± SEM of three independent experiments. Ordinary one-way ANOVA with Tukey’s multiple comparison test was used for multiple comparisons in e, f, g. **, p<0.01; ns, no significant.

Extended Data Fig. 5.. EccDNAs are potent immunostimulants for BMDCs

a, Confirmation of BMDC identity by flow cytometry. After differentiating bone marrow cells with 20 ng/ml GM-CSF for 7 days, cell debris (left) were first excluded and singlets (middle) were then phenotyped on the basis of their CD11c and major histocompatibility complex II (MHCII) expression (right) to define BMDC, the numbers indicate the percentage of gated cells. Data were further analyzed with FlowJo. V10.8.0 and shown as representative of 2 independent experiments. b, Various DNAs were resolved by agarose gel electrophoresis. Li-DNA: sheared linear genomic DNA; poly(dG:dC), poly(deoxyguanylic-deoxycytidylic). Representative gel of three independent experiments was shown. c-d, Bar graphs showing the relative mRNA (c) and protein (ELISA) (d) levels of IL-6 and TNF-α. Data is shown as mean ± SEM of replicates (n=4 per group) of a representative experiment in three independent experiments. e-f, DNase I pretreatment abolishes IL-6 and TNF-α induction by eccDNA. Equal amount of DNA (120 ng/ml) used to prepare transfection mixtures were pre-treated with or without DNase I as indicated, then transfected to BMDCs. 12 hours later, total RNA was extracted for RT-qPCR (e) and medium was collected for ELISA (f). Data is shown as mean ± SEM of replicates (n=4 per group) of a representative experiment in three independent experiments. Comparisons in c-f were done on biological replicates by Ordinary one-way ANOVA with Tukey’s multiple comparison test. *, p<0.05; **, p<0.01; ***, p<0.001; ****, p<0.0001; ns, no significant; nd, not detected.

Extended Data Fig. 6.. EccDNAs are potent immunostimulants for BMDMs

a, Confirmation of BMDMs identify by flow cytometry. After differentiating bone marrow cells with L929 conditioned medium for 7 days, cells debris (left) were first excluded and singlets (middle) then phenotyped on the basis of F4/80 and CD11b expression (right) to define BMDM, the numbers indicate the percentage of gated cells. Data were further analyzed with FlowJo. V10.8.0 and shown as representative of 2 independent experiments. b-c, EccDNAs induce cytokine genes in BMDMs. Bar graphs showing the induction of mRNA (b) and protein (c) of IL-6 and TNF-α in BMDMs that transfected with varying levels of eccDNA, compared with fragmented linear DNA, and poly(dG:dC). RT-qPCR were performed after 12-hours transfection. ELISA analysis (c) was performed after 24-hours transfection. Data is shown as mean ± S EM of replicates (n=4 per group) of a representative experiment of three independent experiments. Comparisons were performed on biological replicates with equal amount of DNA transfection by Ordinary one-way ANOVA with Tukey’s multiple comparison test. *, p<0.05; **, p<0.01; ***, p<0.001; ****, p<0.0001; ns, no significant; nd, not detected.

Extended Data Fig. 7.. The circularity of eccDNAs, but not the sequence, is critical for their immunostimulant activity

a, Bar graphs showing the relative IL-6 and TNF-α mRNA levels. Data is shown as mean ± S EM of replicates (n=4 per group) of a representative experiment in three independent experiments. b-c, Bar graphs showing the relative IL-6 and TNF-α mRNA levels (b), and protein (ELISA) levels (c). Data is shown as mean ± SEM of replicates (n=4 per group) of a representative experiment in three independent experiments. d, Diagram of DNA transfection efficiency and stability assay. Step-1: 5 Phosphorothioate (purple “*”) end-protected synthetic linear DNA (PS-syn-linear) and its circular form with equal number of phosphorothioate bonds (PS-Syn-circular) were transfected to BMDCs in the same way as in Fig. 5 for either 1 or 12 hours. Step-2: cells were lysed in 100 μl lysis buffer and treated with Thermoliable Proteinase K to prepare total DNA. Step-3: 4 μl total DNA was used for qPCR with a set of primers that amplify a 117 bp fragment in both linear and circular DNA. e, qPCR analysis of the samples prepared as described in (d). Transfected DNA level was normalized to that of 10 ng/ml PS-syn-linear transfection (n= 4 or 6, as indicated by dotes). Bars indicate mean ± SEM. of three independent experiments. f, 12 hours after transfection of indicated DNA at 30 ng/ml, medium was collected for ELISA essay, Data is shown as mean ± SEM of replicates (n=4 per group) of a representative experiment in three independent experiments. Comparisons in a-c were performed on biological replicates by Ordinary one-way ANOVA with Tukey’s multiple comparison test; two-tailed unpaired t tests (e-f). *, p<0.05; **, p<0.01; ***, p<0.001; ****, p<0.0001; ns, no significant.

Extended Data Fig. 8.. Reproducibility of the BMDC transcriptomes

a-c, Scatter plot of pair-wise comparison of the transcriptomes of three independent BMDC samples of untreated (a), treated with eccDNA (b) or linear DNA (c). The x and y-axis are log2(FPKM+0.1).

Extended Data Fig. 9.. Global transcriptional response to eccDNA in BMDMs

a-c, Scatter plot of pair-wise comparison of the transcriptomes of three independent BMDM samples of untreated (a), treated with eccDNA (b) or linear DNA (c). The x and y-axis are log2(FPKM+0.1). d, Scatter plot showing 380 genes (left panel, red dots) that are significantly induced (FC ≥ 5, adjusted p-value < 0.001; FC and p-value were generated using DESeq2 and p-values were adjusted by IHW) by eccDNA, but not linear DNA, in BMDMs. 24 significantly induced cytokine genes are indicated (right panel, red dots). The x and y-axis are log2-transformed normalized read counts. e, Heatmap presentation of the top 20 induced genes. f, GO terms enriched in the genes activated by eccDNA treatment in BMDMs. The number of genes in each term and the p-value of the enrichment is indicated.

Extended Data Fig. 10.. Analysis of the eccDNA sensing pathway

a, Scatter plot indicates the transcriptomes of the two replicates of synthetic circular DNA treated BMDCs are highly similar. The x and y-axis are log2(FPKM+0.1). b, Western blot confirmation of the Sting−/− and Myd88−/− cells. Blots were performed once, but cell genotypes were further confirmed by mRNA sequences from RNA-seq data (data not shown). c, Correlation of the transcriptomes of 2 replicates eccDNA treated Sting−/− and Myd88−/− BMDC. The x and y-axis are log2(FPKM+0.1).

Fig. 1.. Development of a three-step eccDNA purification procedure

a, Schematic of the three-step eccDNA purification and sequencing procedure. Step 1, extract crude DNA circles from whole cells in a buffered alkaline lysis and bound to silica column; Step 2, linearize mtDNA by PacI and reduce overall linear DNA level with P.S. DNase; Step 3, Selectively recover eccDNAs by excluding residual linear DNA in Solution A; Step 4, sequence eccDNAs by Oxford Nanopore (left) following RCA or by Illumina after Tn5 tagmentation on eccDNAs (right). b, Agarose gel showing eccDNAs purified from over-confluent HeLa without (−) or with (+) PacI treatment. Mt: mtDNA, M, linear DNA maker. c, EccDNAs in (b) scanned with atomic force microscope (SAFM). d, Agarose gel showing eccDNAs purified from normal cultured mESCs. Red arrow heads indicate distinct DNA bands. e, EccDNAs in (d) by SAFM. Representative gels are shown from three independent experiments (b and d); two representative fields are shown, black bars = 200 nm in (c and e).

Fig. 2.. EccDNAs are circularized genomic DNA fragments that mapped across the genome

a, Integrative Genomics Viewer (IGV) showing eccDNA examples from two genomic loci on chromosome 18 and 17. Individual horizontal bars in identical color represent sub-reads from a unique nanopore long read that was repeatedly aligned to the same genomic locus (loci). ecc-1, ecc-2 and ecc-4 are single-fragment circles; ecc-1 partially overlaps with ecc-2; ecc-4 partially overlaps with one fragment of ecc-3, is a two-fragment circle (2f ecc) aligned to two loci on chr18 and chr17, respectively. b, Histogram showing the eccDNA size distribution and relative abundance. c, Pie chart showing the percentages of eccDNA with the indicated event number in the total unique eccDNAs identified. d, Bar graph showing eccDNA counts with the number of fragments (1–7) in each circle. e, Circle plot showing chromosomal origin of all 2 fragments eccDNAs (2f ecc). Fragments from the same chromosome are in the same color. f, Overall chromosomal distribution of eccDNAs across the genome.

Fig. 3.. Apoptotic DNA fragmentation and subsequent ligation by Lig3 is required for eccDNA production in mESCs

a-b, EccDNA production is induced by apoptosis. mESCs were treated with the indicated apoptosis inducers, and total DNA (a) and eccDNAs (b) were purified. DMSO: Dimethylsulfoxide; STS: Staurosporine; ETO: etoposide; UV: ultraviolet. c-d, Deficiency of oligonucleosomal DNA fragmentation abolishes apoptosis induced eccDNA production. Deficiency of DNase 𝛾^−/−, but not EndoG^−/−, abolishes UV-induced oligonucleosomal DNA fragmentation (c), and eccDNA production (d) in mESCs. MtDNA was kept as an inner control. e, Confirmation of DNA ligases deficient cell lines. Up, immunoblotting confirming knockout of DNA ligases in CH12F3 cell lines. Bottom, genomic structure of Lig3 with CRISPR/Cas9 specific targeting (Δ) NucLig3 but retaining MtLig3 for cell viability. f-g, Lig3 is the major DNA ligase for eccDNA generation. Staurosporine induced oligonucleosomal DNA fragmentation (f) and eccDNA (g) from the indicated CH12F3 cell lines. Amount of input cells, elution and loading volume were equal among samples within each agarose gel (a-d, and f-g). Shown are representatives of three independent experiments.

Fig. 4.. EccDNAs are potent immunostimulants

a, EccDNAs induce IFN-α and IFN-β expression in BMDCs. Equal amount of the indicated DNA were transfected to BMDC at increasing concentrations for RT-qPCR analysis. Data are presented as relative mRNA fold change (y-axis) to that in mock transfection (without DNA). Li-DNA: sonicated genomic linear DNA with sizes similar to that of eccDNAs; poly(dG:dC), poly(deoxyguanylic-deoxycytidylic). b, ELISA analysis of IFN-α and IFN-β production in medium from (a). c, Confirming eccDNA linearization. Representative gel shows equal amount of the indicated DNA digested with or without P.S. DNase (P.S.). Li-ecc: linearized eccDNA. d, Linearized eccDNAs lost their immunostimulatory activities. DNA of lanes 1–3 from (c) were transfected to BMDCs at 30 ng/ml and mRNAs were evaluated as in (a). e-f, Synthetic small DNA circles are potent immunostimulants. The same experiments were performed as in (a-b) except the li-DNA and eccDNA were replaced by the synthetic linear (Syn-linear) and circular (Syn-circular) DNAs of the same sequences, mRNA (e) and ELISA (f). g, EccDNAs are present in supernatant of apoptotic medium of WT, but not of DNase γ−/− cells. Representative gel of eccDNA (left) and quantifications (right, n=3); nd, not detected. h, Exonuclease resistant DNA (not mtDNA) in the supernatant of apoptotic medium activate IFN-α and IFN-β. Supernatants of apoptotic medium from WT or DNase γ−/− cells were treated as indicated, then incubated with BMDCs for RT-qPCR analysis as in (a). PacI (for linearizing mtDNA), Benz: Benzonase. Representative data were shown as mean ± SEM of replicates (n=4 per group in a-b, d-f, and h;) of three independent experiments. Statistics were calculated on biological replicates with ordinary one-way ANOVA with Tukey’s multiple comparison test (a-b, d-f, and h) or two-tailed unpaired t tests (g). *, p<0.05; **, p<0.01; ***, p<0.001; ****, p<0.0001; ns, no significant.

Fig. 5.. Sting is required for eccDNA induced gene expression

a, Scatter plot showing 290 genes (left panel, red dots) that are significantly induced by eccDNA, but not linear DNA, in BMDC. 34 significantly induced cytokine genes are indicated (right panel, red dots). FC (fold change). b, Heatmap presentation of the top 20 induced genes. c, GO terms enriched in the genes activated by eccDNA treatment in BMDC. The number of genes in each term and the p-values of the enrichment are indicated. d, Scatter plot indicates that the transcriptomes of BMDC treated with eccDNAs and synthetic circular DNA are highly similar. e, Heatmap presentation of the eccDNA responsive genes in control and eccDNA treated BMDC of the indicated genotypes. f, Scatter plots comparing the transcriptome affected by eccDNA in BMDC from WT, Sting−/−, and Myd88−/− mice. EccDNA responsive genes in WT BMDC are indicated by red dots (up-regulated, n=365) and blue dots (down-regulated, n=79). The x and y-axis are log2-transformed normalized read counts, p-value were generated using DESeq2 and adjusted by IHW(a, d, and f); FC ≥ 5, adjusted p-value < 0.001 in ( a and f); FC ≥ 2, adjusted p-value < 0.01 in (d).