Massive APOBEC3 editing of hepatitis B viral DNA in cirrhosis

Abstract

DNA viruses, retroviruses and hepadnaviruses, such as hepatitis B virus (HBV), are vulnerable to genetic editing of single stranded DNA by host cell APOBEC3 (A3) cytidine deaminases. At least three A3 genes are up regulated by interferon-alpha in human hepatocytes while ectopic expression of activation induced deaminase (AICDA), an A3 paralog, has been noted in a variety of chronic inflammatory syndromes including hepatitis C virus infection. Yet virtually all studies of HBV editing have confined themselves to analyses of virions from culture supernatants or serum where the frequency of edited genomes is generally low (< or = 10(-2)). We decided to look at the nature and frequency of HBV editing in cirrhotic samples taken during removal of a primary hepatocellular carcinoma. Forty-one cirrhotic tissue samples (10 alcoholic, 10 HBV(+), 11 HBV(+)HCV(+) and 10 HCV(+)) as well as 4 normal livers were studied. Compared to normal liver, 5/7 APOBEC3 genes were significantly up regulated in the order: HCV+/-HBV>HBV>alcoholic cirrhosis. A3C and A3D were up regulated for all groups while the interferon inducible A3G was over expressed in virus associated cirrhosis, as was AICDA in approximately 50% of these HBV/HCV samples. While AICDA can indeed edit HBV DNA ex vivo, A3G is the dominant deaminase in vivo with up to 35% of HBV genomes being edited. Despite these highly deleterious mutant spectra, a small fraction of genomes survive and contribute to loss of HBeAg antigenemia and possibly HBsAg immune escape. In conclusion, the cytokine storm associated with chronic inflammatory responses to HBV and HCV clearly up regulates a number of A3 genes with A3G clearly being a major restriction factor for HBV. Although the mutant spectrum resulting from A3 editing is highly deleterious, a very small part, notably the lightly edited genomes, might help the virus evolve and even escape immune responses.

Figure 1. Transcription profiling of all 11 human cytidine deaminases in cirrhosis.

The A3 transcription data are in the form of box-whisker plots with the mean, quartiles, maxima and minima. Data are normalized to the expression levels of three invariable reference genes (TRIM44, HMBS and LMF2). Asterisks indicate statistically significant up regulation: ** 0.01<p<0.001; * 0.05<p<0.01. Inset) AICDA, APOBEC1 and APOBEC2 transcripts were detected in 0, 1 and 1 HL samples respectively but present in several HBV±HCV samples. APOBEC4 transcripts were undetectable in all samples tested.

Figure 2. AICDA impacts HBV replication by hyperediting the genome.

A) Macroscopic impact of AICDA and A3G on HBsAg secretion into the culture supernatant following transfection of the infectious molecular clone, pCayw. B) 3DPCR recovered A3G- and AICDA-edited HBV genomes down to 86.6°C and 85.2°C respectively. pv: empty plasmid vector and HBV alone. Asterisks refer to the samples cloned and sequenced. C) Mutation matrices for hyperedited X gene sequences derived from cloned 88.7°C 3DPCR products. n indicates the number of bases sequenced. D) Bulk dinucleotide context of HBV X region minus strand DNA by eight human cytidine deaminases. E) Clonal analysis of editing for individual edited sequences. The number of TpC+CpC vs. GpC+ApC targets edited per sequence are computed and represented on the y and x axes respectively. As the A3C and A3G genes were strongly up regulated (Figure 1) they have been separated from the others. Clonal analysis using TpC vs. CpC allows clear isolation of A3G from other A3 enzymes.

Figure 3. A3 deaminases are the major editors of HBV DNA in vivo.

A) PCR and 3DPCR amplification at the normal and restrictive temperatures of 95°C and 88.7°C respectively. Sample codes are given above. Five 3DPCR samples identified by asterisks were chosen for cloning and sequencing. B) Summary of the unique hyperedited sequences in the form of the number and fraction of G→A (minus stand) edits, C→T (plus strand) and all other point mutations. The excess of GC→AT transitions over all other mutations varied from 23–40 fold. C) Clonal analysis using the number of TpC+CpC vs. GpC+ApC targets edited. The vast majority of patient sequences map to the area typical of APOBEC deaminases. D) Clonal analysis using the number of TpC vs. CpC targets edited. The majority of sequences map to the area typical of APOBEC3G (between 57–71% marked in bold face).

Figure 4. High frequency of A3 editing recovered by standard PCR.

A) Frequency analysis of edited genomes as a function of the number of edits per sequence for 95°C derived PCR products. The 268 bp sequences were derived from the first round product. The sequences in insert to Figure 4A were stripped down to the size of the inner 167 bp locus and reanalyzed to allow comparison with the 3DPCR products. The numbers above the columns indicate the combined numbers of sequences across the four samples. B) Frequency distribution of edited sequences for the 3DPCR products obtained at 88.7°C. In order to calculate the bias resulting from PCR close to the denaturation temperature, let's assume that the frequency of clones with 1–17 edited cytidines reflected sub optimal amplification, while the profile in Figure 4A is close to the true distribution. By summing the number of clones with 1–17 and ≥18 edits for Figures 4A and 4B the estimated number with between 1–17 edits in Figure 4B is n, where 79/n = 7/300; n = 3386. As the number of clones in Figure 4B with 1–17 edits is 284, 3DPCR underestimates the true frequency by a factor of 3386/284, or ∼12. C) Bulk dinucleotide analysis of the 95°C sequences harbouring 1, 2–4 and ≥5 G→A transitions reveals the CpC hallmark of A3G editing. D & E) Clonal analysis reveals that editing was due to an APOBEC deaminase, approximately half being due to A3G. The smaller number of sequences used (n = 40) in these figures means that the values of 55% and 45% are less robust than for Figure 3C & 3D. F) 3DPCR amplification across a 85–93°C gradient using either Taq or Pfu DNA polymerase, the latter fails to amplify DNA containing dU, the product of A3 deamination. Asterisks indicate the PCR products cloned and sequenced. G) Mutation matrices of Pfu and Taq amplified HBV hypermutants given as percentages.

Figure 5. A3 editing of the precore and HBsAg coding regions.

A) Site specific frequency analysis of A3G editing in the precore region from a tissue culture transfection experiment and from patient #326 recovered by 3DPCR at the restrictive temperature of 85.5°C. B) A selection of edited precore sequences in vivo. C) Correlation of G→A and C→T edited sites observed from the 95°C amplifications of samples #203, #318, #326 and #372 with those described from other studies with respect to the RNA stem loop structure implicit to DNA replication. D) Secondary structure of the common “a” determinant of HBsAg. The frequent G145R substitution and the G145R variant are noted along with the corresponding codon changes. E) A selection of A3 edited S region sequences bearing mutations in the G145 codon (standard PCR (95°C)). Such sequences represent <10% of the total.