Twin gradients in APOBEC3 edited HIV-1 DNA reflect the dynamics of lentiviral replication

Abstract

The human immunodeficiency virus (HIV) Vif protein blocks incorporation of two host cell cytidine deaminases, APOBEC3F and 3G, into the budding virion. Not surprisingly, on a vif background nascent minus strand DNA can be extensively edited leaving multiple uracil residues. Editing occurs preferentially in the context of TC (GA on the plus strand) and CC (GG) depending on the enzyme. To explore the distribution of APOBEC3F and -3G editing across the genome, a product/substrate ratio (AA + AG)/(GA + GG) was computed for a series of 30 edited genomes present in the data bases. Two highly polarized gradients were noted each with maxima just 5' to the central polypurine tract (cPPT) and LTR proximal polypurine tract (3'PPT). The gradients are in remarkable agreement with the time the minus strand DNA remains single stranded. In vitro analyses of APOBEC3G deamination of nascent cDNA spanning the two PPTs showed no pronounced dependence on the PPT RNA:DNA heteroduplex ruling out the competing hypothesis of a PPT orientation effect. The degree of hypermutation varied smoothly among genomes indicating that the number of APOBEC3 molecules packaged varied considerably.

Figure 1

High-resolution analysis of the hypermutated full-length genome (HVau) compared to its unedited reference sequence (Vau). To reduce noise due to small numbers, a 200 bp non-overlapping window was chosen for analysis. Whether substitutions are normalized to the G (C on the negative strand) content (black), GG + GA (CC + TC, blue, the preferred context for APOBEC3 deamination) twin gradients were always observed. No significant gradient was observed for the GT + GC (AC + GC, red which are avoided by APOBEC3). The proviral form of the sequence is given along with the cPPT and 3′PPTs.

Figure 2

APOBEC3 product/substrate ratio (PS) scans across HIV genomes. (A) PS scans for a collection of 20 unedited HIV-1 M references sequences (Table 1) starting from the beginning of the Gag orf and running through to the U3 and R regions of the LTR. Hence the numbering system is not that of complete HIV sequences. The window length was 600 bp displaced at 50 bp intervals. The peak at ∼5800 corresponds to a known A-rich region centered on the first hypervariable region in the gp120 coding region. (B) PS scan for HVau along with the mean ± 3 SDs clearly shows that all regions of the HVau genome were significantly edited by APOBEC3 molecules albeit to different degrees. The positions of the cPPT and 3′PPT are indicated.

Figure 3

APOBEC3 product/substrate ratio scans for three groups of hypermutated genomes. Given the somewhat irregular PS ratio across the HIV genome (Figure 2A) the mean PS ratios for the reference sequences were subtracted from those of the individual hypermutated sequences, yielding the PS* ratio. (A) A collection of 13 sequences where PS*max <1. The profiles in bold for all four graphs represents the mean + 3 SD derived from the reference sequences. (B) A collection of 13 sequences where 1<PS*max<2. (C) In order to enhance the signal the PS* values of the 13 sequences represented in B) were averaged. (D) A collection of 3 sequences where PS*max>2. Note that the ordinate scale varies for all three graphs. The positions of the cPPT and 3′PPT are given. As the PS* ratio for the interval x→x + 600 bp is reported at position x, the PS* ratio starts to decay at cPPT-600 and 3′PPT-600. Hence the twin gradients do indeed reach maxima just 5′ to the two PPTs. The sharp break in the PS* ratio for six sequences ∼7800 results from their being slightly shorter than the reference sequence set (Figure 5C).

Figure 4

Smooth distribution in the A and G content of HIV-1 M group hypermutated genomes. The increase in A content is strictly related to the depletion of G. The large cross represents the mean (35.6%) for the 20 reference sequences. The two data points for the Vau sequences (HIV-1 O) are displaced towards a lower G content. However, as the gradient is parallel to that for HIV-1 M group sequences, it may be presumed that there is no qualitative difference in the way the hypermutated Vau sequences was edited.

Figure 5

In vitro APOBEC3G editing of nascent HIV PPT cDNA. (A) Cytidine specific deamination frequencies within 338 bp fragment spanning the cPPT. It encodes 83 G(C) residues and is shown with respect to the reference plus strand. The ordinate gives the frequency of editing for every C residue among a collection of 20 clones. The box denotes the PPT sequence while the horizontal bars denote the mean cytidine editing frequency on either side of the PPT. (B) Cytidine specific deamination frequencies within 461 bp fragment spanning the 3′PPT, and comprises a total of 143 G(C) residues. (C) Edited PPT sequences from the two loci shown with respect to the reference sequence. (D) Graphic representation of % site-specific deamination frequencies across the template for 3 and 26 h reactions are plotted on the x and y axes, respectively. The mean site-specific editing frequencies over all sites were 21.9% at 3 h and 53.0% at 26 h. Hence editing was 2.4-fold more extensive after 26 h incubation. As most of the preferred CC and TC targets are >90%, the 26 h reaction showed signs of saturation.

Figure 6

Kinetic model of APOBEC3 editing of nascent HIV-1 DNA. (A) Schematic representation of HIV proviral transcription and the first steps of reverse transcription drawn to scale. PBS, primer binding site; cPPT and 3′PPT, central and 3′ polypurine tracts. (B) The amplitude of cytidine deamination f_c→u is proportional to the time (t) a base remains single stranded. Assuming that the velocities of RNA- and DNA-dependent reverse transcription (V_R and V_D) are constant across the genome, equal access to all sites and a smooth distribution of targets across the sequence, then f_c→u = b[APOBEC3]t = bd(1/V_R + 1/V_D) where d is the distance of any cytidine residue to the downstream PPT, [APOBEC3] is the concentration of APOBEC3 molecules for a single virion, and b is a constant. This reduces to f_c→u = b′d, where b′ is a constant. Given that the maximum values of d are essentially the same, 4.2 and 4.4 kb for the two regions primed by synthesis from the 3′PPT-PBS and cPPT, this results in twin gradients of similar amplitude. The model predicts that the LTR minus strand is lightly edited compared to other parts of the genome. Although very few complete hypermutated LTR sequences exist, two papers reported infrequent editing just 3′ of the 3′PPT (10,30). (C) Linear schematic indicating the lengths and numbers of sequences used in this study.