Non-catalytic site HIV-1 integrase inhibitors disrupt core maturation and induce a reverse transcription block in target cells

Abstract

HIV-1 integrase (IN) is the target for two classes of antiretrovirals: i) the integrase strand-transfer inhibitors (INSTIs) and ii) the non-catalytic site integrase inhibitors (NCINIs). NCINIs bind at the IN dimer interface and are thought to interfere primarily with viral DNA (vDNA) integration in the target cell by blocking IN-vDNA assembly as well as the IN-LEDGF/p75 interaction. Herein we show that treatment of virus-producing cells, but not of mature virions or target cells, drives NCINI antiviral potency. NCINIs target an essential late-stage event in HIV replication that is insensitive to LEDGF levels in the producer cells. Virus particles produced in the presence of NCINIs displayed normal Gag-Pol processing and endogenous reverse transcriptase activity, but were defective at initiating vDNA synthesis following entry into the target cell. NCINI-resistant virus carrying a T174I mutation in the IN dimer interface was less sensitive to the compound-induced late-stage effects, including the reverse transcription block. Wild-type, but not T174I virus, produced in the presence of NCINIs exhibited striking defects in core morphology and an increased level of IN oligomers that was not observed upon treatment of mature cell-free particles. Collectively, these results reveal that NCINIs act through a novel mechanism that is unrelated to the previously observed inhibition of IN activity or IN-LEDGF interaction, and instead involves the disruption of an IN function during HIV-1 core maturation and assembly.

Figure 1. NCINIs act as late-stage HIV-1 inhibitors.

(A) Schematic overview of the full cycle assay system is shown. Exposure to compounds was limited to the stage of virus production (yellow), target cell infection (green), or both (orange). EC₅₀ values for ATV, RAL, GS-A, and GS-B for WT and T174I-IN mutant virus measured under the three compound exposure conditions are tabulated. Results represent a mean of two independent experiments. nd, not determined. (B) Cell-free virus was incubated with the different classes of inhibitors, and the infectivity was measured before (white bars) and after (gray bars) compound removal via ultrafiltration. Results represent mean ± SD values obtained from triplicate measurements in at least three independent experiments.

Figure 2. NCINI potency is unaffected by LEDGF expression levels during virus production.

(A) Western blot analysis of HEK293T cells overexpressing LEDGF during virus production. (B) Infectivity of virus produced from mock (black bars) and LEDGF overexpressing (light grey bars) HEK293T producer cells. (C) Western-blot analysis of LEDGF expression in HEK293T cells generated from mock transfection or stable transfection with control scrambled or LEDGF-specific shRNAs. (D) Infectivity of virus produced from HEK293T cells that were mock transfected (black bars) or stably transfected with scrambled shRNA (hatched bars) or LEDGF shRNA #8 (white bars) and #3 (grey bars). Infectivity measurements for B and D represent mean ± SD values obtained from triplicate measurements from a representative experiment.

Figure 3. NCINIs do not inhibit Gag-Pol processing, ERT, or target cell entry.

(A) Western blot analysis of purified HIV-1 particles produced in the presence of different inhibitors at 1 µM concentration. Gag/Gag-Pol processing was assessed using anti-CA (upper), anti-IN (middle), and anti-RT antibodies (lower). (B) Equal p24 amounts of virus shown in A were analyzed for virion-associated endogenous reverse transcriptase activity. Values were averaged from duplicate measurements. (C) Percentage of cells positive for beta-lactamase activity following infection with Blam-Vpr complemented HIV-1 produced in the presence of DMSO or 1 µM tested compounds. Values are normalized to DMSO-treated control and represent a mean of two independent experiments performed in duplicate.

Figure 4. Virus produced in the presence of GS-B is defective in vDNA synthesis in target cells.

(A) HIV-1 produced in the presence of DMSO, 1 µM RAL (gray bars), 1 µM GS-B (black bars), or 1 µM EFV (white bars) was used to infect MT-2 cells in the presence of the same respective drugs and assayed by quantitative PCR 12 hours post-infection for early and late reverse transcription products (left panel), and 24 hours post infection for aborted (2-LTR) and completed (Alu-LTR) integration products (right panel). (B) Quantitative PCR assessment of reverse transcription and integration products in MT-2 target cells directly infected with HIV-1 in the presence of 1 µM RAL (gray bars) or 5 µM GS-B (black bars). (C) Quantitative PCR assessment of early RT and late RT product formation in MT-2 cells infected with T174I virus produced and infected in the presence of GS-B (1 µM) or EFV (1 µM). Results in A-C represent mean ± SD values normalized to DMSO (set to 100%) obtained from quadruplicate infections each assayed in duplicate.

Figure 5. NCINIs disrupt normal HIV-1 core formation and architecture.

(A) Representative electron micrograph images illustrating normal, aberrant and immature particle morphologies. Arrows highlight the mislocalized electron-dense ribonucleoprotein complex outside of the capsid shell in many aberrant particles. Frequencies of the different core phenotypes are shown for WT (B) and T174I mutant (C) HIV-1 produced in the presence of DMSO (gray bars) or 1 µM GS-B (black bars). (D) Quantitation of core morphology frequencies for the IN-negative virus. For B–D, data represent mean ± SD, each derived from >1000 particles.

Figure 6. GS-B reduces HIV-1 core yield and content.

Wild-type and T174I mutant HIV-1 was produced in the presence of DMSO or GS-B (1 µM) and fractionated over a detergent-layered sucrose gradient. Eleven 3-mL fractions collected sequentially from the top of each gradient were assayed for density (g/mL), CA/IN/RT proteins, and viral nucleic acid content. (A) Distribution of capsid (p24), the major core protein, in relation to sample density. (B) Viral RNA distribution in the gradient fractions, as determined by quantitative RT-PCR. Results in A & B represent the mean ± SD values obtained from four independently fractionated samples. Arrows highlight NCINI-induced reduction of CA and viral RNA within peak core fraction 10. (C) Western-blot analyses for relative abundance and distribution of IN (p32) and RT (p51/p66) proteins in gradient fractions 6–10.

Figure 7. GS-B enhances IN oligomerization during virus production.

(A) Purified WT or T174I-IN mutant HIV-1 produced in the presence of DMSO or GS-B was briefly treated with cross-linking agent BS3 and the IN monomeric and dimeric forms assessed by anti-IN Western blot analysis. Left, Representative anti-IN Western blot of progeny virus treated with cross-linker. Right, quantitation of monomeric vs dimeric IN forms. (B) Quantitation of IN oligomeric state in progeny virus when virus producer cells vs cell-free virus particles are treated with GS-B (1 µM). Quantitations represent data from individual representative gels.