Exonuclease removal of dideoxycytidine (zalcitabine) by the human mitochondrial DNA polymerase

Abstract

The toxicity of nucleoside analogs used for the treatment of human immunodeficiency virus infection is due primarily to the inhibition of replication of the mitochondrial genome by the human mitochondrial DNA polymerase (Pol gamma). The severity of clinically observed toxicity correlates with the kinetics of incorporation versus excision of each analog as quantified by a toxicity index, spanning over six orders of magnitude. Here we show that the rate of excision of dideoxycytidine (zalcitabine; ddC) was reduced fourfold (giving a half-life of approximately 2.4 h) by the addition of a physiological concentration of deoxynucleoside triphosphates (dNTPs) due to the formation of a tight ternary enzyme-DNA-dNTP complex at the polymerase site. In addition, we provide a more accurate measurement of the rate of excision and show that the low rate of removal of ddCMP results from both the unfavorable transfer of the primer strand from the polymerase to the exonuclease site and the inefficient binding and/or hydrolysis at the exonuclease site. The analogs ddC, stavudine, and ddATP (a metabolite of didanosine) each bind more tightly at the polymerase site during incorporation than normal nucleotides, and this tight binding contributes to slower excision by the proofreading exonuclease, leading to increased toxicity toward mitochondrial DNA.

FIG. 1.

Exonuclease removal of dCMP with primers with or without frayed termini. The wild-type holoenzyme (100 nM) was preincubated with 90 nM 26-mer-45-mer terminated with dCMP correctly base paired (○) or frayed at the 3′ terminus (eight mismatches; •) and mixed with Mg²⁺ to start the reaction. The concentration of the substrate (26-mer primer) as a function of time was fit to a double exponential equation. Reactions of both the correctly base paired and frayed DNA were biphasic. The correctly paired dCMP DNA was excised at rates of 0.86 ± 0.35 s⁻¹ and 0.016 ± 0.004 s⁻¹ with amplitudes of 21 ± 3 nM and 70 ± 3 nM, respectively. The frayed dCMP-terminated DNA was excised at rates of 1.6 ± 0.5 s⁻¹ and 0.1 ± 0.07 s⁻¹ with amplitudes of 60 ± 10 nM and 25 ± 10 nM, respectively.

FIG. 2.

Exonuclease removal of ddCMP primers with or without frayed termini. The wild-type holoenzyme (100 nM) was preincubated with 90 nM 26-mer-45-mer terminated with ddC correctly base paired (○) or frayed at the 3′ terminus (eight mismatches; •) and mixed with Mg²⁺ to start the reaction. The concentration of the substrate (26-mer primer) as a function of time was plotted and fit to a single exponential equation. The reactions were not double exponentials as in Fig. 1 and were dramatically slower, at a rate of 3 ± 0.4 × 10⁻⁴ s⁻¹ for the correctly paired ddC-terminated primer and 4.4 ± 0.5 × 10⁻³ s⁻¹ for the ddC-terminated frayed DNA. Both reactions had full amplitudes of about 90 nM.

FIG. 3.

Exonuclease removal of ddCMP from primer strands with or without frayed termini in the presence of dNTPs. The wild-type holoenzyme (100 nM) was preincubated with 90 nM 26-mer-45-mer terminated with ddC correctly base paired (○) or frayed at the 3′ terminus (eight mismatches; •) and mixed with Mg²⁺ and 100 μM dNTPs to start the reaction. The concentration of the substrate (26-mer primer) as a function of time was plotted and fit to a single exponential equation. The correctly paired ddC-terminated DNA was excised at a rate of 8 ± 0.7 × 10⁻⁵ s⁻¹. The frayed ddC-terminated DNA was excised at a rate of 6.3 ± 0.3 × 10⁻³ s⁻¹. Both reactions had amplitudes of about 90 nM.

FIG. 4.

Overview of rates of exonuclease removal by Pol γ. Shown in the bar graph are the relative rates of exonuclease removal of the eight FDA-approved nucleoside analogs (ddATP [ddA] is the metabolically active form of dideoxyinosine) in addition to the natural nucleotide dCMP (dC). The rate of excision of ddC was obtained in the experiment with a correctly paired DNA substrate and no dNTPs present so that parallel comparisons could be made. The numerical value for the rate of exonuclease removal (s⁻¹) is plotted on the x axis and given below the name of each nucleoside analog. Note that the chemical structures have been abbreviated for clarity and that the only nucleoside analog with a modified nucleobase is (−)FTC, which has fluorine on C-5, denoted in the structure as C5F. The most notable differences between each of the structures are in the ribose ring, and the highest rate of removal is 33-fold higher than the lowest rate. The rates of removal of d4T, AZT, ddATP, PMPA, and CBV are from reference , that of (−)3TC is from reference , and that for (−)FTC is from reference .