Multiple, linked human immunodeficiency virus type 1 drug resistance mutations in treatment-experienced patients are missed by standard genotype analysis

Abstract

To investigate the extent to which drug resistance mutations are missed by standard genotyping methods, we analyzed the same plasma samples from 26 patients with suspected multidrug-resistant human immunodeficiency virus type 1 by using a newly developed single-genome sequencing technique and compared it to standard genotype analysis. Plasma samples were obtained from patients with prior exposure to at least two antiretroviral drug classes and who were on a failing antiretroviral regimen. Standard genotypes were obtained by reverse transcriptase (RT)-PCR and sequencing of the bulk PCR product. For single-genome sequencing, cDNA derived from plasma RNA was serially diluted to 1 copy per reaction, and a region encompassing p6, protease, and a portion of RT was amplified and sequenced. Sequences from 15 to 46 single viral genomes were obtained from each plasma sample. Drug resistance mutations identified by single-genome sequencing were not detected by standard genotype analysis in 24 of the 26 patients studied. Mutations present in less than 10% of single genomes were almost never detected in standard genotypes (1 of 86). Similarly, mutations present in 10 to 35% of single genomes were detected only 25% of the time in standard genotypes. For example, in one patient, 10 mutations identified by single-genome sequencing and conferring resistance to protease inhibitors (PIs), nucleoside analog reverse transcriptase inhibitors, and nonnucleoside reverse transcriptase inhibitors (NNRTIs) were not detected by standard genotyping methods. Each of these mutations was present in 5 to 20% of the 20 genomes analyzed; 15% of the genomes in this sample contained linked PI mutations, none of which were present in the standard genotype. In another patient sample, 33% of genomes contained five linked NNRTI resistance mutations, none of which were detected by standard genotype analysis. These findings illustrate the inadequacy of the standard genotype for detecting low-frequency drug resistance mutations. In addition to having greater sensitivity, single-genome sequencing identifies linked mutations that confer high-level drug resistance. Such linkage cannot be detected by standard genotype analysis.

FIG. 1.

Phylogenetic analysis of patient HIV sequences. Phylogenetic trees of aligned sequences obtained by SGS from patients enrolled in the AIDS Clinical Trials Group study 398 (A) or the NIH clinic (B) were determined by using the neighbor-joining distance method, as implemented in the molecular evolutionary genetics analysis package (http://www.megasoftware.net). Patient identification is shown next to each group of sequences analyzed. All sequences containing resistance mutations (as defined in the Stanford database) that were identified by SGS but not found in the standard genotype were included in the analysis and are shown by filled circles. Four other sequences, which did not contain unique mutations, were chosen at random from each patient and are represented by open circles.