Comparison of a high-resolution melting assay to next-generation sequencing for analysis of HIV diversity

Abstract

Next-generation sequencing (NGS) has recently been used for analysis of HIV diversity, but this method is labor-intensive, costly, and requires complex protocols for data analysis. We compared diversity measures obtained using NGS data to those obtained using a diversity assay based on high-resolution melting (HRM) of DNA duplexes. The HRM diversity assay provides a single numeric score that reflects the level of diversity in the region analyzed. HIV gag and env from individuals in Rakai, Uganda, were analyzed in a previous study using NGS (n = 220 samples from 110 individuals). Three sequence-based diversity measures were calculated from the NGS sequence data (percent diversity, percent complexity, and Shannon entropy). The amplicon pools used for NGS were analyzed with the HRM diversity assay. HRM scores were significantly associated with sequence-based measures of HIV diversity for both gag and env (P < 0.001 for all measures). The level of diversity measured by the HRM diversity assay and NGS increased over time in both regions analyzed (P < 0.001 for all measures except for percent complexity in gag), and similar amounts of diversification were observed with both methods (P < 0.001 for all measures except for percent complexity in gag). Diversity measures obtained using the HRM diversity assay were significantly associated with those from NGS, and similar increases in diversity over time were detected by both methods. The HRM diversity assay is faster and less expensive than NGS, facilitating rapid analysis of large studies of HIV diversity and evolution.

Fig 1

Diversity data collected from a representative study participant. Neighbor-joining trees of HIV GAG and ENV next-generation consensus sequences from one individual at two time points are shown. The number of sequence reads included in each consensus sequence is shown at the end of the sequence, following an underscore. Subtype reference sequences and random sequences from unrelated individuals in Rakai are included. The diversity measures associated with both time points and regions are shown in the table below the trees. Note that this participant is infected with an A/D recombinant strain of HIV (A in env, D in gag).

Fig 2

HRM scores and sequence-based diversity measures increase over time after infection. HRM scores and sequence-based diversity measures (percent diversity, percent complexity, and Shannon entropy) increased for both GAG (A, B, C, and D) and ENV (E, F, G, and H) over time from seroconversion. Univariate logistic regression analysis was used to calculate the mean longitudinal change (solid line) with 95% confidence intervals (dotted lines).