Newly designed amplicons-based method for near-full-length genome (NFLG) sequencing of HIV-1 group M recombinant forms

Abstract

Background: Over the years the spread of HIV-1 across the globe resulted in the creation of multiple subtypes and new recombinant forms (RFs). While the pol gene region of the HIV-1 genome is used for resistance mutations analysis and initial detection of RFs, whole genome sequencing analysis is required to determine recombination events across the viral genome. Here, we present a newly designed robust near-full length genome (NFLG) sequencing approach for the sequencing of HIV-1 genomes, out of clinical whole blood samples. This method has been successfully tested for various HIV-1 subtypes and RFs.

Methods and results: The method is based on an in-house developed set of 32 pan-genotypic primer pairs, divided into two pools, each containing 16 primer pairs covering the entire HIV-1 genome. Two parallel multiplex PCR reactions were used to generate 32 overlapping DNA fragments spanning the HIV-1 genome. Nextera XT protocol was used to obtain barcoded DNA libraries, which were sequenced with the Illumina Miseq platform using a V3 kit. A consensus sequence was determined for each sample and was used to define recombination events across the genome. For this aim, a combined analysis of several computational tools including HIV BLAST, phylogenetic analysis, RIP, SimPlot + + and jpHMM were employed. Overall, plasma samples from 33 patients suspected to carry RFs and 2 different, known pure subtypes controls, were included in this study. Genome coverage varied between RFs, while the gag and pol genes were nearly fully covered, the highly variable env gene region was not. Yet, these NFLG analyses enabled the identification of recombination events genome wide.

Conclusions: In summary, we describe a methodology for HIV-1 NFLG sequencing, which is based on partially overlapping, multiple PCR fragments, spanning the HIV-1 genome. Additionally, this newly refined method was compared to HIV-1 NFLG results of PCR-free metagenomic sequencing and proved to obtain greater coverage of the HXB2 reference genome. Yet, further testing and validation on a larger cohort is required. Still, this method enables sequencing of 20 different patient samples in a single MiSeq sequencing run and was used for the characterization of different HIV-1 RFs and pure subtypes circulating in Israel.

Keywords: Circulating recombinant forms (CRFs); HIV; HIV near-full length genome (NFLG) sequencing; HIV-1; Illumina miseq; Metagenomics; Next generation sequencing (NGS).

Fig. 1

Schematic mapping of the primers covering HIV-1 HXB2 genome. The general outline of the primers across the HIV-1 reference HXB2 genome designed using primal-scheme [9] is shown. The primer positions are colored in bright red; the amplicons are shown in darker shaded red. The pink line under the genomic location represents the GC content of the corresponding genomic region

Fig. 2

Comparison of HIV-1 HXB2 genome coverage between the newly designed amplicons method and metagenomics. Values (Y-axis) represent normalized number of reads mapped to the corresponding base position in the HXB2 genome (X-axis). Y-axis directionality ( +) for Amplicons and (-) for Metagenomics has no mathematical meaning and was plotted for comparison of each genomic position between the two methods. In the middle of each plot the HXB2 genome map is depicted with genomic regions/genes as follows: 5’LTR, gag, pol, vif, vpr, vpu, env, nef, 3’ LTR

Fig. 3

Reads down-sampling analysis for establishing the optimal number of reads needed to allocate for each sample. The blue lines correspond to the Y-axis on the left, representing HXB2 genome precent coverage. The red lines correspond to the Y-axis on the right corresponding to the mean sequence depth (in number of reads). The X-axis are the number of reads (K = thousand, M = million) randomly sampled. For each one of the 10 samples analyzed, a shape was assigned as shown on the grey legend, also in the legend in parenthesis next to sample number is the assigned HIV-1 subtype. The top blue line with diamond shape corresponds to sample 88,192 of HIV-1 subtype B, while bottom blue line with triangle shape corresponds to sample 69,734 of HIV-1 subtype C and A1. In the plot X-axis, the TOTAL average number of mapped paired-end reads was 1,095,890 and varied by samples and subtypes