Mining the antibodyome for HIV-1-neutralizing antibodies with next-generation sequencing and phylogenetic pairing of heavy/light chains

Abstract

Next-generation sequencing of antibody transcripts from HIV-1-infected individuals with broadly neutralizing antibodies could provide an efficient means for identifying somatic variants and characterizing their lineages. Here, we used 454 pyrosequencing and identity/divergence grid sampling to analyze heavy- and light-chain sequences from donor N152, the source of the broadly neutralizing antibody 10E8. We identified variants with up to 28% difference in amino acid sequence. Heavy- and light-chain phylogenetic trees of identified 10E8 variants displayed similar architectures, and 10E8 variants reconstituted from matched and unmatched phylogenetic branches displayed significantly lower autoreactivity when matched. To test the generality of phylogenetic pairing, we analyzed donor International AIDS Vaccine Initiative 84, the source of antibodies PGT141-145. Heavy- and light-chain phylogenetic trees of PGT141-145 somatic variants also displayed remarkably similar architectures; in this case, branch pairings could be anchored by known PGT141-145 antibodies. Altogether, our findings suggest that phylogenetic matching of heavy and light chains can provide a means to approximate natural pairings.

Fig. 1.

Identification of somatic variants of antibody 10E8 by next-generation sequencing and grid sampling. (A) 10E8 identity/divergence plots of donor N152 heavy-chain antibodyome (Left) with grid sampling (Right). Identity to 10E8 is shown on the vertical axis, and divergence from germ-line V gene origin is plotted on the horizontal axis, with frequency of antibodies shown as a heat map. Grid sampling is shown, with selected antibodies that either did not express or bind to MPER as open circles and selected antibodies that did bind as solid circles colored according to their phylogenetic distance from 10E8 in C. (B) 10E8 identity/divergence plots of donor N152 light-chain antibodyome (Left) with grid sampling (Right). Axes and coloring are the same as in A except for the open red circle, which represents an antibody that failed to express at the 250-mL scale. (C and D) Phylogenetic trees of grid-identified variants for heavy chain in C and light chain in D. (E and F) 10E8 and 10E8 variant neutralization of six HIV-1 isolates assessed in duplicate for heavy-chain variants, E, and light-chain variants, F. The average IC₅₀ values of gVRC-H1_dN152:10E8L and gVRC-H11_dN152:10E8L were roughly sixfold improved over the original template 10E8. Variants are arranged and named by their genetic distance from 10E8, and colored relative to their phylogenetic segregation. Horizontal bars represent median IC₅₀ values for each variant. Bars representing 0.01 changes per nucleotide site are shown.

Fig. 2.

Sequences and modeled structures of 10E8 variants that neutralize HIV-1. (A) Heavy-chain sequences. Sequences are arranged by genetic distance from 10E8 and colored according to their phylogenetic segregation, with sequence changes from 10E8 highlighted in red. Framework and CDR residues are labeled along with residues that interact with the gp41 MPER epitope (open circle, main chain interactions; open circle with rays, side chain interactions; solid circle, both main chain and side chain interactions). (B) Modeled structures of heavy-chain variants in complex with gp41 epitope. The most potent neutralizers from each 10E8 phylogenetic heavy chain subgroup (with heavy chains colored according to phylogenetic segregation as in Fig. 1B) were threaded onto the structure of WT 10E8 in complex with the MPER region of HIV-1 gp41 (yellow). Structures are displayed as Cα-ribbons, with amino acid side chains that vary from WT 10E8 highlighted in red stick representation. (C) Light-chain sequences. Sequences are arranged by genetic distance from 10E8 and colored according to their phylogenetic segregation, with sequence changes from 10E8 highlighted in red. Framework and CDR residues are labeled along with residues that interact with the gp41 MPER epitope (as described in A). (D) Modeled structures of light-chain variants in complex with gp41 epitope. The most potent neutralizers from each 10E8 phylogenetic light-chain subgroup (with light chains colored according to phylogenetic segregation as in Fig. 1D) were threaded onto the structure of WT 10E8 in complex with the MPER region of HIV-1 gp41 (yellow). Structures are displayed as Cα-ribbons, with amino acid side chains that vary from 10E8 highlighted in red stick representation.

Fig. 3.

Pairing of phylogenetic branches of heavy- and light-chain variants of 10E8. (A) Phylogenetic branch matching. From the phylogenetic trees of grid-identified antibodies (Fig. 1 C and D), branches were named based on phylogenetic distance from 10E8 (b1-H for heavy and b1-L for light for the branch containing 10E8) and in descending order [b2-H (b2-L), b3-H (b3-L), and b4-H for the farthest branch]. The variant from each branch that displayed the most potent neutralization (lowest median IC₅₀) with a 10E8 WT partner (Fig. 1 E and F) was chosen, and a full matrix of 12 antibodies was reconstituted. (B) HIV-1 neutralization. Neutralization was assessed on six isolates for 10E8 variants from matched and mismatched branch pairings. (C) HEp-2 epithelial cell staining. Autoreactivity was assessed with HEp-2 epithelial cell staining for 10E8 variants from matched and mismatched branch pairings. The dotted line represents the threshold for autoreactivity; HEp-2 epithelial cell staining scores below 1.0 are not considered autoreactive. Measurements were made at antibody concentrations of 25 and 50 μg/mL, as indicated. P value, 0.049 in this case, based on comparison of autoreactivity between matched and mismatched antibodies when both 25- and 50-μg/mL data are used in a two-way ANOVA.

Fig. 4.

Phylogenetic trees of PGT141–145 somatic variants from donor IAVI 84. Maximum likelihood trees of sequences identified by intradonor phylogenetic analysis from donor IAVI 84, along with five known antibodies from this donor (PGT141–145), are rooted by their respective germ-line genes for both heavy chains (A) and light chains (B). Bars representing 0.01 changes per nucleotide site are shown.