Inference of the HIV-1 VRC01 Antibody Lineage Unmutated Common Ancestor Reveals Alternative Pathways to Overcome a Key Glycan Barrier

Abstract

Elicitation of VRC01-class broadly neutralizing antibodies (bnAbs) is an appealing approach for a preventative HIV-1 vaccine. Despite extensive investigations, strategies to induce VRC01-class bnAbs and overcome the barrier posed by the envelope N276 glycan have not been successful. Here, we inferred a high-probability unmutated common ancestor (UCA) of the VRC01 lineage and reconstructed the stages of lineage maturation. Env immunogens designed on reverted VRC01-class bnAbs bound to VRC01 UCA with affinity sufficient to activate naive B cells. Early mutations defined maturation pathways toward limited or broad neutralization, suggesting that focusing the immune response is likely required to steer B cell maturation toward the development of neutralization breadth. Finally, VRC01 lineage bnAbs with long CDR H3s overcame the HIV-1 N276 glycan barrier without shortening their CDR L1, revealing a solution for broad neutralization in which the heavy chain, not CDR L1, is the determinant to accommodate the N276 glycan.

Keywords: B lymphocytes; HIV-1; cell lineage; clonal evolution; glycans; immunogen design; indel mutation; monoclonal antibody VRC01; neutralizing antibodies; vaccines.

Graphical abstract

Figure 1

VRC01 UCA IgH and IgL Amino Acid Sequences Differed from Those of VRC01 Lineage GL Antibodies (A) VRC01 UCA IgH (top) and IgL (bottom) aa sequences numbered according to the Kabat system (Kabat et al., 1991). (B) Ig heavy (top) and light (bottom) chain alignment of VRC01 UCA to VRC01 lineage GL mAbs. The sequence of the mature VRC01 bnAb is shown as reference and mature VRC01 residues involved in interactions with gp120 Env (Zhou et al., 2010) are indicated with closed circle. (C) VRC01 UCA CDR H3 aa sequence (positions 95 through 102) aligned to CDR H3s of VRC01 lineage GL mAbs. Cysteines shown in green shade. Differences in CDR H3 length, indels, and aa identity to VRC01 UCA are shown on the right. See also Figure S1.

Figure 2

VRC01 UCA Bound to Immunogens Designed of GL VRC01-Class mAbs (A) VRC01 UCA (red) and GL VRC01-class mAbs (black) dissociation constants against six immunogens. Each data point shows the average of at least duplicate experiments. mAbs that did not display measurable binding are shown with K_D > 100 μM. (B) On-rates (x-axis) and off-rates (y-axis) for the same mAbs and immunogens. Only mAbs with K_D < 100 μM are shown. (C) B cell activation mediated by immunogens (red) measured by calcium flux (y-axis) on Ramos B cells expressing VRC01 UCA IgM BCR over 300 s (x-axis). Immunogen mutants with either D279K/D368R or D268R/E370A double mutation are shown in black (“KO mutants”). For the GT1 trimer, BG505 SOSIP was used as KO mutant. Results are expressed as percentage of the maximum signal obtained with an anti-IgM F(ab)₂ antibody and are representative of at least duplicate experiments. (D) Binding of monomeric (left), heptameric (middle), and icositetrameric (right) TM4ΔV1-3 core (green) and eOD-GT8 (blue) to VRC01 UCA IgG. KO mutants are shown with dotted lines. Results are representative of duplicate experiments. See also Table S1, Figures S2 and S3.

Figure 3

VRC01 Phylogeny from the VRC01 UCA Detailed the Maturation Pathways of VRC01 Lineage Antibodies VRC01 phylogeny reconstructed from 45 mAbs with natural paired IgH and IgL sequences. Inferred maturation intermediate antibodies IA1 through IA6 are colored based on clade membership (right). Indels (aa) are mapped on the tree. Units of branch-length estimates are nt substitutions per site.

Figure 4

CDR H3 and CDR L1 Maturation Was Divergent across VRC01 Lineage Clades Alignment of CDR H3 (left) and CDR L1 (right) aa sequences of the observed VRC01 lineage mAbs to the VRC01 UCA sequence (green). Sequences are grouped by clade and subclade membership. mAbs are listed by their respective sequences. mAbs with sequences that clustered outside their subclade membership are indicated with an asterisk.

Figure 5

VRC01+07 and VRC08 Clade Antibodies Acquired Broad Neutralization whereas VRC03+06 Antibodies Displayed Limited Neutralization Breadth (A) Neutralization was measured against the 12-virus global panel and expressed as percentage (y-axis). mAbs were grouped by clade membership: 16 in clade 03+06, 4 in clade 08, and 23 in clade 01+07. Subclade 06 mAbs are shown as clear dots. Lines indicate geometric mean. Results are representative of duplicate observations. Significance was evaluated using Kruskal-Wallis and Dunn’s multiple comparisons tests at the alpha 0.05 level. (B) Neutralization potency (IC₅₀) expressed in μg/mL (y-axis). Differences in potency across clades were not statistically significant. See also Tables S2 and S3.

Figure 6

Heavy Chain, Not CDR L1, Is the Determinant to Accommodate the N276 Glycan in VRC08 bnAb and Initiate Breadth (A) Superposition of the VRC08 structure onto the JRFL SOSIP structure in complex with VRC01. Coloring scheme is as follows: heavy chain (blue), light chain (gray), CDR H3 (red), CDR H3 contact surface (cyan), gp120s (green shades), and gp41s (orange shades). Glycans are shown in stick representation. The N301 glycan was removed from the view for clarity. (B) Structure of VRC01 in complex with JR-FL SOSIP used to superpose VRC08, with same color scheme of (A). (C) Heat map analysis of neutralization data of VRC01 UCA, VRC08_H/UCA_L chimera, and mature VRC08 bnAb (columns) against the 426c wild-type HIV-1 strain and its N276D mutant (in which the potential N-linked glycosylation site at position 276 was abrogated) and the 12-virus global panel. MLV-SVA is shown as negative control. Neutralization potency IC₅₀ is expressed in μg/mL and coloring ranges from white (>50 μg/mL) to dark red (<0.023 μg/mL). Results are representative of at least duplicate experiments. See also Figure S4, Videos S1 and S2.

Figure 7

Lack of Relationship between Auto- and Polyreactivity and Neutralization Breadth in Mature VRC01 Lineage bnAbs (A) UBE3A reactivity (red), polyreactivity (blue), and anti-nuclear antigens (ANA) autoreactivity are shown for each mAb. (B and C) Neutralization breadth (B) and potency (C) of non-auto-/polyreactive (n = 9) and auto-polyreactive (n = 34) antibodies as defined in (A). Significance was evaluated with the Mann-Whitney U test at the alpha 0.05 level. (D and E) Lack of correlation between neutralization breadth (D) or potency (E) and polyreactivity. See also Figures S5 and S6.