Membrane-bound mRNA immunogens lower the threshold to activate HIV Env V2 apex-directed broadly neutralizing B cell precursors in humanized mice

Abstract

Eliciting broadly neutralizing antibodies (bnAbs) is the core of HIV vaccine design. bnAbs specific to the V2-apex region of the HIV envelope acquire breadth and potency with modest somatic hypermutation, making them attractive vaccination targets. To evaluate Apex germline-targeting (ApexGT) vaccine candidates, we engineered knockin (KI) mouse models expressing the germline B cell receptor (BCR) of the bnAb PCT64. We found that high affinity of the ApexGT immunogen for PCT64-germline BCRs was necessary to specifically activate KI B cells at human physiological frequencies, recruit them to germinal centers, and select for mature bnAb mutations. Relative to protein, mRNA-encoded membrane-bound ApexGT immunization significantly increased activation and recruitment of PCT64 precursors to germinal centers and lowered their affinity threshold. We have thus developed additional models for HIV vaccine research, validated ApexGT immunogens for priming V2-apex bnAb precursors, and identified mRNA-LNP as a suitable approach to substantially improve the B cell response.

Keywords: B cell receptor; HIV vaccine; V2 apex; antibody; bnAbs; immunization; knockin; mRNA.

Graphical abstract

Figure 1

GT2 immunization activates PCT64 precursor B cells (A) Human PCT64 LMCA IGH (green), murine IGH (dark gray), human PCT64 LMCA IGK (purple) and murine IGK (light gray) sequences amplified from single-cell sorted B220⁺ naive B cells from two PCT64^LMCA mice. n = pairs amplified. See also Figures S1 and S2A–S2D. (B) Representative FACS plots of epitope-specific GT2-positive and GT2-KO-negative peripheral B cells in naive PCT64^LMCA or C57BL/6J mice. Events were pre-gated on lymphocytes/singlets/CD4^-CD8^-F4/80^-Gr1^-/B220⁺ B cells. (C) GT2-specific blood peripheral B cells from PCT64^LMCA and WT C57BL/6J mice (n = 4). Bars are mean ± SD. (D) Human PCT64 LMCA IGH (green), human PCT64 LMCA IGK (purple) and murine IGK (light gray) sequences from single-cell sorted GT2-specific naive B cells in PCT64^LMCA mice (n = 2). n = pairs amplified. (E) Schematic of PCT64^LMCA B cell adoptive transfer and immunization. Experiments performed in triplicate; n = 4. A representative experiment is shown in (F–H). (F) Representative plots of splenic B cells obtained at 8, 16, and 42 dpi with GT2 trimers. Events pre-gated on lymphocytes/singlets/live/CD4^-CD8^-F4/80^-Gr1^-/B220⁺ B cells and represent GC, CD45.1, and CD45.2 cells in GC, and frequency of GT2⁺ CD45.2 cells present in GC. For control groups see Figure S2E. (G) B cell subsets responsive to GT2-immunization at 7, 16, and 42 dpi (n = 4). Left to right: total GCs, CD45.2⁺ B cells in GCs, and GT2-binding CD45.2⁺ B cells. Bars are mean ± SD. p values calculated by Mann-Whitney test, ^∗∗p < 0.01. See also Figure S2E. (H) ELISA quantification of GT2-binding (left) and GT2-KO-binding (right) serum IgG from PCT64^LMCA−HL recipient mice versus WT C57BL/6J mice (n = 4). Line represents mean values. Area under the curve (AUC) was assessed prior to immunization with GT2 trimers and at 7, 14, 21, and 42 dpi.

Figure 2

A single GT2 prime induces antibodies with mature PCT64-like mutations Antigen-specific splenic CD95⁺CD38^low CD45.2⁺ PCT64^LMCA B cells sorted at 8 and 42 dpi for single-cell BCR sequencing. (A) Phylogenetic trees of PCT64^LMCA IGH aa at 42 dpi. (B) Total nt (left) and aa (right) mutations in PCT64^LMCA IGHV and IGKV at 8 and 42 dpi. p values calculated by Mann-Whitney test: ^∗∗p < 0.01, ^∗p < 0.05. (C) HC mutation frequencies per residue observed at 8 (n = 93) and 42 (n = 57) dpi. HCDRs highlighted in gray. Red = present in mature PCT64; blue = present in early PCT64 isolates. aa positions 31, 35, 52B, and 100D analyzed in D. (D) Distribution of selected PCT64^LMCA B cell HC aa mutations in positions 31, 35, 52B, and 1 at 8 and 42 dpi. Red = present in mature PCT64; blue = present in early PCT64 isolates; black = original LMCA aa; gray = all other mutations. See also Figure S2F. (E) Frequencies of LC mutations at each residue 42 dpi (n = 39). LCDRs are highlighted in gray. (F) SPR affinity measurement against GT2 for 14 antibodies isolated at 42 dpi (white, right) compared with PCT64^LMCA (green, left). (G) Full cryo-EM structure of ApexGT2 in complex with GT2-d42.16 and RM20A3 Fabs and close-up of the epitope/paratope region with sites of SHM in yellow. See also Figure S3. (H) Structures of GT2-d42.16 and PCT64^LMCA (dark gray) overlayed showing an identical angle of approach relative to their respective ApexGT trimers. (I) Close up of the HCDR1 (light blue) and 2 domains (dark blue) with H-bonds between the N156gp120A glycan and gp120 residues shown as dashed lines.

Figure 3

PCT64 precursor responses to GT2 are driven by the heavy chain (A) 10x Genomics single-cell BCR sequences from 4703 splenic B cells from a naive PCT64^LMCA−H mouse. Relative bubble size indicates IGHV gene frequency. Human PCT64 IGHV gene frequency in green (82.6%). Murine IGHV genes in various colors. (B) Left: representative fluorescence-activated cell sorting (FACS) plot of GT2-binding and GT2-KO-negative peripheral B cells in naive PCT64^LMCA−H (n = 4). Events were pre-gated on lymphocytes/singlets/CD4⁻CD8^-F4/80^-Gr1^-/B220⁺ B cells. Right: quantification of GT2-specific blood peripheral B cells from PCT64^LMCA−H and C57BL/6J WT mice. Bars are mean ± SD. (C) Paired human PCT64^LMCA IGH (green) and murine IGK (variable) sequences amplified from single-cell sorted GT2-specific naive B cells from PCT64^LMCA−H mice. n = pairs amplified. (D) Murine IGK V genes paired with human PCT64 IGH in a naive PCT64^LMCA−H mouse (n = 3,888). Relative bubble size indicates frequency of IGK V gene usage. Relevant IGK V genes marked in color and analyzed in (E) and (F). See also Figure S4. (E) Murine IGK V genes paired with human PCT64 IGH isolated from GCs at 8 and 42 dpi. Some frequently enriched IGK V genes are highlighted: V2-109 (red), V12-44 (blue), V14-111 (yellow), V4-74 (light green), and V1-135 (teal). See also Figure S5A. (F) SPR affinity against GT2 for 23 antibodies with various murine IGKV pairings isolated from naive PCT64^LMCA−H mice at 42 dpi, compared to human PCT64^LMCA (black, square). (G) Frequencies of IGH aa mutations per residue 42 dpi. HCDRs are boxed in gray. Red = key mutations present in mature PCT64. aa positions 31, 35, 52B, and 100D analyzed in (J). See also Figures S5B–S5E. (H) Distribution of select PCT64^LMCA B cell IGH aa mutations in positions 31, 35, 52B, and 100D at 8 and 42 dpi. Red = present in mature PCT64; blue = present in early PCT64 isolates; black = original LMCA aa; gray = all others.

Figure 4

High affinity GT5 immunogen activates PCT64 precursors at physiological frequencies (A) Schematic of adoptive transfer model to calibrate PCT64^LMCA B cell frequencies. Experiments were performed in duplicate with one presented; n = 5. (B) Gating strategy for titration of cell transfer model. (C) Precursor frequencies (y axis) corresponding to number of B cells transferred (x axis). Bars are mean ± SD. (D) Analysis of linearity of CD45.2 PCT64^LMCA B cells recovered 24 h post transfer. (E) Schematic of immunizations performed at precursor frequencies of 100, 20, and 10 per 10⁶. Experiments were performed in triplicate with one presented; n = 4. (F) Representative FACS plots at 8 dpi with GT, showing CD45.2 GC B cell responses at precursor frequency of 100, 20, and 10 per 10⁶ of B cells. (G) Quantification of GC B cells and CD45.2⁺ PCT64^LMCA cells present in GC at 8 dpi with GT2. Bars are mean ± SD. (H) SPR of PCT64^LMCA for GT2 and GT5 trimers. (I) Representative FACS plots 8 dpi with GT5, showing CD45.2 GC B cell responses at precursor frequency of 100, 20, and 10 per 10⁶ of B cells. (J) Quantification of GC cells and CD45.2⁺ PCT64^LMCA cells present in GC at 8 dpi with GT5 at decreasing precursor frequencies (n = 4 and n = 5 for 10:10⁶). Bars are mean ± SD. See also Figures S5F and S5G. (K) Representative FACS plots at 8, 16, and 42 dpi with GT5, showing CD45.2 GC B cell responses at precursor frequency of 100, 10, and 1 per 10⁶ B cells (n = 4). (L) Quantification of K. Data are represented as mean ± SD. (M) ELISA quantification of GT2-/GT5-binding (top) and GT2-/GT5-KO-binding (bottom) serum IgG from PCT64^LMCA recipient mice compared to WT C57BL/6J mice (n = 4). AUC was assessed prior to immunization by GT2 or GT5 and at 7, 14, 21, and 42 dpi. Points are mean ± SD.

Figure 5

GT5 immunization induces key PCT64-like mutations in IGH (A) Quantification of total nt mutations in PCT64^LMCA IGH and IGK V genes at 42 dpi. Red line = mean. See also Figure S5H. (B) Quantification of total aa mutations in PCT64^LMCA IGH and IGK V genes at 42 dpi. Red line = mean. (C) SPR affinity measurement of antibodies isolated at 42 dpi with GT5 from mice presenting a PCT64 IGH (left) or IGH + IGK (right) (10 precursors per 10⁶). (D) PCT64-like aa mutations in PCT64^LMCA IGHs isolated at 42 dpi. Numbers in each square indicate sequences sharing the total aa mutations (x axis) and the PCT64-like aa mutations (y axis). (E) Frequencies of HC aa mutations per residue at 42 dpi. HCDRs boxed in gray. Red = present in mature PCT64; blue = present in early PCT64 isolates. (F) Frequency of selected PCT64^LMCA B cell HC aa mutations at 42 dpi in HCDR1 positions 28, 31, and 35; in HCDR2 positions 52, 52B, and 52C; in HCDR3 positions 92, 97, 100D, and 100E. Red = present in mature PCT64; blue = present in early PCT64 isolates; black = original PCT64^LMCA aa; gray = all others. (G) Neutralization assay of selected PCT64^LMCA 42 dpi mAbs. The five highest affinity mAbs elicited by ApexGT2 or GT5 were evaluated in addition to PCT64 lineage members and other V2 apex bnAbs. GT5-V2B, BG505.ApexGT5 PSV with loopV2B reverted to BG505 WT; GT5-N167, BG505.ApexGT5 PSV with N167D (BG505 WT has D167); GT5-NR, BG505.ApexGT5 PSV with N167D and R169K (BG505 WT has D167 and K169). Numbers indicate the percentage of neutralization at 10 ug/mL. (H) Cryo-electron microscopy (cryo-EM) structure of ApexGT5 in complex with GT5-d42.16 Fab overlayed with the structure of ApexGT2 in complex with GT2-d42.16 Fab. Sites of SHM are designated in magenta and yellow, respectively. See also Figure S6. (I) Close up of the HCDR1 and 2 domains of both Fabs and their interactions with the N156gp120A glycan and gp120 residues. (J) Low pass filtered ApexGT5 + GT5-d42.16 cryo-EM map (gray) and (ApexGT2 + GT2-d42.16) – (ApexGT5 + GT5-d42.16) difference map (purple) showing the density associated with the N187 glycan and the slight shift in angle of approach of the GT2-d42.16 Fab (arrow). (K) Close up of ApexGT5 loop2B on protomer C showing the cryo-EM map density (transparent gray) that bridges W188 at the tip of the loop and the N160gp120C glycan along with multiple loop models generated from multi-model refinement. (L) All three gp120 protomers of ApexGT5 aligned to one another showing the conformation adopted by the protomer C loop.

Figure 6

GT5 mRNA effectively activates rare precursors (A) Schematic of IM immunization. Mice received either GT5 trimers adjuvanted with SIGMA or GT5 mRNA. Experiments performed in duplicate with one presented; n = 5. (B) Representative FACS plots of LN B cells at 13, 28, and 42 dpi IM with GT5 trimers, and SIGMA adjuvant showing GCs, CD45.2⁺ B cells in GC, and GT5-binding CD45.2 B cells. (C) Quantification of GCs, CD45.2⁺ B cells in GC, and GT5-binding CD45.2 B cells at 13, 28, and 42 dpi IM with GT5 trimers and SIGMA adjuvant (n = 5). Data are represented as mean ± SD. (D) ELISA quantification of GT5-binding (left) and GT5-KO-binding (right) serum IgG from PCT64^LMCA recipient mice immunized with GT5 trimers and SIGMA adjuvant (as in B and C). Line represents mean value. (E) Representative plots of LN B cells at 13, 28, and 42 dpi IM with GT5 mRNA. (F) Quantification of LN GCs, CD45.2⁺ B cells in GC, and GT5-binding CD45.2 B cells at 13, 28, and 42 dpi IM with GT5 mRNA (n = 5). Bars are mean ± SD. (G) ELISA quantification of GT5-binding (left) and GT5-KO-binding (right) serum IgG from PCT64^LMCA recipient mice immunized with GT5 mRNA (as in E and F). Line represents mean value. (H) Representative plots of LN B cells at 13 and 42 dpi IM with GT5 trimers in mice with a starting PCT64 precursor frequency of 10 and 1 per 10⁶ B cells. Plots show the frequency of CD45.2⁺ B cells in GC. Experiments were performed in duplicate with one presented; n = 5. (I) Quantification of GCs, CD45.2⁺ B cells in GC, and GT5-binding CD45.2 B cells at 13 and 42 dpi IM with GT5 trimers in mice with a starting PCT64 precursor frequency of 10 or 1 per 10⁶ B cells. Bars are mean ± SD. (J) Total nt and aa mutations acquired in PCT64^LMCA IGH and IGK V genes at 42 dpi with GT5 mRNA in 2 different mice. Red line indicates mean. (K) Frequencies of IGH aa mutations per residue at 42 dpi. HCDRs boxed in gray. Red = present in mature PCT64; blue = present in early PCT64-lineage isolates.

Figure 7

GT5-mRNA immunization activates a J-region-reverted PCT64 precursor (A) Sequence alignment of the HCDR3 of PCT64^LMCA.JREV, PCT64^LMCA and germline VH3-15, DH3-3 and JH6. (B) Human PCT64 LMCA.JREV HC (teal), murine HC (dark gray), human PCT64^LMCA.JREV IGK (purple) and murine LC (light gray) sequences amplified from single cell sorted B220⁺ naive B cells from two PCT64^LMCA.JREV mice. n = pairs amplified. See also Figures S7A and S7B. (C) SPR affinity measurement against GT5 of LMCA and LMCA.JREV IGH paired with various murine IGK. (D) FACS plots with epitope specific GT2-binding (top) and GT5 binding of peripheral B cells in naive PCT64^LMCA.JREV mouse model. Events were pre-gated on lymphocytes/singlets/CD4⁻CD8^-F4/80^-Gr1^-/B220⁺ B cells. See also Figures S7C–S7F. (E) Schematic of study design. Recipient mice at 100, 20, or 10 PCT64^LMCA.JREV per 10⁶ B cells prior to immunization i.p. with GT5 trimers or IM with GT5 mRNA; responses analyzed 13 dpi. Experiments performed in triplicate with one presented; n = 4 or 5. See also Figures S7G and S7H. (F) Representative FACS plots of GCs, CD45.2 PCT64^LMCA.JREV present in GC, and GT5 specific responses at 13 dpi after immunization with GT5 protein i.p. (pink) or GT5 mRNA IM (teal). Spleen were analyzed for i.p. responses and inguinal LN for IM responses. (G) Quantification of responses in GCs as in (E) and (F) (n = 4 or 5). Bars are mean ± SD. (H) Quantification of GC responses, frequency of CD45.2 PCT64^LMCA.JREV B cells in GC and GT5 specific responses at 42 dpi (n = 5). Bars are mean ± SD.