Functional characterization of two scFv-Fc antibodies from an HIV controller selected on soluble HIV-1 Env complexes: a neutralizing V3- and a trimer-specific gp41 antibody

Abstract

HIV neutralizing antibodies (nAbs) represent an important tool in view of prophylactic and therapeutic applications for HIV-1 infection. Patients chronically infected by HIV-1 represent a valuable source for nAbs. HIV controllers, including long-term non-progressors (LTNP) and elite controllers (EC), represent an interesting subgroup in this regard, as here nAbs can develop over time in a rather healthy immune system and in the absence of any therapeutic selection pressure. In this study, we characterized two particular antibodies that were selected as scFv antibody fragments from a phage immune library generated from an LTNP with HIV neutralizing antibodies in his plasma. The phage library was screened on recombinant soluble gp140 envelope (Env) proteins. Sequencing the selected peptide inserts revealed two major classes of antibody sequences. Binding analysis of the corresponding scFv-Fc derivatives to various trimeric and monomeric Env constructs as well as to peptide arrays showed that one class, represented by monoclonal antibody (mAb) A2, specifically recognizes an epitope localized in the pocket binding domain of the C heptad repeat (CHR) in the ectodomain of gp41, but only in the trimeric context. Thus, this antibody represents an interesting tool for trimer identification. MAb A7, representing the second class, binds to structural elements of the third variable loop V3 and neutralizes tier 1 and tier 2 HIV-1 isolates of different subtypes with matching critical amino acids in the linear epitope sequence. In conclusion, HIV controllers are a valuable source for the selection of functionally interesting antibodies that can be selected on soluble gp140 proteins with properties from the native envelope spike.

Figure 1. Characterization of soluble lectin purified ADA.C1 gp140 glycoproteins.

(A) Western blot detecting ADA.C1 Env glycoprotein with anti V3 mAb 447-52D and trimer-specific mAb Md-1. CHO-neg corresponds to the supernatant of CHO cells transfected with empty vector and used as negative control for biopanning. (B) Binding of various mAbs directed against linear and conformational Env epitopes and HIV-positive sera to immobilized ADA.C1 determined by ELISA. Each sample was tested in duplicates and error bars represent standard deviations of the mean.

Figure 2. Recognition of Env proteins from different constructs by the selected scFv.

(A) Binding of the two antibody classes scFv A7 and A2 to gp140 and gp120 Env proteins determined by ELISA. Detection was with anti c-myc antibody (300 ng/well) and HRP conjugated anti-mouse antibody (1∶1,000). (B) Reactivity of scFv-Fc A2 with SDS and DTT treated and non-treated gp41 Env proteins by ELISA. Each sample was tested in triplicates and error bars represent standard deviations of the mean. Significance analysis was performed with two way ANOVA Tukeýs multiple comparison test. (D) Immunoprecipitation of gp140 ADA.C1 protein from culture supernatants on scFv A2 coupled beads. Fractions of scFv A2 and gp140 flow through (FT), washing (W1-W4), elution (E1–E3) and control resin were analyzed by Western blot with HIV-positive serum (upper panel) and trimer-specific mAb Md-1 (lower panel).

Figure 3. Recognition of native gp160 JR-FL Env on cells.

Binding of scFv-Fc A2 and A7 as well as control antibodies to 293T cells transfected with JR-FL Env (black) or mock transfected (gray) by FACS analysis. Detection of bound antibodies was with a PE labeled secondary anti-human IgG antibody. Percent PE-positive cells are shown together with the secondary antibody only control. Each antibody was tested in triplicates and error bars represent the standard deviation of the mean.

Figure 4. Epitope analysis of scFv-Fc A2.

Schematic representation of functional domains of gp41: fusion peptide (FP), N-terminal heptad repeat (N-HR, in blue), C-terminal heptad repeat (C-HR, in green) and membrane proximal external region (MPER). The pocket-forming sequence in the N-HR domain and the pocket-binding domain (PBD) and lipid-binding domain (LBD) in the C-HR domain are underlined. Small letters “a”,”d” in C-HR and ”e” and “g” in N-HR mark interacting amino acid residues during 6 helix bundle formation. Sequences of N36, T20 and C34 petides as well as the scFv-Fc A2 epitope, as derived from the peptide array, are indicated. Further the schematic view of the gp41 6 helix bundle (top view) is depicted at the bottom.

Figure 5. Epitope fine map of scFv-Fc A7 on 18 mer, and 7 mer peptide arrays.

(A) 18 mer overlapping peptides of the ADA V3 epitope were incubated with scFv-Fc A7 identifying “KSIHIGP” (underlined) as core epitope. (B) Further fine mapping of the core epitope was analyzed via stepwise alanin substitutions in the 7 mer epitope. (C) Variations with 1, 2, 3 and 5 amino acids in the core epitope were analyzed for scFv-Fc A7 binding.

Figure 6. Analysis scFv-Fc A2 and A7 for autoreactivity against cardiolipin and phosphatidylserine.

Autoreactivity of purified scFv-Fc A2 and A7 was analyzed by commercial ELISA (Bio-Rad) using the internal positive and negative control sera. mAb 4E10 was added as positive control and mAb 447-52D as negative control (each 100 µg/mL). Each sample was tested in duplicates and error bars represent the standard deviations of the mean.