Delineation of autoantibody repertoire through differential proteogenomics in hepatitis C virus-induced cryoglobulinemia

Abstract

Antibodies cross-reactive to pathogens and autoantigens are considered pivotal in both infection control and accompanying autoimmunity. However, the pathogenic roles of autoantibodies largely remain elusive without a priori knowledge of disease-specific autoantigens. Here, through a novel quantitative proteogenomics approach, we demonstrated a successful identification of immunoglobulin variable heavy chain (VH) sequences highly enriched in pathological immune complex from clinical specimens obtained from a patient with hepatitis C virus-induced cryoglobulinemia (HCV-CG). Reconstructed single-domain antibodies were reactive to both HCV antigens and potentially liver-derived human proteins. Moreover, over the course of antiviral therapy, a substantial "de-evolution" of a distinct sub-repertoire was discovered, to which proteomically identified cryoprecipitation-prone autoantibodies belonged. This sub-repertoire was characterized by IGHJ6*03-derived, long, hydrophobic complementarity determining region (CDR-H3). This study provides a proof-of-concept of de novo mining of autoantibodies and corresponding autoantigen candidates in a disease-specific context in human, thus facilitating future reverse-translational research for the discovery of novel biomarkers and the development of antigen-specific immunotherapy against various autoantibody-related disorders.

Figure 1. Identification of V_H sequences highly enriched in cryoprecipitate.

(a) Schematic illustration of experimental framework. HCV-CG, hepatitis C virus-induced cryoglobulinemia. Illustrations were modified from the resources distributed in the Togo picture gallery (http://g86.dbcls.jp/~togoriv/), licensed under CC-BY 4.0 ©Togo picture gallery by the Database Center for Life Science (DBCLS), Japan. (b) Labeling efficiencies of iTRAQ reporter tags. Fab samples from cryoprecipitate and serum remnant were labeled with iTRAQ reporter reagents 116 and 117, respectively. The labeling efficiency was defined as the ratio of the number of spectra containing the iTRAQ peak of interest to the total number of acquired spectra. Statistical comparison was carried out through the Welch’s t-test. (c) Correlation plot of relative abundances of identified V_H sequences. Generally, a weak correlation was observed between the abundance of each V_H sequence in serum remnant and that in cryoprecipitate. The size of each dot represents Cook’s distance, which indicates how outlying that sequence is. The band represents a 95% prediction interval. (d) Summary table for three representative V_H sequences selected on the basis of their relative enrichment in cryoprecipitate. For CDR-H3 amino acid sequence, bold indicates non-templated regions, and underline indicates somatic mutations. PEP, posterior error probability. (e) Representative mass spectra of the evidence peptides of three selected V_H sequences: left, UT1.1, middle, UT1.2, right, UT1.3.

Figure 2. Reactivity profiles of representative V_H sequences.

(a) Reactivity against HCV core and nonstructural (NS) antigens was measured via indirect ELISA. Background-subtracted absorbance values are shown. The synthetic peptide has the same sequence to the C-terminus of single-domain antibodies studied. Since two-way ANOVA revealed significant reciprocal relationships, multiple groups were compared by pairwise one-way ANOVA followed by Tukey post hoc test, using the pairw.anova function implemented in the asbio package in R. Adjusted P values against GST control are presented according to the following codes: *P < 0.05, **P < 0.01, ***P < 0.001. Bars indicate mean ± s.e.m. N = 3 per group. Experiments were performed in duplicate and repeated twice. (b) Summary table of autoreactivity profiles identified in the HuProt protein array experiments. No autoreactivity was identified for UT1.2. Completely overlapping candidate autoantigens were identified for both UT1.1 and UT1.3 when candidates with Z-score of 2.5 or less were ignored. ^†Protein-level expression data were retrieved from The Human Protein Atlas. Bil, bile duct cells. Hep, hepatocytes. HCC, hepatocellular carcinoma. The codes H, M, L, and N denote high, medium, low, and no detectable expression, respectively.

Figure 3. Longitudinal dynamics of CDR-H3 repertoire architecture over antiviral therapy.

(a) Construction of AAIndexScore as the best predictive axis for CryoglobulinIndex, which is defined as a rescaled ratio of iTRAQ signal intensities. A dash line represents the best threshold value determined by receiver operating characteristic (ROC) analysis. (b) Relative contributions of amino acid residues to AAIndexScore. Lowercase alphabetical characters indicate amino acid categories classified through a hierarchical clustering approach. (c) Similarity-based two-dimensional mapping of CDR-H3 repertoires. On the basis of the amino acid categories shown in (b), edit distance between each CDR-H3 sequence pair was calculated. The resultant distance matrix was converted to coordinates through a principal coordinate analysis (PCoA) followed by a linear discriminant analysis (LDA). Longitudinal shifts were particularly notable in IGHV1-69 and IGHV3-21 repertoires, but not in IGHV3-23 repertoire. (d) Similarity network analysis of CDR-H3 repertoires. IGHV1-69, IGHV3-21 and IGHV3-23-derived CDR-H3 sequences in different time points were combined to construct a single network, in which each CDR-H3 node was connected to their most-similar counterparts on the basis of the distance defined in (c). Representative clustering results obtained by multilevel optimization algorism is presented. Red, Cluster8. Blue, Cluster11. Interestingly, CDR-H3 sequences of UT1.1-1.3 were classified into the same cluster. (e) Longitudinal shrinkage of Cluster8 identified in (d). (f) Distributions of AAIndexScore. CDR-H3 sequences in Cluster8 generally have higher AAIndexScore than those in Cluster11. Meanwhile, no notable time-dependent changes in AAIndexScore were observed.

Figure 4. Feature characterization of the most dynamically shrinking CDR-H3 sub-repertoire.

(a) Cluster8 was enriched with CDR-H3 sequences derived from IGHJ6. Longitudinal shrinkage of sub-repertoire derived from IGHJ6, particularly IGHJ6*03, was observed. (b) Motif screening. CDR-H3 amino acid sequence motifs were screened by univariate analysis. Note that amino acids categorized as defined in Fig. 3b were used for the motif analysis. Nineteen motifs were retained after filtering by the threshold of Bonferroni-adjusted P value < 0.05. Most of the motifs significantly enriched in Cluster8 were of IGHJ6*03 origin. (c,d) Diminishing trends of two representative motifs, “pcqp” and “qpppp”. In most cases, “pcqp” and “qpppp” correspond to IGHJ6-derived sequences YMDV and D/EYYYY, respectively. Of note, UT1.1 contains “qpppp”, and UT1.3 contains “pcqp”.