Tensor‐structured decomposition improves systems serology analysis

• Published in: Molecular systems biology Vol. 17; no. 9; pp. e10243 - n/a
• Main Authors: Tan, Zhixin Cyrillus, Murphy, Madeleine C, Alpay, Hakan S, Taylor, Scott D, Meyer, Aaron S
• Format: Journal Article
• Language: English
• Published: London Nature Publishing Group UK 01.09.2021; EMBO Press; John Wiley and Sons Inc; Springer Nature
• Subjects: Antibodies; Antigens; Approximation; Binding; Data reduction; Datasets; Decomposition; Disease; effector function; EMBO10; EMBO19; EMBO23; Gene expression; HIV; Human immunodeficiency virus; Humoral immunity; Immune system; Infections; Mathematical analysis; Pattern recognition; Prediction models; Principal components analysis; Regulatory mechanisms (biology); SARS‐CoV‐2; Serology; Severe acute respiratory syndrome coronavirus 2; System effectiveness; systems serology; tensor decomposition; Tensors; effector function; systems serology; HIV; SARS‐CoV‐2; tensor decomposition
• ISSN: 1744-4292; 1744-4292
• DOI: 10.15252/msb.202110243

Systems serology provides a broad view of humoral immunity by profiling both the antigen‐binding and Fc properties of antibodies. These studies contain structured biophysical profiling across disease‐relevant antigen targets, alongside additional measurements made for single antigens or in an antigen‐generic manner. Identifying patterns in these measurements helps guide vaccine and therapeutic antibody development, improve our understanding of diseases, and discover conserved regulatory mechanisms. Here, we report that coupled matrix–tensor factorization (CMTF) can reduce these data into consistent patterns by recognizing the intrinsic structure of these data. We use measurements from two previous studies of HIV‐ and SARS‐CoV‐2‐infected subjects as examples. CMTF outperforms standard methods like principal components analysis in the extent of data reduction while maintaining equivalent prediction of immune functional responses and disease status. Under CMTF, model interpretation improves through effective data reduction, separation of the Fc and antigen‐binding effects, and recognition of consistent patterns across individual measurements. Data reduction also helps make prediction models more replicable. Therefore, we propose that CMTF is an effective general strategy for data exploration in systems serology. SYNOPSIS Systems serology measurements can advance our understanding of humoral immunity. A data reduction method, “coupled matrix‐tensor factorization”, effectively analyzes such data by recognizing conserved patterns and separating antigen from Fc property effects. Structured decomposition provides substantial data reduction while retaining meaningful information. Predictions based on decomposed factors are accurate and robust to missing measurements. Decomposition structure allows insightful mechanistic interpretation of modeling results. Decomposed factors represent meaningful patterns in the HIV and SARS‐CoV‐2 humoral responses. Graphical Abstract Systems serology measurements can advance our understanding of humoral immunity. A data reduction method, “coupled matrix‐tensor factorization”, effectively analyzes such data by recognizing conserved patterns and separating antigen from Fc property effects.