Tensor‐structured decomposition improves systems serology analysis

Abstract

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.

Cytokine-expression patterns reveal coordinated immunological programs associated with persistent MRSA bacteremia

“…In contrast, here we wish to explain the total variation across both the tensor and matrix. This is accomplished with CMTF (11–13).…”

“…Variation along each mode of the data in tensor form is effectively separated by these techniques (11,12). When integrating two sources of data each in a matrix or tensor format, coupled matrix-tensor factorization allows one to detect shared patterns between datasets of differing dimensionality (11)(12)(13). Recognizing coupling across datasets provides two distinct benefits: (1) the extent of data reduction is increased by using a common set of patterns across both datasets; and (2) patterns distinguished in the shared mode reflect the trends presented in both datasets, thus their definition is better shaped.…”

Multivalent, asymmetric IL-2-Fc fusions provide optimally enhanced regulatory T cell selectivity

“…Restricting ones’ view to a single time point, cell type, or ligand concentration provides only a slice of the picture (Figs. 1 & 2) 15,30 . Dimensionality reduction is a generally effective tool for exploring multidimensional data.…”

“…1 & 2) 15,30 . Dimensionality reduction is a generally effective tool for exploring multidimensional data.…”

Platelet response to influenza vaccination reflects effects of aging

“…To analyze temporal patterns we leveraged the TCA tensor decomposition framework that has seen increased application for complex analytics in bioinformatics, including characterizing tissue-specific gene expression phenotypes 35 , Mycobacterium tuberculosis subtyping 36 , and systems serology profiling 37 . To extract multi-index patterns that are individually interpretable, we performed a non-negative version of TCA, using CANDECOMP/POLYADIC decomposition (NCPD), which models the data as a non-negative sum of rank-one tensors, termed components 30 .…”