Background: Autoantibodies are commonly used as biomarkers in autoimmune diseases, but there are limitations. For example, autoantibody biomarkers have poor sensitivity or specificity in systemic lupus erythematosus and do not exist in the spondyloarthropathies, impairing diagnosis and treatment. While autoantibodies suitable for strong biomarkers may not exist in these conditions, another possibility is that technology has limited their discovery. The purpose of this study was to use a novel high-density peptide array that enables the evaluation of IgG binding to every possible linear antigen in the entire human peptidome, as well as a novel machine learning approach that incorporates ELISA validation predictability in order to discover autoantibodies that could be developed into sensitive and specific markers of lupus or spondyloarthropathy. Methods: We used a peptide array containing the human peptidome, several viral peptidomes, and key post-translational modifications (6 million peptides) to quantify IgG binding in lupus, spondyloarthropathy, rheumatoid arthritis, Sjögren’s disease, and control sera. Using ELISA data for 70 peptides, we performed a random forest analysis that evaluated multiple array features to predict which peptides might be good biomarkers, as confirmed by ELISA. We validated the peptide prediction methodology in rheumatoid arthritis and COVID-19, conditions for which the antibody repertoire is well-understood, and then evaluated IgG binding by ELISA to peptides that we predicted would be highly bound specifically in lupus or spondyloarthropathy. Results: Our methodology performed well in validation studies, but peptides predicted to be highly and specifically bound in lupus or spondyloarthropathy could not be confirmed by ELISA. Conclusions: In a comprehensive evaluation of the entire human peptidome, highly sensitive and specific IgG autoantibodies were not identified in lupus or spondyloarthropathy. Thus, the pathogenesis of lupus and spondyloarthropathy may not depend upon unique autoantigens, and other types of molecules should be sought as optimal biomarkers in these conditions.
A/B testing, a widely used form of Randomized Controlled Trial (RCT), is a fundamental tool in business data analysis and experimental design. However, despite its intent to maintain randomness, A/B testing often faces challenges that compromise this randomness, leading to significant limitations in practice. In this study, we introduce Bootstrap Matching, an innovative approach that integrates Bootstrap resampling, Matching techniques, and high-dimensional hypothesis testing to address the shortcomings of A/B tests when true randomization is not achieved. Unlike traditional methods such as Difference-in-Differences (DID) and Propensity Score Matching (PSM), Bootstrap Matching is tailored for large-scale datasets, offering enhanced robustness and computational efficiency. We illustrate the effectiveness of this methodology through a real-world application in online advertising and further discuss its potential applications in digital marketing, empirical economics, clinical trials, and high-dimensional bioinformatics.
Peptide microarrays have emerged as a powerful technology in immunoproteomics as they provide a tool to measure the abundance of different antibodies in patient serum samples. The high dimensionality and small sample size of many experiments challenge conventional statistical approaches, including those aiming to control the false discovery rate (FDR). Motivated by limitations in reproducibility and power of current methods, we advance an empirical Bayesian tool that computes local false discovery rate statistics and local false sign rate statistics when provided with data on estimated effects and estimated standard errors from all the measured peptides. As the name suggests, the \verb+MixTwice+ tool involves the estimation of two mixing distributions, one on underlying effects and one on underlying variance parameters. Constrained optimization techniques provide for model fitting of mixing distributions under weak shape constraints (unimodality of the effect distribution). Numerical experiments show that \verb+MixTwice+ can accurately estimate generative parameters and powerfully identify non-null peptides. In a peptide array study of rheumatoid arthritis (RA), \verb+MixTwice+ recovers meaningful peptide markers in one case where the signal is weak, and has strong reproducibility properties in one case where the signal is strong. \verb+MixTwice+ is available as an R software package. \href{https://github.com/wiscstatman/MixTwice}{https://github.com/wiscstatman/MixTwice}