Search

Abstract Determination of malignancy in thyroid nodules remains a major diagnostic challenge. Here we report the feasibility and clinical utility of developing an AI-defined protein-based biomarker panel for diagnostic classification of thyroid nodules: based initially on formalin-fixed paraffin-embedded (FFPE), and further refined for fine-needle aspiration (FNA) tissue specimens of minute amounts which pose technical challenges for other methods. We first developed a neural network model of 19 protein biomarkers based on the proteomes of 1724 FFPE thyroid tissue samples from a retrospective cohort. This classifier achieved over 91% accuracy in the discovery set for classifying malignant thyroid nodules. The classifier was externally validated by blinded analyses in a retrospective cohort of 288 nodules (89% accuracy; FFPE) and a prospective cohort of 294 FNA biopsies (85% accuracy) from twelve independent clinical centers. This study shows that integrating high-throughput proteomics and AI technology in multi-center retrospective and prospective clinical cohorts facilitates precise disease diagnosis which is otherwise difficult to achieve by other methods.

Abstract Little is known regarding why a subset of COVID-19 patients exhibited prolonged positivity of SARS-CoV-2 infection. Here, we found that patients with long viral RNA course (LC) exhibited prolonged high-level IgG antibodies and higher regulatory T (Treg) cell counts compared to those with short viral RNA course (SC) in terms of viral load. Longitudinal proteomics and metabolomics analyses of the patient sera uncovered that prolonged viral RNA shedding was associated with inhibition of the liver X receptor/retinoid X receptor (LXR/RXR) pathway, substantial suppression of diverse metabolites, activation of the complement system, suppressed cell migration, and enhanced viral replication. Furthermore, a ten-molecule learning model was established which could potentially predict viral RNA shedding period. In summary, this study uncovered enhanced inflammation and suppressed adaptive immunity in COVID-19 patients with prolonged viral RNA shedding, and proposed a multi-omic classifier for viral RNA shedding prediction.