COVID-19 is highly variable in its clinical presentation, ranging from asymptomatic infection to severe organ damage and death. There is an urgent need for predictive markers that can guide clinical decision-making, inform about the effect of experimental therapies, and point to novel therapeutic targets. Here, we characterize the time-dependent progression of COVID-19 through different stages of the disease, by measuring 86 accredited diagnostic parameters and plasma proteomes at 687 sampling points, in a cohort of 139 patients during hospitalization. We report that the time-resolved patient molecular phenotypes reflect an initial spike in the systemic inflammatory response, which is gradually alleviated and followed by a protein signature indicative of tissue repair, metabolic reconstitution and immunomodulation. Further, we show that the early host response is predictive for the disease trajectory and gives rise to proteomic and diagnostic marker signatures that classify the need for supplemental oxygen therapy and mechanical ventilation, and that predict the time to recovery of mildly ill patients. In severely ill patients, the molecular phenotype of the early host response predicts survival, in two independent cohorts and weeks before outcome. We also identify age-specific molecular response to COVID-19, which involves increased inflammation and lipoprotein dysregulation in older patients. Our study provides a deep and time resolved molecular characterization of COVID-19 disease progression, and reports biomarkers for risk-adapted treatment strategies and molecular disease monitoring. Our study demonstrates accurate prognosis of COVID-19 outcome from proteomic signatures recorded weeks earlier.

Global healthcare systems are challenged by the COVID-19 pandemic. There is a need to optimize allocation of treatment and resources in intensive care, as clinically established risk assessments such as SOFA and APACHE II scores show only limited performance for predicting the survival of severely ill COVID-19 patients. Comprehensively capturing the host physiology, we speculated that proteomics in combination with new data-driven analysis strategies could produce a new generation of prognostic discriminators. We studied two independent cohorts of patients with severe COVID-19 who required intensive care and invasive mechanical ventilation. SOFA score, Charlson comorbidity index and APACHE II score were poor predictors of survival. Plasma proteomics instead identified 14 proteins that showed concentration trajectories different between survivors and non-survivors. A proteomic predictor trained on single samples obtained at the first time point at maximum treatment level (i.e. WHO grade 7) and weeks before the outcome, achieved accurate classification of survivors in an exploratory (AUROC 0.81) as well as in the independent validation cohort (AUROC of 1.0). The majority of proteins with high relevance in the prediction model belong to the coagulation system and complement cascade. Our study demonstrates that predictors derived from plasma protein levels have the potential to substantially outperform current prognostic markers in intensive care.

Background Earlier detection of pancreatic ductal adenocarcinoma (PDAC) is key to improving patient outcomes, as it is mostly detected at advanced stages which are associated with poor survival. Developing non-invasive blood tests for early detection would be an important breakthrough. Methods The primary objective of the work presented here is to use a dataset that is prospectively collected, to quantify a set of cancer-associated proteins and construct multi-marker models with the capacity to predict PDAC years before diagnosis. The data used is part of a nested case-control study within the UK Collaborative Trial of Ovarian Cancer Screening and is comprised of 218 samples, collected from a total of 143 post-menopausal women who were diagnosed with pancreatic cancer within 70 months after sample collection, and 249 matched non-cancer controls. We develop a stacked ensemble modelling technique to achieve robustness in predictions and, therefore, improve performance in newly collected datasets. Results Here we show that with ensemble learning we can predict PDAC status with an AUC of 0.91 (95% CI 0.75–1.0), sensitivity of 92% (95% CI 0.54–1.0) at 90% specificity, up to 1 year prior to diagnosis, and at an AUC of 0.85 (95% CI 0.74–0.93) up to 2 years prior to diagnosis (sensitivity of 61%, 95% CI 0.17–0.83, at 90% specificity). Conclusions The ensemble modelling strategy explored here outperforms considerably biomarker combinations cited in the literature. Further developments in the selection of classifiers balancing performance and heterogeneity should further enhance the predictive capacity of the method.

DNA methylation variability arises due to concurrent genetic and environmental influences. Each of them is a mixture of regular and noisy sources, whose relative contribution has not been satisfactorily understood yet. We conduct a systematic assessment of the age-dependent methylation by the signal-to-noise ratio and identify a wealth of “deterministic” CpG probes (about 90%), whose methylation variability likely originates due to genetic and general environmental factors. The remaining 10% of “stochastic” CpG probes are arguably governed by the biological noise or incidental environmental factors. Investigating the mathematical functional relationship between methylation levels and variability, we find that in about 90% of the age-associated differentially methylated positions, the variability changes as the square of the methylation level, whereas in the most of the remaining cases the dependence is linear. Furthermore, we demonstrate that the methylation level itself in more than 15% cases varies nonlinearly with age (according to the power law), in contrast to the previously assumed linear changes. Our findings present ample evidence of the ubiquity of strong DNA methylation regulation, resulting in the individual age-dependent and nonlinear methylation trajectories, whose divergence explains the cross-sectional variability. It may also serve a basis for constructing novel nonlinear epigenetic clocks.