Population scale proteomics enables adaptive digital twin modelling in sepsis
Scott, A. M.; Mellhammar, L.; Malmström, E.; Goch Gustafsson, A.; Bakochi, A.; Isaksson, M.; Mohanty, T.; Thelaus, L.; Kahn, F.; Malmström, L.; Malmström, J.; Linder, A.
10.1101/2024.03.20.24304575 medRxivShow abstract
Sepsis is one of the leading causes of mortality in the world. Currently, the heterogeneity of sepsis makes it challenging to determine the molecular mechanisms that define the syndrome. Here, we leverage population scale proteomics to analyze a well-defined cohort of 1364 blood samples taken at time-of-admission to the emergency department from patients suspected of sepsis. We identified panels of proteins using explainable artificial intelligence that predict clinical outcomes and applied these panels to reduce high-dimensional proteomics data to a low-dimensional interpretable latent space (ILS). Using the ILS, we constructed an adaptive digital twin model that accurately predicted organ dysfunction, mortality, and early-mortality-risk patients using only data available at time-of-admission. In addition to being highly effective for investigating sepsis, this approach supports the flexible incorporation of new data and can generalize to other diseases to aid in translational research and the development of precision medicine.
Matching journals
The top 12 journals account for 50% of the predicted probability mass.
Similar papers in this journal
- Multi-omics identify LRRC15 as a COVID-19 severity predictor and persistent pro-thrombotic signals in convalescence 94%
- Proteome allocation is linked to transcriptional regulation through a modularized transcriptome 94%
- Imputation of label-free quantitative mass spectrometry-based proteomics data using self-supervised deep learning 93%
Similar papers in this journal
- PathIntegrate: Multivariate modelling approaches for pathway-based multi-omics data integration 93%
- Protein prediction models support widespread post-transcriptional regulation of protein abundance by interacting partners 93%
- MiMeNet: Exploring Microbiome-Metabolome Relationships using Neural Networks 92%
Similar papers in this journal
Similar papers in this journal
- International multi-cohort analysis identifies novel framework for quantifying immune dysregulation in critical illness: results of the SUBSPACE consortium 92%
- Direct Antimicrobial Resistance Prediction from clinical MALDI-TOF mass spectra using Machine Learning 91%
- A consensus Covid-19 immune signature combines immuno-protection with discrete sepsis-like traits associated with poor prognosis 90%
Similar papers in this journal
- Mass spectrometry-based quantification of proteins and post-translational modifications in dried blood: longitudinal sampling of patients with sepsis in Tanzania 95%
- Monitoring Functional Post-Translational Modifications Using a Data-Driven Proteome Informatic Pipeline 93%
- Characterization of cytokine treatment on human pancreatic islets by top-down proteomics 92%
"Similar papers" are the closest papers from that journal in the model's embedding space. They show what the match is built on, but the ranking comes mostly from a classifier over the whole training set, not from these examples alone.