National Institute of Allergy and Infectious Diseases 5U19AI135964-09

Modeling Core

This award funds the Modeling Core project at Northwestern University to develop machine learning models of severe pneumonia using clinical and multi-omics data. The project aims to identify biomarkers and therapeutic targets to improve clinical decision-making for pneumonia, including SARS-CoV-2 pneumonia.

Description

The Modeling Core, as part of SCRIPT, aimed to apply machine learning approaches to clinical and -omics data generated by the SCRIPT projects and cores to develop models of severe pneumonia and identify novel biomarkers and therapeutic targets. Using an iterative systems biology approach, a detailed model of severe SARS-CoV-2 pneumonia was generated, explaining its unique host response pathobiology. The project will continue to leverage serial sampling and multi-omics technologies to develop models of pneumonia pathogenesis to augment clinical decision making. The project includes three specific aims focused on generating interpretable latent space models of clinical states, identifying biomarkers and clinical interventions predictive of clinical state transitions, and generalizing models to external datasets.

View original record