Esta entrada está disponible en inglés.
Journal of Biological Chemistry abstract: mechanism-aware ML identifies a protease–chemokine–galectin axis in COVID-19
A RIPLRT abstract in the Journal of Biological Chemistry (ASBMB 2026 supplement) uses mechanism-aware machine learning to link plasma proteomics to single-cell signaling and compactly classify COVID-19 severity.
Dr. Félix E. Rivera-Mariani has published an abstract in the Journal of Biological Chemistry as part of the American Society for Biochemistry and Molecular Biology (ASBMB) 2026 annual meeting supplement:
Mechanism-Aware ML Identifies a Protease–Chemokine–Galectin (PCG) Axis that Links Plasma Proteomics to Single-Cell Signaling and Enables Compact Severity Classification in COVID-19
Rather than treating machine learning as a black box, the work constrains models with known biology ("mechanism-aware ML") so that the features it selects correspond to interpretable pathways. Applied to COVID-19, this approach:
- identified a protease–chemokine–galectin (PCG) axis as a biologically meaningful driver of disease severity,
- linked plasma proteomic signatures to single-cell signaling states, bridging two layers of multi-omic data, and
- yielded a compact severity classifier using a small number of proteins, a step toward practical clinical tools.
The abstract connects two threads of RIPLRT's research: the environmental fungal-spore exposure signals we study in Puerto Rico and the multi-omic biomarker analysis that helps explain who becomes severely ill and why.
Adapted from Lynn University News.