LiverDCP: A Disease-Cell-Protein Framework for Multi-scale Modeling of Disease Biology
- 1University of Texas Medical Branch
Abstract
Understanding how molecular interactions give rise to disease phenotypes across cellular contexts remains a central challenge in biomedical research. Here, we introduce a Disease-Cell-Protein (DCP) paradigm for modeling multi-scale disease biology, which jointly represents disease states, cellular composition, and protein interaction networks within a unified graph architecture. We instantiate this paradigm in the liver as LiverDCP by integrating LiverHomo, a harmonized single-cell atlas of liver diseases, with proteome-wide predicted protein-protein interactions to construct over 280 context-specific interactomes across diverse liver disease and cellular conditions. LiverDCP employs a multi-context representation learning strategy that enables joint training across hundreds of disease-cell environments, capturing shared interaction principles while preserving context-specific variation. LiverDCP incorporates pretrained protein sequence-derived features through a geometry-aware two-phase training scheme that preserves embedding structure while improving predictive performance. The resulting DCP protein embeddings reveal extensive rewiring of protein functional states across diseases, providing a transferable representation for downstream biomedical applications. Without GWAS supervision during representation learning, LiverDCP enables disease-risk gene classification and identifies cell types through which genetic risk may act. For therapeutic target discovery, LiverDCP recovers established Phase II+ MASH targets and prioritizes previously unrecognized candidates from the unannotated proteome, with 26 of the top 50 predictions showing independent PubMed evidence related to MASH biology. Context-specific interaction analysis further provides mechanistic hypotheses for less-characterized candidates. Together, these results establish DCP as a generalizable framework for connecting molecular interactions, cellular context, genetic risk, and therapeutic opportunities across complex diseases.
Related
- An automated machine vision-based index for Rett Syndrome provides a generalizable framework for modeling rare disease therapeutics
- Emerging Technologies in Cardiovascular Disease Modeling: Bridging Basic Science and Clinical Translation
- Human iPSC-Derived Brain Cells, Organoids, and Organoids-on-Chips: Advancing Neurological Disease Modeling to Improve Clinical Outcome
- Evolution of deep learning for structural magnetic resonance imaging analysis in Alzheimer’s disease: from slice-level classification to brain structure modeling
- Protein damage and repair in aging: mechanisms, homeostasis and disease
BibTeX
@misc{shi2026liverdcp,
title = {{LiverDCP: A Disease-Cell-Protein Framework for Multi-scale Modeling of Disease Biology}},
author = {Z. Shi and Z. Song and H. Stevenson-Lerner and B. Dong and H. Zhao},
howpublished = {bioRxiv},
year = {2026},
month = aug,
doi = {10.64898/2026.08.07.743628},
url = {https://www.biorxiv.org/content/10.64898/2026.08.07.743628v2},
note = {CC BY-NC-ND},
}
RIS
TY - UNPB
TI - LiverDCP: A Disease-Cell-Protein Framework for Multi-scale Modeling of Disease Biology
AU - Z. Shi
AU - Z. Song
AU - H. Stevenson-Lerner
AU - B. Dong
AU - H. Zhao
PY - 2026
DA - 2026/08/07
PB - bioRxiv
DO - 10.64898/2026.08.07.743628
UR - https://www.biorxiv.org/content/10.64898/2026.08.07.743628v2
AB - Understanding how molecular interactions give rise to disease phenotypes across cellular contexts remains a central challenge in biomedical research. Here, we introduce a Disease-Cell-Protein (DCP) paradigm for modeling multi-scale disease biology, which jointly represents disease states, cellular composition, and protein interaction networks within a unified graph architecture. We instantiate this paradigm in the liver as LiverDCP by integrating LiverHomo, a harmonized single-cell atlas of liver diseases, with proteome-wide predicted protein-protein interactions to construct over 280 context-specific interactomes across diverse liver disease and cellular conditions. LiverDCP employs a multi-context representation learning strategy that enables joint training across hundreds of disease-cell environments, capturing shared interaction principles while preserving context-specific variation. LiverDCP incorporates pretrained protein sequence-derived features through a geometry-aware two-phase training scheme that preserves embedding structure while improving predictive performance. The resulting DCP protein embeddings reveal extensive rewiring of protein functional states across diseases, providing a transferable representation for downstream biomedical applications. Without GWAS supervision during representation learning, LiverDCP enables disease-risk gene classification and identifies cell types through which genetic risk may act. For therapeutic target discovery, LiverDCP recovers established Phase II+ MASH targets and prioritizes previously unrecognized candidates from the unannotated proteome, with 26 of the top 50 predictions showing independent PubMed evidence related to MASH biology. Context-specific interaction analysis further provides mechanistic hypotheses for less-characterized candidates. Together, these results establish DCP as a generalizable framework for connecting molecular interactions, cellular context, genetic risk, and therapeutic opportunities across complex diseases.
ER -