CPRISP: an interpretable deep learning framework predicting circRNA-RBP interactions and guiding therapeutic discovery in neurodegeneration
Abstract
Circular RNAs regulate gene expression through interactions with ribonucleic acid binding proteins, but their binding sites remain difficult to predict across proteins and cellular contexts. Existing methods often focus on transcript features while making limited use of protein-specific information and structural context. Here, we show that an integrated deep learning framework combining circular transcript sequence composition, physicochemical properties, secondary structure, pretrained representations and protein features improves interaction-site prediction across 37 benchmark datasets and generalizes across cell lines; model interpretation recovers conserved single-stranded sequence patterns, while analyses of proteins linked to Alzheimer disease, Parkinson disease and amyotrophic lateral sclerosis identify recurrent pathways involving nucleocytoplasmic transport, lysosomal signaling and guanosine triphosphatase activity and prioritize compounds for experimental follow-up, supporting accurate and interpretable mapping of circular ribonucleic acid protein interactions without implying therapeutic efficacy.
Related
- The "Invisible Killer” of Neurodegeneration: Mitochondrial Dysfunction in Neurodegenerative Disorders, Mechanisms, Emerging Pathways and Therapeutic Strategies
- An inverse-protein-folding pre-trained model for predicting the mutational effects in protein-protein interactions
- Predicting specificity of TCR-pMHC interactions using machine-learning and biophysical models
- Microglial Vulnerability to Mitochondrial Proteotoxic Stress: A Failed-Resolution Framework for Neurodegeneration
- Pantethine and Neurodegeneration: A Coenzyme A-Centered Framework Linking Metabolism, Neuroinflammation, and Mitochondrial Dysfunction
BibTeX
@article{wang2026cprisp,
title = {{CPRISP: an interpretable deep learning framework predicting circRNA-RBP interactions and guiding therapeutic discovery in neurodegeneration}},
author = {Yongtian Wang and Jiahao Li and Xinmeng Liu and Linlin You and Calvin Yu-Chian Chen},
journal = {Nature Communications},
year = {2026},
month = oct,
doi = {10.1038/s41467-026-79009-3},
url = {https://www.nature.com/articles/s41467-026-79009-3},
note = {CC BY 4.0},
}
RIS
TY - JOUR
TI - CPRISP: an interpretable deep learning framework predicting circRNA-RBP interactions and guiding therapeutic discovery in neurodegeneration
AU - Yongtian Wang
AU - Jiahao Li
AU - Xinmeng Liu
AU - Linlin You
AU - Calvin Yu-Chian Chen
PY - 2026
DA - 2026/10/28
JO - Nature Communications
DO - 10.1038/s41467-026-79009-3
UR - https://www.nature.com/articles/s41467-026-79009-3
AB - Circular RNAs regulate gene expression through interactions with ribonucleic acid binding proteins, but their binding sites remain difficult to predict across proteins and cellular contexts. Existing methods often focus on transcript features while making limited use of protein-specific information and structural context. Here, we show that an integrated deep learning framework combining circular transcript sequence composition, physicochemical properties, secondary structure, pretrained representations and protein features improves interaction-site prediction across 37 benchmark datasets and generalizes across cell lines; model interpretation recovers conserved single-stranded sequence patterns, while analyses of proteins linked to Alzheimer disease, Parkinson disease and amyotrophic lateral sclerosis identify recurrent pathways involving nucleocytoplasmic transport, lysosomal signaling and guanosine triphosphatase activity and prioritize compounds for experimental follow-up, supporting accurate and interpretable mapping of circular ribonucleic acid protein interactions without implying therapeutic efficacy.
SN - 2041-1723
ER -