Yun, C.-S. | Search bioRxiv

bioRxiv2025

A high-throughput cell-based platform for Rhinovirus C research and antiviral drug discovery.

Rhinoviruses (RVs) are the most common cause of upper respiratory infections, yet RV-C is particularly associated with severe respiratory disease, including exacerbations of asthma and chronic obstructive pulmonary disease (COPD). Despite its clinical significance, RV-C research and antiviral development have been hindered by the lack of scalable and biologically relevant models for high-throughput screening (HTS). Here, we present the development, optimization, and validation of a scalable high-content imaging-based platform for RV-C research. Our approach combines engineered HeLa cells expressing CDHR3C529Y, a genetically stable mGreenLantern-reporter RV-C15 virus, and a phenotypic selection strategy to identify monoclonal cell lines with maximal and sustained permissiveness. This approach enabled assay optimization in both 96- and 384-well formats, achieving robust performance (Z' > 0.7) and reproducibility across more than 100 runs with reference antiviral compounds. The platform was readily adapted to RV-A16, RV-B14, and additional RV-C types (C11 and C41), demonstrating broad applicability across rhinovirus species. A pilot screen of 10 240 compounds identified confirmed RV-C inhibitors, highlighting the readiness of the platform for integration into drug discovery pipelines. This platform provides a robust and scalable tool for systematic antiviral discovery and a foundation for mechanistic studies of RV-C replication. Significance statementRhinovirus C (RV-C) is strongly associated with severe respiratory disease such as asthma and COPD exacerbations, yet its study has been limited by the absence of scalable cell-based systems. We developed a high-content imaging-based high-throughput screening platform that supports efficient RV-C replication in engineered CDHR3-expressing cells and enables systematic antiviral discovery. The platform integrates a genetically stable fluorescent reporter virus with phenotypically selected permissive monoclonal cell lines, achieving high reproducibility and scalability in both 96- and 384-well formats. Its adaptability across multiple rhinovirus species establishes a unified framework for antiviral testing and mechanistic investigation. A pilot screen of 10K compounds confirmed the applicability of the platform to drug discovery campaigns.

microbiology↗

bioRxiv2025

Advancing Wildlife Image Analysis: A Graph Attention Contrastive Learning Approach for Region-Specific Mammal Classification

1. Camera traps have become a cornerstone of wildlife ecological research, yet the manual analysis of the millions of images they generate requires substantial time and resources. Deep learning-based automation has emerged as a promising solution, existing global general-purpose models exhibit limitations in precisely recognizing local endemic species and adapting to unique local ecosystems. 2. This study developed a high-performance classification model optimized for native species. A large-scale "Korean Wildlife Dataset" was constructed from data collected across diverse domestic habitats, and a novel architecture was proposed to overcome limitations of conventional CNNs. The proposed Graph Attention Contrastive Learning (GACL) model is structured as a two-stage pipeline. Stage one employs YOLOv5 and MegaDetector to detect animals, humans, and vehicles, filtering valid images. Stage two performs fine-grained species classification. GACL captures structural relationships among object parts using a Graph Attention Transformer (GAT) and aligns semantic correspondence between images and textual descriptions via Parallel Contrastive Learning, enabling deeper understanding beyond simple visual features. 3. Evaluation on an independent test set demonstrated that the proposed model robust classification performance with an overall accuracy of 96.83% across four classes (Wildboar, Goral, Deers, and Other). Notably, in a comparative analysis against a global general-purpose model, our model showed distinct advantages in the precise recognition of endemic species. Furthermore, it exhibited a lower false positive rate in identifying animals in empty images, confirming its potential to enhance the efficiency of the data cleaning process. 4. Beyond technical accuracy, this study highlights that region-specific AI models that reflect local ecological characteristics can provide substantial practical value for wildlife monitoring and biodiversity conservation. Future work will require continuous efforts in data diversification and model lightweighting to further improve model robustness and practicality.

ecology↗