Cho, N.-C. | Search bioRxiv

bioRxiv2026

PredHLM: quantitative and interpretable prediction of metabolic half-life in human liver microsomes

MotivationHuman liver microsome (HLM)-based metabolic stability assays are fundamental in early drug discovery, shaping pharmacokinetic profiles and oral bioavailability. However, these experimental assays are labor-intensive and time-consuming, limiting their application in large-scale virtual screening. Computational models can prioritize compounds at scale, yet most are classification-based, leaving quantitative and interpretable prediction of HLM half-life limited. ResultsIn this study, we developed a quantitative machine learning model for the direct prediction of HLM half-life (T1/2) by integrating 11,790 compounds combining in-house and curated public data. Among various combinations of molecular features and learning algorithms, the XGBoost model with RDKit 2D descriptors achieved the best predictive performance, with an RMSE of 0.507 and an R2 of 0.431 on an independent test set. Shapley Additive Explanations (SHAP) analysis identified lipophilicity and known metabolic soft-spot features as the primary contributors to the predictions. These results suggest that this quantitative approach provides a practical framework for defining metabolic stability margins, thereby supporting rapid Go/No-go decisions in preclinical drug discovery. AvailabilityThe source code, data, and trained model are available at https://github.com/joshua-416/PredHLM. Graphical abstract O_FIG O_LINKSMALLFIG WIDTH=200 HEIGHT=77 SRC="FIGDIR/small/736062v1_ufig1.gif" ALT="Figure 1"> View larger version (17K): org.highwire.dtl.DTLVardef@7d94c1org.highwire.dtl.DTLVardef@b13e71org.highwire.dtl.DTLVardef@7aa684org.highwire.dtl.DTLVardef@4a2668_HPS_FORMAT_FIGEXP M_FIG C_FIG

bioinformatics↗

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↗