EviCYP: In Silico Prediction of Cytochrome P450 Substrates Based on Vector Quantization and Evidential Deep Learning

Clinical Snapshot

Key Findings

• P Value: Not reported in abstract

• Effect Size: AUROC = 0.9500 (excellent discriminative ability)

• Primary Outcome: AUROC performance for CYP substrate prediction

• Nnt Or Sensitivity: High correlation between uncertainty estimates and classification errors (specific metrics not provided)

• Confidence Interval: Not reported in abstract

Clinical Application

Requires computational expertise and infrastructure; may need integration into existing drug development workflows Highly relevant for TGA drug evaluation processes, pharmaceutical industry R&D, and academic drug discovery programs. Could support PBS listing decisions by improving drug safety predictions Pharmaceutical researchers, drug developers, regulatory scientists involved in drug metabolism and safety assessment

Abstract

The accurate identification of cytochrome P450 (CYP) substrates is crucial in drug discovery and safety assessment, as these enzymes mediate the metabolism of most clinical drugs. However, existing computational models are often limited by data quality issues and lack the ability to quantify prediction uncertainty, hindering their reliable application. To address these challenges, we present EviCYP, a novel prediction framework that integrates evidential deep learning with vector quantization (VQ). We first constructed a high-quality data set by curating 4388 substrates and 2880 nonsubstrates from 1629 publications, and supplemented it with 3728 pseudonegative samples, resulting in 10,996 samples spanning nine major CYP isoforms. The EviCYP architecture processes multimodal molecular representations and enzyme sequences through dedicated encoders, compresses features via VQ to reduce redundancy, and employs an evidential layer to output both class probabilities and an uncertainty estimate. On an internal test set, EviCYP achieved an average AUROC of 0.9500. Notably, the model's uncertainty quantification is highly reliable, with high-uncertainty predictions strongly correlating with classification errors. This work provides a robust and trustworthy computational tool for CYP substrate prediction.

References

1. 1.Yang, Y., Zhang, Y., Song, W., Zhu, K., Li, X., Tong, M., Liu, G., Li, W., & Tang, Y. (2026). EviCYP: In Silico Prediction of Cytochrome P450 Substrates Based on Vector Quantization and Evidential Deep Learning. Journal of Chemical Information and Modeling. https://doi.org/10.1021/acs.jcim.6c00074