Compound toxicity prediction based on transcriptomics data and gene ontology knowledge
10.7644/j.issn.1674-9960.2025.03.003
- VernacularTitle:基于转录组数据和基因本体知识的化合物毒性预测
- Author:
Caiyun ZHAO
1
;
Song HE
;
Yiguang JIN
;
Xiaochen BO
Author Information
1. 军事科学院军事医学研究院,北京 100850
- Keywords:
compound toxicity prediction;
CYP enzyme activity;
p53 pathway stress response;
transcriptome;
gene ontology;
deep learning
- From:
Military Medical Sciences
2025;49(3):178-184
- CountryChina
- Language:Chinese
-
Abstract:
Objective To develop a new model for predicting compound toxicity and exploring related toxicity mechanisms using transcriptomic data and gene ontology knowledge.Methods Using the TOXRIC database,two toxicity-related datasets were constructed and a Tox VNN model was established that incorporated gene ontology knowledge to evaluate compound toxicity and identify key biological processes.Results Tox VNN demonstrated good predictability.The identification of important biological processes related to CYP enzyme activity and p53 pathway stress response provided insights into the toxicity mechanisms.Conclusion The Tox VNN,which integrates data and knowledge,can not only ensure high predictability,but also effectively identify important biological processes related to toxicity.This model offers a new approach to predicting and understanding compound toxicity in drug safety evaluation.
