相关实验视频

Updated: Sep 11, 2025

Predicting Treatment Response to Image-Guided Therapies Using Machine Learning: An Example for Trans-Arterial Treatment of Hepatocellular Carcinoma

Predicting Treatment Response to Image-Guided Therapies Using Machine Learning: An Example for Trans-Arterial Treatment of Hepatocellular Carcinoma

Published on: October 10, 2018

提高药物诱导性肝损伤预测使用图形神经网络与增强图形特征从分子优化

Taeyeub Lee¹, Joram M Posma²

¹Section of Bioinformatics, Division of Systems Medicine, Department of Metabolism, Digestion and Reproduction, Imperial College London, London, W12 0NN, UK. t.lee23@imperial.ac.uk.

Journal of cheminformatics

|August 18, 2025

概括

这项研究介绍了DILIGeNN,一种新的图形神经网络 (GNN) 模型,用于预测药物诱导的肝损伤 (DILI). 通过利用详细的3D分子结构,DILIGeNN实现了最先进的性能,在DILI预测和其他分子性质任务中表现优于现有的方法.

科学领域:

计算化学是一种计算化学.
机器学习在药物发现中的作用
毒理学毒理学毒理学

背景情况:

药物诱导性肝损伤 (DILI) 在药物开发中构成重大风险,经常导致试验终止和退出市场.
早期预测DILI对于有效的药物开发和安全至关重要.

研究的目的:

开发和评估一个名为DILIGeNN的图形神经网络 (GNN) 模型,用于预测DILI.
利用详细的分子图表表示,包括空间和静电特征,以提高预测准确度.

主要方法:

在DILI和其他分子数据集上评估了GNN架构 (GCN,GAT,GraphSAGE,GIN).
开发了一种新的方法,从优化的分子结构中创建一个自定义的图形数据集,具有现实的化学特征 (债券长度,部分电荷).
实现了DILIGeNN,一个GNN框架,将空间和静电信息编码为单个图形表示.

主要成果:

在DILI数据集中,DILIGeNN的AUC达到0.897,超过了当前的最先进数据.
证明了强大的通用性,AUC为0.918 (克林托克斯),0.993 (BBBP) 和0.953 (BACE).
超越了使用分子指纹或多个图表表示的现有方法.

结论:

DILIGeNN有效地使用单个图表表示来预测DILI,其性能优于当前最先进的方法.
分子图生成和GNN培训方法是早期药物开发和重新利用的强大工具.
该方法在单个图中编码空间和静电信息的能力是预测毒理学和药物发现的重大进步.

关键词:

药物诱导的肝损伤是药物诱导的肝损伤.功能工程的特点工程.图形神经网络是一个神经网络.分子优化分子优化

更多相关视频

Human Liver Microphysiological System for Assessing Drug-Induced Liver Toxicity In Vitro

Human Liver Microphysiological System for Assessing Drug-Induced Liver Toxicity In Vitro

Published on: January 31, 2022

A Knowledge Graph Approach to Elucidate the Role of Organellar Pathways in Disease via Biomedical Reports

A Knowledge Graph Approach to Elucidate the Role of Organellar Pathways in Disease via Biomedical Reports

Published on: October 13, 2023

相关概念视频

Determination of Renal Drug Clearance: Graphical and Midpoint Methods

Determination of Renal Drug Clearance: Graphical and Midpoint Methods

Renal clearance, a crucial parameter in pharmacokinetics, can be determined using two different methods: the graphical method and the midpoint method. These methods provide insights into the rate of drug excretion by the kidneys and aid in assessing renal function.
The graphical method involves plotting the rate of drug excretion in urine against the plasma drug concentration. By analyzing the graph, the clearance can be calculated and obtained. Drugs rapidly excreted by the kidneys exhibit a...

Protein Networks

Protein Networks

An organism can have thousands of different proteins, and these proteins must cooperate to ensure the health of an organism. Proteins bind to other proteins and form complexes to carry out their functions. Many proteins interact with multiple other proteins creating a complex network of protein interactions.
These interactions can be represented through maps depicting protein-protein interaction networks, represented as nodes and edges. Nodes are circles that are representative of a protein,...