| アイテムタイプ |
学術雑誌論文 / Journal Article(1) |
| 公開日 |
2025-08-21 |
| タイトル |
|
|
タイトル |
On QSAR-based cardiotoxicity modeling with the expressiveness-enhanced graph learning model and dual-threshold scheme |
| 言語 |
|
|
言語 |
eng |
| キーワード |
|
|
主題Scheme |
Other |
|
主題 |
hERG |
| キーワード |
|
|
主題Scheme |
Other |
|
主題 |
cardiotoxicity |
| キーワード |
|
|
主題Scheme |
Other |
|
主題 |
graph transformer neural network |
| キーワード |
|
|
主題Scheme |
Other |
|
主題 |
meta-path |
| キーワード |
|
|
主題Scheme |
Other |
|
主題 |
dual-threshold |
| 資源タイプ |
|
|
資源タイプ |
journal article |
| アクセス権 |
|
|
アクセス権 |
open access |
| 著者 |
Wang, Huijia
Zhu, Guangxian
Izu, Leighton T.
Chen-Izu, Ye
小野, 直亮
Altaf-Ul-Amin, MD.
金谷, 重彦
Huang, Ming
|
| 抄録 |
|
|
内容記述タイプ |
Abstract |
|
内容記述 |
Introduction: Given the direct association with malignant ventricular arrhythmias, cardiotoxicity is a major concern in drug design. In the past decades, computational models based on the Quantitative structure-structure relationship (QSAR) have been proposed to screen out cardiotoxic compounds and have shown promising results. The combination of molecular fingerprint and machine learning model shows stable performance for a wide spectrum of problems, however, not long after the advent of the graph neural network (GNN) deep learning model and its variant (e.g., Graph Transformer), it has become the principal way of QSAR-based modeling for its high flexibility in feature extraction and decision rule generation. In spite of all these progresses, the expressiveness (the ability of a program to identify non-isomorphic graph structures) of the GNN model is bounded by the WL isomorphism test, and a suitable thresholding scheme that relates directly to the sensitivity and credibility of a model is still an open question. Methods: In this research, we further improved the expressiveness of the GNN model by introducing the substructure-aware bias by the Graph Subgraph Transformer network (GSTN) model. Moreover, to propose the most appropriate thresholding scheme, a comprehensive comparison of the thresholding schemes was conducted. Results: Based on these improvements,
the best model attains performance with 90.4% Precision, 90.4% Recall, and 90.5% F1-score with a dual threshold scheme (active: <1 uM; non-active: >30 uM). the improved pipeline (GSTN model and thresholding scheme) also shows its advantages in terms of the activity cliff problem and model interpretability. |
| 書誌情報 |
en : Frontiers in Physiology
巻 14,
ページ数 21,
発行日 2023-05-09
|
| 出版者 |
|
|
出版者 |
Frontiers Media |
| ISSN |
|
|
収録物識別子タイプ |
EISSN |
|
収録物識別子 |
1664-042X |
| 出版者版DOI |
|
|
関連タイプ |
isReplacedBy |
|
|
識別子タイプ |
DOI |
|
|
関連識別子 |
https://doi.org/10.3389/fphys.2023.1156286 |
| 出版者版URI |
|
|
関連タイプ |
isReplacedBy |
|
|
識別子タイプ |
URI |
|
|
関連識別子 |
https://www.frontiersin.org/journals/physiology/articles/10.3389/fphys.2023.1156286/full |
| 権利 |
|
|
権利情報Resource |
https://creativecommons.org/licenses/by/4.0/ |
|
権利情報 |
© 2023 Wang, Zhu, Izu, Chen-Izu, Ono, Altaf-Ul-Amin, Kanaya and Huang. This is an open-access article distributed under the terms of the Creative Commons Attribution License (CC BY). The use, distribution or reproduction in other forums is permitted, provided the original author(s) and the copyright owner(s) are credited and that the original publication in this journal is cited, in accordance with accepted academic practice. No use, distribution or reproduction is permitted which does not comply with these terms. |
| 著者版フラグ |
|
|
出版タイプ |
NA |
| 助成情報 |
|
|
|
助成機関名 |
Japan Society for the Promotion of Science (JSPS) |
|
|
研究課題番号 |
20K19923 |
|
|
研究課題番号URI |
https://kaken.nii.ac.jp/grant/KAKENHI-PROJECT-20K19923/ |
|
|
研究課題名 |
後天性因子により心臓の健康状態を解釈・推定する基盤技術の研究開発 |
