JOURNALS
2025
2.
Dohyeon Lee; Sunyong Yoo
Abstract | Links | BibTeX | Dimensions | Tags: Artificial Intelligence, Attention mechanism, Bioinformatics, Cardiotoxicity, Deep learning, Graph attention network
@article{Lee2025,
title = {hERGAT: predicting hERG blockers using graph attention mechanism through atom- and molecule-level interaction analyses},
author = {Dohyeon Lee and Sunyong Yoo},
url = {https://link.springer.com/article/10.1186/s13321-025-00957-x?utm_source=rct_congratemailt&utm_medium=email&utm_campaign=oa_20250128&utm_content=10.1186/s13321-025-00957-x},
doi = {10.1186/s13321-025-00957-x},
issn = {1758-2946},
year = {2025},
date = {2025-01-28},
urldate = {2025-01-28},
journal = {Journal of Cheminformatics},
volume = {17},
number = {11},
abstract = {The human ether-a-go-go-related gene (hERG) channel plays a critical role in the electrical activity of the heart, and its blockers can cause serious cardiotoxic effects. Thus, screening for hERG channel blockers is a crucial step in the drug development process. Many in silico models have been developed to predict hERG blockers, which can efficiently save time and resources. However, previous methods have found it hard to achieve high performance and to interpret the predictive results. To overcome these challenges, we have proposed hERGAT, a graph neural network model with an attention mechanism, to consider compound interactions on atomic and molecular levels. In the atom-level interaction analysis, we applied a graph attention mechanism (GAT) that integrates information from neighboring nodes and their extended connections. The hERGAT employs a gated recurrent unit (GRU) with the GAT to learn information between more distant atoms. To confirm this, we performed clustering analysis and visualized a correlation heatmap, verifying the interactions between distant atoms were considered during the training process. In the molecule-level interaction analysis, the attention mechanism enables the target node to focus on the most relevant information, highlighting the molecular substructures that play crucial roles in predicting hERG blockers. Through a literature review, we confirmed that highlighted substructures have a significant role in determining the chemical and biological characteristics related to hERG activity. Furthermore, we integrated physicochemical properties into our hERGAT model to improve the performance. Our model achieved an area under the receiver operating characteristic of 0.907 and an area under the precision-recall of 0.904, demonstrating its effectiveness in modeling hERG activity and offering a reliable framework for optimizing drug safety in early development stages.},
note = {Correspondence to Sunyong Yoo},
keywords = {Artificial Intelligence, Attention mechanism, Bioinformatics, Cardiotoxicity, Deep learning, Graph attention network},
pubstate = {published},
tppubtype = {article}
}
The human ether-a-go-go-related gene (hERG) channel plays a critical role in the electrical activity of the heart, and its blockers can cause serious cardiotoxic effects. Thus, screening for hERG channel blockers is a crucial step in the drug development process. Many in silico models have been developed to predict hERG blockers, which can efficiently save time and resources. However, previous methods have found it hard to achieve high performance and to interpret the predictive results. To overcome these challenges, we have proposed hERGAT, a graph neural network model with an attention mechanism, to consider compound interactions on atomic and molecular levels. In the atom-level interaction analysis, we applied a graph attention mechanism (GAT) that integrates information from neighboring nodes and their extended connections. The hERGAT employs a gated recurrent unit (GRU) with the GAT to learn information between more distant atoms. To confirm this, we performed clustering analysis and visualized a correlation heatmap, verifying the interactions between distant atoms were considered during the training process. In the molecule-level interaction analysis, the attention mechanism enables the target node to focus on the most relevant information, highlighting the molecular substructures that play crucial roles in predicting hERG blockers. Through a literature review, we confirmed that highlighted substructures have a significant role in determining the chemical and biological characteristics related to hERG activity. Furthermore, we integrated physicochemical properties into our hERGAT model to improve the performance. Our model achieved an area under the receiver operating characteristic of 0.907 and an area under the precision-recall of 0.904, demonstrating its effectiveness in modeling hERG activity and offering a reliable framework for optimizing drug safety in early development stages.
2024
1.
이도현; 유선용
Abstract | Links | BibTeX | Dimensions | Tags: Bioinformatics, Cardiotoxicity, Graph attention network
@article{nokey,
title = {메시지 패싱 그래프 기반 딥러닝 모델을 활용한 화합물의 심장독성 예측},
author = {이도현 and 유선용},
url = {https://www.dbpia.co.kr/journal/articleDetail?nodeId=NODE11956044},
doi = {10.9728/dcs.2024.25.10.2961},
isbn = {1598-2009},
year = {2024},
date = {2024-01-01},
urldate = {2024-01-01},
journal = {한국디지털콘텐츠학회},
volume = {25},
number = {10},
pages = {2961-2968},
abstract = {hERG 채널은 심장의 전기 활동에 필수적이며, 이 채널을 차단하는 물질은 심각한 심장 독성 효과를 일으킬 수 있다. 인실리코 예측 모델은 hERG 차단제를 효율적으로 선별할 수 있어 시간과 자원을 절약할 수 있다. 이전 접근법은 예측 결과를 해석하고 분자 구조-기능 관계를 이해하는 데 어렵다. 본 연구에서는 공개 데이터베이스로부터 화합물을 수집하여 12,920개의 데이터셋을 구축 하였다. 화합물의 그래프 구조를 고려하는 그래프 신경망(GNN) 가운데 메시지 패싱 신경망(MPNN)을 활용하여 특징 벡터를 추출하고, 이를 구조적ㆍ물리화학적 특성과 결합하여 최종 hERG 차단제를 예측하였다. 해당 모델은 AUROC는 0.864 (±0.009), AUPR은 0.907 (±0.010)의 성능을 달성하였다. 실험 결과, 제안된 모델은 그래프 특징 벡터를 통합하여 분자 특성을 효과적으로 반영하고 분자 간의 관계를 예측하여 hERG 차단제를 예측할 수 있음을 시사한다. 본 연구는 약물 개발과정에서 예비 도구로 활용되어 심장독성을 조기에 평가할 수 있을 것이다.},
note = {Correspondence to Sunyong Yoo},
keywords = {Bioinformatics, Cardiotoxicity, Graph attention network},
pubstate = {published},
tppubtype = {article}
}
hERG 채널은 심장의 전기 활동에 필수적이며, 이 채널을 차단하는 물질은 심각한 심장 독성 효과를 일으킬 수 있다. 인실리코 예측 모델은 hERG 차단제를 효율적으로 선별할 수 있어 시간과 자원을 절약할 수 있다. 이전 접근법은 예측 결과를 해석하고 분자 구조-기능 관계를 이해하는 데 어렵다. 본 연구에서는 공개 데이터베이스로부터 화합물을 수집하여 12,920개의 데이터셋을 구축 하였다. 화합물의 그래프 구조를 고려하는 그래프 신경망(GNN) 가운데 메시지 패싱 신경망(MPNN)을 활용하여 특징 벡터를 추출하고, 이를 구조적ㆍ물리화학적 특성과 결합하여 최종 hERG 차단제를 예측하였다. 해당 모델은 AUROC는 0.864 (±0.009), AUPR은 0.907 (±0.010)의 성능을 달성하였다. 실험 결과, 제안된 모델은 그래프 특징 벡터를 통합하여 분자 특성을 효과적으로 반영하고 분자 간의 관계를 예측하여 hERG 차단제를 예측할 수 있음을 시사한다. 본 연구는 약물 개발과정에서 예비 도구로 활용되어 심장독성을 조기에 평가할 수 있을 것이다.