Cargando…

Predicting hERG channel blockers with directed message passing neural networks

Compounds with human ether-à-go-go related gene (hERG) blockade activity may cause severe cardiotoxicity. Assessing the hERG liability in the early stages of the drug discovery process is important, and the in silico methods for predicting hERG channel blockers are actively pursued. In the present s...

Descripción completa

Detalles Bibliográficos
Autores principales: Shan, Mengyi, Jiang, Chen, Chen, Jing, Qin, Lu-Ping, Qin, Jiang-Jiang, Cheng, Gang
Formato: Online Artículo Texto
Lenguaje:English
Publicado: The Royal Society of Chemistry 2022
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8979305/
https://www.ncbi.nlm.nih.gov/pubmed/35425351
http://dx.doi.org/10.1039/d1ra07956e
_version_ 1784681148159361024
author Shan, Mengyi
Jiang, Chen
Chen, Jing
Qin, Lu-Ping
Qin, Jiang-Jiang
Cheng, Gang
author_facet Shan, Mengyi
Jiang, Chen
Chen, Jing
Qin, Lu-Ping
Qin, Jiang-Jiang
Cheng, Gang
author_sort Shan, Mengyi
collection PubMed
description Compounds with human ether-à-go-go related gene (hERG) blockade activity may cause severe cardiotoxicity. Assessing the hERG liability in the early stages of the drug discovery process is important, and the in silico methods for predicting hERG channel blockers are actively pursued. In the present study, the directed message passing neural network (D-MPNN) was applied to construct classification models for identifying hERG blockers based on diverse datasets. Several descriptors and fingerprints were tested along with the D-MPNN model. Among all these combinations, D-MPNN with the moe206 descriptors generated from MOE (D-MPNN + moe206) showed significantly improved performances. The AUC-ROC values of the D-MPNN + moe206 model reached 0.956 ± 0.005 under random split and 0.922 ± 0.015 under scaffold split on Cai's hERG dataset, respectively. Moreover, the comparisons between our models and several recently reported machine learning models were made based on various datasets. Our results indicated that the D-MPNN + moe206 model is among the best classification models. Overall, the excellent performance of the DMPNN + moe206 model achieved in this study highlights its potential application in the discovery of novel and effective hERG blockers.
format Online
Article
Text
id pubmed-8979305
institution National Center for Biotechnology Information
language English
publishDate 2022
publisher The Royal Society of Chemistry
record_format MEDLINE/PubMed
spelling pubmed-89793052022-04-13 Predicting hERG channel blockers with directed message passing neural networks Shan, Mengyi Jiang, Chen Chen, Jing Qin, Lu-Ping Qin, Jiang-Jiang Cheng, Gang RSC Adv Chemistry Compounds with human ether-à-go-go related gene (hERG) blockade activity may cause severe cardiotoxicity. Assessing the hERG liability in the early stages of the drug discovery process is important, and the in silico methods for predicting hERG channel blockers are actively pursued. In the present study, the directed message passing neural network (D-MPNN) was applied to construct classification models for identifying hERG blockers based on diverse datasets. Several descriptors and fingerprints were tested along with the D-MPNN model. Among all these combinations, D-MPNN with the moe206 descriptors generated from MOE (D-MPNN + moe206) showed significantly improved performances. The AUC-ROC values of the D-MPNN + moe206 model reached 0.956 ± 0.005 under random split and 0.922 ± 0.015 under scaffold split on Cai's hERG dataset, respectively. Moreover, the comparisons between our models and several recently reported machine learning models were made based on various datasets. Our results indicated that the D-MPNN + moe206 model is among the best classification models. Overall, the excellent performance of the DMPNN + moe206 model achieved in this study highlights its potential application in the discovery of novel and effective hERG blockers. The Royal Society of Chemistry 2022-01-26 /pmc/articles/PMC8979305/ /pubmed/35425351 http://dx.doi.org/10.1039/d1ra07956e Text en This journal is © The Royal Society of Chemistry https://creativecommons.org/licenses/by-nc/3.0/
spellingShingle Chemistry
Shan, Mengyi
Jiang, Chen
Chen, Jing
Qin, Lu-Ping
Qin, Jiang-Jiang
Cheng, Gang
Predicting hERG channel blockers with directed message passing neural networks
title Predicting hERG channel blockers with directed message passing neural networks
title_full Predicting hERG channel blockers with directed message passing neural networks
title_fullStr Predicting hERG channel blockers with directed message passing neural networks
title_full_unstemmed Predicting hERG channel blockers with directed message passing neural networks
title_short Predicting hERG channel blockers with directed message passing neural networks
title_sort predicting herg channel blockers with directed message passing neural networks
topic Chemistry
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8979305/
https://www.ncbi.nlm.nih.gov/pubmed/35425351
http://dx.doi.org/10.1039/d1ra07956e
work_keys_str_mv AT shanmengyi predictinghergchannelblockerswithdirectedmessagepassingneuralnetworks
AT jiangchen predictinghergchannelblockerswithdirectedmessagepassingneuralnetworks
AT chenjing predictinghergchannelblockerswithdirectedmessagepassingneuralnetworks
AT qinluping predictinghergchannelblockerswithdirectedmessagepassingneuralnetworks
AT qinjiangjiang predictinghergchannelblockerswithdirectedmessagepassingneuralnetworks
AT chenggang predictinghergchannelblockerswithdirectedmessagepassingneuralnetworks