Prediction of pharmacological activities from chemical structures with graph convolutional neural networks

Abstract Many therapeutic drugs are compounds that can be represented by simple chemical structures, which contain important determinants of affinity at the site of action. Recently, graph convolutional neural network (GCN) models have exhibited excellent results in classifying the activity of such...

Descripción completa

Guardado en:
Detalles Bibliográficos
Autores principales: Miyuki Sakai, Kazuki Nagayasu, Norihiro Shibui, Chihiro Andoh, Kaito Takayama, Hisashi Shirakawa, Shuji Kaneko
Formato: article
Lenguaje:EN
Publicado: Nature Portfolio 2021
Materias:
R
Q
Acceso en línea:https://doaj.org/article/e24b906189ad43caa5818c58ca25debc
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
id oai:doaj.org-article:e24b906189ad43caa5818c58ca25debc
record_format dspace
spelling oai:doaj.org-article:e24b906189ad43caa5818c58ca25debc2021-12-02T14:12:10ZPrediction of pharmacological activities from chemical structures with graph convolutional neural networks10.1038/s41598-020-80113-72045-2322https://doaj.org/article/e24b906189ad43caa5818c58ca25debc2021-01-01T00:00:00Zhttps://doi.org/10.1038/s41598-020-80113-7https://doaj.org/toc/2045-2322Abstract Many therapeutic drugs are compounds that can be represented by simple chemical structures, which contain important determinants of affinity at the site of action. Recently, graph convolutional neural network (GCN) models have exhibited excellent results in classifying the activity of such compounds. For models that make quantitative predictions of activity, more complex information has been utilized, such as the three-dimensional structures of compounds and the amino acid sequences of their respective target proteins. As another approach, we hypothesized that if sufficient experimental data were available and there were enough nodes in hidden layers, a simple compound representation would quantitatively predict activity with satisfactory accuracy. In this study, we report that GCN models constructed solely from the two-dimensional structural information of compounds demonstrated a high degree of activity predictability against 127 diverse targets from the ChEMBL database. Using the information entropy as a metric, we also show that the structural diversity had less effect on the prediction performance. Finally, we report that virtual screening using the constructed model identified a new serotonin transporter inhibitor with activity comparable to that of a marketed drug in vitro and exhibited antidepressant effects in behavioural studies.Miyuki SakaiKazuki NagayasuNorihiro ShibuiChihiro AndohKaito TakayamaHisashi ShirakawaShuji KanekoNature PortfolioarticleMedicineRScienceQENScientific Reports, Vol 11, Iss 1, Pp 1-14 (2021)
institution DOAJ
collection DOAJ
language EN
topic Medicine
R
Science
Q
spellingShingle Medicine
R
Science
Q
Miyuki Sakai
Kazuki Nagayasu
Norihiro Shibui
Chihiro Andoh
Kaito Takayama
Hisashi Shirakawa
Shuji Kaneko
Prediction of pharmacological activities from chemical structures with graph convolutional neural networks
description Abstract Many therapeutic drugs are compounds that can be represented by simple chemical structures, which contain important determinants of affinity at the site of action. Recently, graph convolutional neural network (GCN) models have exhibited excellent results in classifying the activity of such compounds. For models that make quantitative predictions of activity, more complex information has been utilized, such as the three-dimensional structures of compounds and the amino acid sequences of their respective target proteins. As another approach, we hypothesized that if sufficient experimental data were available and there were enough nodes in hidden layers, a simple compound representation would quantitatively predict activity with satisfactory accuracy. In this study, we report that GCN models constructed solely from the two-dimensional structural information of compounds demonstrated a high degree of activity predictability against 127 diverse targets from the ChEMBL database. Using the information entropy as a metric, we also show that the structural diversity had less effect on the prediction performance. Finally, we report that virtual screening using the constructed model identified a new serotonin transporter inhibitor with activity comparable to that of a marketed drug in vitro and exhibited antidepressant effects in behavioural studies.
format article
author Miyuki Sakai
Kazuki Nagayasu
Norihiro Shibui
Chihiro Andoh
Kaito Takayama
Hisashi Shirakawa
Shuji Kaneko
author_facet Miyuki Sakai
Kazuki Nagayasu
Norihiro Shibui
Chihiro Andoh
Kaito Takayama
Hisashi Shirakawa
Shuji Kaneko
author_sort Miyuki Sakai
title Prediction of pharmacological activities from chemical structures with graph convolutional neural networks
title_short Prediction of pharmacological activities from chemical structures with graph convolutional neural networks
title_full Prediction of pharmacological activities from chemical structures with graph convolutional neural networks
title_fullStr Prediction of pharmacological activities from chemical structures with graph convolutional neural networks
title_full_unstemmed Prediction of pharmacological activities from chemical structures with graph convolutional neural networks
title_sort prediction of pharmacological activities from chemical structures with graph convolutional neural networks
publisher Nature Portfolio
publishDate 2021
url https://doaj.org/article/e24b906189ad43caa5818c58ca25debc
work_keys_str_mv AT miyukisakai predictionofpharmacologicalactivitiesfromchemicalstructureswithgraphconvolutionalneuralnetworks
AT kazukinagayasu predictionofpharmacologicalactivitiesfromchemicalstructureswithgraphconvolutionalneuralnetworks
AT norihiroshibui predictionofpharmacologicalactivitiesfromchemicalstructureswithgraphconvolutionalneuralnetworks
AT chihiroandoh predictionofpharmacologicalactivitiesfromchemicalstructureswithgraphconvolutionalneuralnetworks
AT kaitotakayama predictionofpharmacologicalactivitiesfromchemicalstructureswithgraphconvolutionalneuralnetworks
AT hisashishirakawa predictionofpharmacologicalactivitiesfromchemicalstructureswithgraphconvolutionalneuralnetworks
AT shujikaneko predictionofpharmacologicalactivitiesfromchemicalstructureswithgraphconvolutionalneuralnetworks
_version_ 1718391816987869184