DACPGTN: Drug ATC Code Prediction Method Based on Graph Transformer Network for Drug Discovery
The Anatomical Therapeutic Chemical (ATC) classification system is a drug classification scheme proposed by the World Health Organization, which is widely used for drug screening, repositioning, and similarity research. The ATC system assigns different ATC codes to drugs based on their anatomy, phar...
Main Authors: | , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
Frontiers Media S.A.
2022-06-01
|
Series: | Frontiers in Pharmacology |
Subjects: | |
Online Access: | https://www.frontiersin.org/articles/10.3389/fphar.2022.907676/full |
_version_ | 1811232962175303680 |
---|---|
author | Chaokun Yan Chaokun Yan Zhihao Suo Zhihao Suo Jianlin Wang Jianlin Wang Ge Zhang Ge Zhang Huimin Luo Huimin Luo |
author_facet | Chaokun Yan Chaokun Yan Zhihao Suo Zhihao Suo Jianlin Wang Jianlin Wang Ge Zhang Ge Zhang Huimin Luo Huimin Luo |
author_sort | Chaokun Yan |
collection | DOAJ |
description | The Anatomical Therapeutic Chemical (ATC) classification system is a drug classification scheme proposed by the World Health Organization, which is widely used for drug screening, repositioning, and similarity research. The ATC system assigns different ATC codes to drugs based on their anatomy, pharmacological, therapeutics and chemical properties. Predicting the ATC code of a given drug helps to understand the indication and potential toxicity of the drug, thus promoting its use in the therapeutic phase and accelerating its development. In this article, we propose an end-to-end model DACPGTN to predict the ATC code for the given drug. DACPGTN constructs composite features of drugs, diseases and targets by applying diverse biomedical information. Inspired by the application of Graph Transformer Network, we learn potential novel interactions among drugs diseases and targets from the known interactions to construct drug-target-disease heterogeneous networks containing comprehensive interaction information. Based on the constructed composite features and learned heterogeneous networks, we employ graph convolution network to generate the embedding of drug nodes, which are further used for the multi-label learning tasks in drug discovery. Experiments on the benchmark datasets demonstrate that the proposed DACPGTN model can achieve better prediction performance than the existing methods. The source codes of our method are available at https://github.com/Szhgege/DACPGTN. |
first_indexed | 2024-04-12T11:12:00Z |
format | Article |
id | doaj.art-2892072ebf464363b689b013a86b812e |
institution | Directory Open Access Journal |
issn | 1663-9812 |
language | English |
last_indexed | 2024-04-12T11:12:00Z |
publishDate | 2022-06-01 |
publisher | Frontiers Media S.A. |
record_format | Article |
series | Frontiers in Pharmacology |
spelling | doaj.art-2892072ebf464363b689b013a86b812e2022-12-22T03:35:35ZengFrontiers Media S.A.Frontiers in Pharmacology1663-98122022-06-011310.3389/fphar.2022.907676907676DACPGTN: Drug ATC Code Prediction Method Based on Graph Transformer Network for Drug DiscoveryChaokun Yan0Chaokun Yan1Zhihao Suo2Zhihao Suo3Jianlin Wang4Jianlin Wang5Ge Zhang6Ge Zhang7Huimin Luo8Huimin Luo9School of Computer and Information Engineering, Henan University, Kaifeng, ChinaHenan Key Laboratory of Big Data Analysis and Processing, Henan University, Kaifeng, ChinaSchool of Computer and Information Engineering, Henan University, Kaifeng, ChinaHenan Key Laboratory of Big Data Analysis and Processing, Henan University, Kaifeng, ChinaSchool of Computer and Information Engineering, Henan University, Kaifeng, ChinaHenan Key Laboratory of Big Data Analysis and Processing, Henan University, Kaifeng, ChinaSchool of Computer and Information Engineering, Henan University, Kaifeng, ChinaHenan Key Laboratory of Big Data Analysis and Processing, Henan University, Kaifeng, ChinaSchool of Computer and Information Engineering, Henan University, Kaifeng, ChinaHenan Key Laboratory of Big Data Analysis and Processing, Henan University, Kaifeng, ChinaThe Anatomical Therapeutic Chemical (ATC) classification system is a drug classification scheme proposed by the World Health Organization, which is widely used for drug screening, repositioning, and similarity research. The ATC system assigns different ATC codes to drugs based on their anatomy, pharmacological, therapeutics and chemical properties. Predicting the ATC code of a given drug helps to understand the indication and potential toxicity of the drug, thus promoting its use in the therapeutic phase and accelerating its development. In this article, we propose an end-to-end model DACPGTN to predict the ATC code for the given drug. DACPGTN constructs composite features of drugs, diseases and targets by applying diverse biomedical information. Inspired by the application of Graph Transformer Network, we learn potential novel interactions among drugs diseases and targets from the known interactions to construct drug-target-disease heterogeneous networks containing comprehensive interaction information. Based on the constructed composite features and learned heterogeneous networks, we employ graph convolution network to generate the embedding of drug nodes, which are further used for the multi-label learning tasks in drug discovery. Experiments on the benchmark datasets demonstrate that the proposed DACPGTN model can achieve better prediction performance than the existing methods. The source codes of our method are available at https://github.com/Szhgege/DACPGTN.https://www.frontiersin.org/articles/10.3389/fphar.2022.907676/fulldrug ATC codemulti-label classificationinteraction informationdrug discoverygraph transformer network |
spellingShingle | Chaokun Yan Chaokun Yan Zhihao Suo Zhihao Suo Jianlin Wang Jianlin Wang Ge Zhang Ge Zhang Huimin Luo Huimin Luo DACPGTN: Drug ATC Code Prediction Method Based on Graph Transformer Network for Drug Discovery Frontiers in Pharmacology drug ATC code multi-label classification interaction information drug discovery graph transformer network |
title | DACPGTN: Drug ATC Code Prediction Method Based on Graph Transformer Network for Drug Discovery |
title_full | DACPGTN: Drug ATC Code Prediction Method Based on Graph Transformer Network for Drug Discovery |
title_fullStr | DACPGTN: Drug ATC Code Prediction Method Based on Graph Transformer Network for Drug Discovery |
title_full_unstemmed | DACPGTN: Drug ATC Code Prediction Method Based on Graph Transformer Network for Drug Discovery |
title_short | DACPGTN: Drug ATC Code Prediction Method Based on Graph Transformer Network for Drug Discovery |
title_sort | dacpgtn drug atc code prediction method based on graph transformer network for drug discovery |
topic | drug ATC code multi-label classification interaction information drug discovery graph transformer network |
url | https://www.frontiersin.org/articles/10.3389/fphar.2022.907676/full |
work_keys_str_mv | AT chaokunyan dacpgtndrugatccodepredictionmethodbasedongraphtransformernetworkfordrugdiscovery AT chaokunyan dacpgtndrugatccodepredictionmethodbasedongraphtransformernetworkfordrugdiscovery AT zhihaosuo dacpgtndrugatccodepredictionmethodbasedongraphtransformernetworkfordrugdiscovery AT zhihaosuo dacpgtndrugatccodepredictionmethodbasedongraphtransformernetworkfordrugdiscovery AT jianlinwang dacpgtndrugatccodepredictionmethodbasedongraphtransformernetworkfordrugdiscovery AT jianlinwang dacpgtndrugatccodepredictionmethodbasedongraphtransformernetworkfordrugdiscovery AT gezhang dacpgtndrugatccodepredictionmethodbasedongraphtransformernetworkfordrugdiscovery AT gezhang dacpgtndrugatccodepredictionmethodbasedongraphtransformernetworkfordrugdiscovery AT huiminluo dacpgtndrugatccodepredictionmethodbasedongraphtransformernetworkfordrugdiscovery AT huiminluo dacpgtndrugatccodepredictionmethodbasedongraphtransformernetworkfordrugdiscovery |