Discovery of EP4 antagonists with image-guided explainable deep learning workflow

In target-based drug design, the manual creation of a poor initial compound library, the time-consuming wet-laboratory experimental screening method, and the weak explainability of their activity against compounds significantly limit the efficiency of discovering novel therapeutics. Here we propose...

Full description

Saved in:
Bibliographic Details
Main Authors: Ma Pengsen, Cheng Zhiyuan, Cheng Zhixiang, Wang Yijie, Chai Xiaolei, Feng Bo, Xiang Hongxin, Zeng Li, Liu Xueming, Li Pengyong, Wei Leyi, Zou Quan, Liu Mingyao, Zeng Xiangxiang, Lu Weiqiang
Format: Article
Language:English
Published: Science Press 2025-06-01
Series:National Science Open
Subjects:
Online Access:https://www.sciengine.com/doi/10.1360/nso/20240015
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849720244781711360
author Ma Pengsen
Cheng Zhiyuan
Cheng Zhixiang
Wang Yijie
Chai Xiaolei
Feng Bo
Xiang Hongxin
Zeng Li
Liu Xueming
Li Pengyong
Wei Leyi
Zou Quan
Liu Mingyao
Zeng Xiangxiang
Lu Weiqiang
author_facet Ma Pengsen
Cheng Zhiyuan
Cheng Zhixiang
Wang Yijie
Chai Xiaolei
Feng Bo
Xiang Hongxin
Zeng Li
Liu Xueming
Li Pengyong
Wei Leyi
Zou Quan
Liu Mingyao
Zeng Xiangxiang
Lu Weiqiang
author_sort Ma Pengsen
collection DOAJ
description In target-based drug design, the manual creation of a poor initial compound library, the time-consuming wet-laboratory experimental screening method, and the weak explainability of their activity against compounds significantly limit the efficiency of discovering novel therapeutics. Here we propose an image-guided, interpretability deep learning workflow, named LeadDisFlow, to enable rapid, accurate target drug discovery. Using LeadDisFlow, we identified four potent antagonists with single-nanomolar antagonistic activity against PGE<sub>2</sub> receptor subtype 4 (EP4), a promising target for tumor immunotherapy. Remarkably, the most potent EP4 antagonist, ZY001, demonstrated an IC<sub>50</sub> value of (0.51 ± 0.02) nM, along with high selectivity. Furthermore, ZY001 effectively impaired the PGE<sub>2</sub>-induced gene expression of a panel of immunosuppressive molecules in macrophages. The workflow facilitates the discovery of potent EP4 antagonists that enhance anti-tumor immune response, and provides a convenient and quick approach to discover promising therapeutics for a specific drug target.
format Article
id doaj-art-32d6dfa1452346fbb794378db610c620
institution DOAJ
issn 2097-1168
language English
publishDate 2025-06-01
publisher Science Press
record_format Article
series National Science Open
spelling doaj-art-32d6dfa1452346fbb794378db610c6202025-08-20T03:11:58ZengScience PressNational Science Open2097-11682025-06-01410.1360/nso/20240015eb33e642Discovery of EP4 antagonists with image-guided explainable deep learning workflowMa Pengsen0Cheng Zhiyuan1Cheng Zhixiang2Wang Yijie3Chai Xiaolei4Feng Bo5Xiang Hongxin6Zeng Li7Liu Xueming8Li Pengyong9Wei Leyi10Zou Quan11Liu Mingyao12Zeng Xiangxiang13Lu Weiqiang14["College of Information Science and Engineering, Hunan University, Changsha 410082, China"]["Shanghai Key Laboratory of Regulatory Biology, Institute of Biomedical Sciences and School of Life Sciences, Shanghai 200241, China"]["College of Information Science and Engineering, Hunan University, Changsha 410082, China"]["Shanghai Key Laboratory of Regulatory Biology, Institute of Biomedical Sciences and School of Life Sciences, Shanghai 200241, China"]["Shanghai Key Laboratory of Regulatory Biology, Institute of Biomedical Sciences and School of Life Sciences, Shanghai 200241, China"]["Department of General Surgery, Ruijin Hospital, Shanghai Jiao Tong University School of Medicine, Shanghai 200025, China"]["College of Information Science and Engineering, Hunan University, Changsha 410082, China"]["Department of AIDD, Shanghai Yuyao Biotechnology Co., Ltd., Shanghai 201109, China"]["Key Laboratory of Image Processing and Intelligent Control, School of Artificial Intelligence and Automation, Huazhong University of Science and Technology, Wuhan 430074, China"]["School of Computer Science and Technology, Xidian University, Xi’an 710071, China"]["School of Software, Shandong University, Jinan 250000, China"]["Institute of Fundamental and Frontier Sciences, University of Electronic Science and Technology of China, Chengdu 611731, China"]["Shanghai Key Laboratory of Regulatory Biology, Institute of Biomedical Sciences and School of Life Sciences, Shanghai 200241, China","Department of AIDD, Shanghai Yuyao Biotechnology Co., Ltd., Shanghai 201109, China","Hainan Academy of Medical Sciences, Hainan Medical University, Haikou 570311, China"]["College of Information Science and Engineering, Hunan University, Changsha 410082, China"]["Shanghai Key Laboratory of Regulatory Biology, Institute of Biomedical Sciences and School of Life Sciences, Shanghai 200241, China","Hainan Academy of Medical Sciences, Hainan Medical University, Haikou 570311, China"]In target-based drug design, the manual creation of a poor initial compound library, the time-consuming wet-laboratory experimental screening method, and the weak explainability of their activity against compounds significantly limit the efficiency of discovering novel therapeutics. Here we propose an image-guided, interpretability deep learning workflow, named LeadDisFlow, to enable rapid, accurate target drug discovery. Using LeadDisFlow, we identified four potent antagonists with single-nanomolar antagonistic activity against PGE<sub>2</sub> receptor subtype 4 (EP4), a promising target for tumor immunotherapy. Remarkably, the most potent EP4 antagonist, ZY001, demonstrated an IC<sub>50</sub> value of (0.51 ± 0.02) nM, along with high selectivity. Furthermore, ZY001 effectively impaired the PGE<sub>2</sub>-induced gene expression of a panel of immunosuppressive molecules in macrophages. The workflow facilitates the discovery of potent EP4 antagonists that enhance anti-tumor immune response, and provides a convenient and quick approach to discover promising therapeutics for a specific drug target.https://www.sciengine.com/doi/10.1360/nso/20240015drug discoveryPGE<sub>2</sub> receptor subtype 4antagonistdeep learningcomputer vision
spellingShingle Ma Pengsen
Cheng Zhiyuan
Cheng Zhixiang
Wang Yijie
Chai Xiaolei
Feng Bo
Xiang Hongxin
Zeng Li
Liu Xueming
Li Pengyong
Wei Leyi
Zou Quan
Liu Mingyao
Zeng Xiangxiang
Lu Weiqiang
Discovery of EP4 antagonists with image-guided explainable deep learning workflow
National Science Open
drug discovery
PGE<sub>2</sub> receptor subtype 4
antagonist
deep learning
computer vision
title Discovery of EP4 antagonists with image-guided explainable deep learning workflow
title_full Discovery of EP4 antagonists with image-guided explainable deep learning workflow
title_fullStr Discovery of EP4 antagonists with image-guided explainable deep learning workflow
title_full_unstemmed Discovery of EP4 antagonists with image-guided explainable deep learning workflow
title_short Discovery of EP4 antagonists with image-guided explainable deep learning workflow
title_sort discovery of ep4 antagonists with image guided explainable deep learning workflow
topic drug discovery
PGE<sub>2</sub> receptor subtype 4
antagonist
deep learning
computer vision
url https://www.sciengine.com/doi/10.1360/nso/20240015
work_keys_str_mv AT mapengsen discoveryofep4antagonistswithimageguidedexplainabledeeplearningworkflow
AT chengzhiyuan discoveryofep4antagonistswithimageguidedexplainabledeeplearningworkflow
AT chengzhixiang discoveryofep4antagonistswithimageguidedexplainabledeeplearningworkflow
AT wangyijie discoveryofep4antagonistswithimageguidedexplainabledeeplearningworkflow
AT chaixiaolei discoveryofep4antagonistswithimageguidedexplainabledeeplearningworkflow
AT fengbo discoveryofep4antagonistswithimageguidedexplainabledeeplearningworkflow
AT xianghongxin discoveryofep4antagonistswithimageguidedexplainabledeeplearningworkflow
AT zengli discoveryofep4antagonistswithimageguidedexplainabledeeplearningworkflow
AT liuxueming discoveryofep4antagonistswithimageguidedexplainabledeeplearningworkflow
AT lipengyong discoveryofep4antagonistswithimageguidedexplainabledeeplearningworkflow
AT weileyi discoveryofep4antagonistswithimageguidedexplainabledeeplearningworkflow
AT zouquan discoveryofep4antagonistswithimageguidedexplainabledeeplearningworkflow
AT liumingyao discoveryofep4antagonistswithimageguidedexplainabledeeplearningworkflow
AT zengxiangxiang discoveryofep4antagonistswithimageguidedexplainabledeeplearningworkflow
AT luweiqiang discoveryofep4antagonistswithimageguidedexplainabledeeplearningworkflow