De novo generation of dual-target compounds using artificial intelligence

Summary: Drugs that interact with multiple therapeutic targets are potential high-value products in polypharmacology-based drug discovery, but the rational design remains a formidable challenge. Here, we present artificial intelligence (AI)-based methods to design the chemical structures of compound...

Full description

Saved in:
Bibliographic Details
Main Authors: Kasumi Yasuda, Francois Berenger, Kazuma Amaike, Ayaka Ueda, Tomoya Nakagomi, Genki Hamasaki, Chen Li, Noriko Yuyama Otani, Kazuma Kaitoh, Koji Tsuda, Kenichiro Itami, Yoshihiro Yamanishi
Format: Article
Language:English
Published: Elsevier 2025-01-01
Series:iScience
Subjects:
Online Access:http://www.sciencedirect.com/science/article/pii/S2589004224027536
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850249135400157184
author Kasumi Yasuda
Francois Berenger
Kazuma Amaike
Ayaka Ueda
Tomoya Nakagomi
Genki Hamasaki
Chen Li
Noriko Yuyama Otani
Kazuma Kaitoh
Koji Tsuda
Kenichiro Itami
Yoshihiro Yamanishi
author_facet Kasumi Yasuda
Francois Berenger
Kazuma Amaike
Ayaka Ueda
Tomoya Nakagomi
Genki Hamasaki
Chen Li
Noriko Yuyama Otani
Kazuma Kaitoh
Koji Tsuda
Kenichiro Itami
Yoshihiro Yamanishi
author_sort Kasumi Yasuda
collection DOAJ
description Summary: Drugs that interact with multiple therapeutic targets are potential high-value products in polypharmacology-based drug discovery, but the rational design remains a formidable challenge. Here, we present artificial intelligence (AI)-based methods to design the chemical structures of compounds that interact with multiple therapeutic target proteins. The molecular structure generation is performed by a fragment-based approach using a genetic algorithm with chemical substructures and a deep learning approach using reinforcement learning with stochastic policy gradients in the framework of generative adversarial networks. Using the proposed methods, we designed the chemical structures of compounds that would interact with two therapeutic targets of bronchial asthma, i.e., adenosine A2a receptor (ADORA2A) and phosphodiesterase 4D (PDE4D). We then synthesized 10 compounds and evaluated their bioactivities via the binding assays of 39 target human proteins, including ADORA2A and PDE4D. Three of the 10 synthesized compounds successfully interacted with ADORA2A and PDE4D with high specificity.
format Article
id doaj-art-ba6eec3db7f04145b4d70de86dec0301
institution OA Journals
issn 2589-0042
language English
publishDate 2025-01-01
publisher Elsevier
record_format Article
series iScience
spelling doaj-art-ba6eec3db7f04145b4d70de86dec03012025-08-20T01:58:33ZengElsevieriScience2589-00422025-01-0128111152610.1016/j.isci.2024.111526De novo generation of dual-target compounds using artificial intelligenceKasumi Yasuda0Francois Berenger1Kazuma Amaike2Ayaka Ueda3Tomoya Nakagomi4Genki Hamasaki5Chen Li6Noriko Yuyama Otani7Kazuma Kaitoh8Koji Tsuda9Kenichiro Itami10Yoshihiro Yamanishi11Department of Bioscience and Bioinformatics, Kyushu Institute of Technology, 680-4 Kawazu, Iizuka, Fukuoka 820-8502, JapanDepartment of Bioscience and Bioinformatics, Kyushu Institute of Technology, 680-4 Kawazu, Iizuka, Fukuoka 820-8502, Japan; Graduate School of Frontier Sciences, The University of Tokyo, 5-1-5 Kashiwa-no-ha, Kashiwa, Chiba 277-8561, JapanGraduate School of Science, Nagoya University, Chikusa, Nagoya, Aichi 464-8602, JapanGraduate School of Science, Nagoya University, Chikusa, Nagoya, Aichi 464-8602, JapanGraduate School of Science, Nagoya University, Chikusa, Nagoya, Aichi 464-8602, JapanDepartment of Bioscience and Bioinformatics, Kyushu Institute of Technology, 680-4 Kawazu, Iizuka, Fukuoka 820-8502, JapanDepartment of Bioscience and Bioinformatics, Kyushu Institute of Technology, 680-4 Kawazu, Iizuka, Fukuoka 820-8502, Japan; Graduate School of Informatics, Nagoya University, Chikusa, Nagoya, Aichi 464-8601, JapanDepartment of Bioscience and Bioinformatics, Kyushu Institute of Technology, 680-4 Kawazu, Iizuka, Fukuoka 820-8502, Japan; Graduate School of Informatics, Nagoya University, Chikusa, Nagoya, Aichi 464-8601, JapanDepartment of Bioscience and Bioinformatics, Kyushu Institute of Technology, 680-4 Kawazu, Iizuka, Fukuoka 820-8502, Japan; Graduate School of Informatics, Nagoya University, Chikusa, Nagoya, Aichi 464-8601, JapanGraduate School of Frontier Sciences, The University of Tokyo, 5-1-5 Kashiwa-no-ha, Kashiwa, Chiba 277-8561, JapanGraduate School of Science, Nagoya University, Chikusa, Nagoya, Aichi 464-8602, Japan; Institute of Transformative Bio-Molecules (WPI-ITbM), Nagoya University, Chikusa, Nagoya, Aichi 464-8602, JapanDepartment of Bioscience and Bioinformatics, Kyushu Institute of Technology, 680-4 Kawazu, Iizuka, Fukuoka 820-8502, Japan; Graduate School of Informatics, Nagoya University, Chikusa, Nagoya, Aichi 464-8601, Japan; Corresponding authorSummary: Drugs that interact with multiple therapeutic targets are potential high-value products in polypharmacology-based drug discovery, but the rational design remains a formidable challenge. Here, we present artificial intelligence (AI)-based methods to design the chemical structures of compounds that interact with multiple therapeutic target proteins. The molecular structure generation is performed by a fragment-based approach using a genetic algorithm with chemical substructures and a deep learning approach using reinforcement learning with stochastic policy gradients in the framework of generative adversarial networks. Using the proposed methods, we designed the chemical structures of compounds that would interact with two therapeutic targets of bronchial asthma, i.e., adenosine A2a receptor (ADORA2A) and phosphodiesterase 4D (PDE4D). We then synthesized 10 compounds and evaluated their bioactivities via the binding assays of 39 target human proteins, including ADORA2A and PDE4D. Three of the 10 synthesized compounds successfully interacted with ADORA2A and PDE4D with high specificity.http://www.sciencedirect.com/science/article/pii/S2589004224027536Natural sciencesBiological sciencesBioinformaticsPharmacoinformatics
spellingShingle Kasumi Yasuda
Francois Berenger
Kazuma Amaike
Ayaka Ueda
Tomoya Nakagomi
Genki Hamasaki
Chen Li
Noriko Yuyama Otani
Kazuma Kaitoh
Koji Tsuda
Kenichiro Itami
Yoshihiro Yamanishi
De novo generation of dual-target compounds using artificial intelligence
iScience
Natural sciences
Biological sciences
Bioinformatics
Pharmacoinformatics
title De novo generation of dual-target compounds using artificial intelligence
title_full De novo generation of dual-target compounds using artificial intelligence
title_fullStr De novo generation of dual-target compounds using artificial intelligence
title_full_unstemmed De novo generation of dual-target compounds using artificial intelligence
title_short De novo generation of dual-target compounds using artificial intelligence
title_sort de novo generation of dual target compounds using artificial intelligence
topic Natural sciences
Biological sciences
Bioinformatics
Pharmacoinformatics
url http://www.sciencedirect.com/science/article/pii/S2589004224027536
work_keys_str_mv AT kasumiyasuda denovogenerationofdualtargetcompoundsusingartificialintelligence
AT francoisberenger denovogenerationofdualtargetcompoundsusingartificialintelligence
AT kazumaamaike denovogenerationofdualtargetcompoundsusingartificialintelligence
AT ayakaueda denovogenerationofdualtargetcompoundsusingartificialintelligence
AT tomoyanakagomi denovogenerationofdualtargetcompoundsusingartificialintelligence
AT genkihamasaki denovogenerationofdualtargetcompoundsusingartificialintelligence
AT chenli denovogenerationofdualtargetcompoundsusingartificialintelligence
AT norikoyuyamaotani denovogenerationofdualtargetcompoundsusingartificialintelligence
AT kazumakaitoh denovogenerationofdualtargetcompoundsusingartificialintelligence
AT kojitsuda denovogenerationofdualtargetcompoundsusingartificialintelligence
AT kenichiroitami denovogenerationofdualtargetcompoundsusingartificialintelligence
AT yoshihiroyamanishi denovogenerationofdualtargetcompoundsusingartificialintelligence