Generative artificial intelligence based models optimization towards molecule design enhancement

Abstract Generative artificial intelligence (GenAI) models have emerged as a transformative tool for addressing the complex challenges of drug discovery, enabling the design of structurally diverse, chemically valid, and functionally relevant molecules. Despite significant advancements, the rapid ex...

Full description

Saved in:
Bibliographic Details
Main Authors: Tarek Khater, Sara Awni Alkhatib, Aamna AlShehhi, Charalampos Pitsalidis, Anna Maria Pappa, Son Tung Ngo, Vincent Chan, Vi Khanh Truong
Format: Article
Language:English
Published: BMC 2025-08-01
Series:Journal of Cheminformatics
Subjects:
Online Access:https://doi.org/10.1186/s13321-025-01059-4
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849331973826281472
author Tarek Khater
Sara Awni Alkhatib
Aamna AlShehhi
Charalampos Pitsalidis
Anna Maria Pappa
Son Tung Ngo
Vincent Chan
Vi Khanh Truong
author_facet Tarek Khater
Sara Awni Alkhatib
Aamna AlShehhi
Charalampos Pitsalidis
Anna Maria Pappa
Son Tung Ngo
Vincent Chan
Vi Khanh Truong
author_sort Tarek Khater
collection DOAJ
description Abstract Generative artificial intelligence (GenAI) models have emerged as a transformative tool for addressing the complex challenges of drug discovery, enabling the design of structurally diverse, chemically valid, and functionally relevant molecules. Despite significant advancements, the rapid expansion of GenAI applications still faces challenges related to prediction accuracy, molecular validity, and optimization for drug-like properties. This review provides a comprehensive analysis of recent techniques and strategies aimed at enhancing the performance of GenAI models in molecular design. We explore key generative architectures, including variational autoencoders, generative adversarial networks, and transformer-based models, highlighting their unique contributions to drug discovery. Additionally, we discuss critical advancements such as reinforcement learning, multi-objective optimization, and the integration of domain-specific chemical knowledge, which collectively enhance molecular validity, novelty, and drug-likeness. Also, the review examines persistent challenges, including data quality limitations, model interpretability, and the need for improved objective functions, while offering insights into future research directions. By mapping the evolving landscape of GenAI-driven molecular design and providing strategic guidance for overcoming existing limitations, this review serves as an essential resource for researchers leveraging GenAI in drug discovery.
format Article
id doaj-art-5e2cbf976ca84c8ab1288164cc3566f4
institution Kabale University
issn 1758-2946
language English
publishDate 2025-08-01
publisher BMC
record_format Article
series Journal of Cheminformatics
spelling doaj-art-5e2cbf976ca84c8ab1288164cc3566f42025-08-20T03:46:21ZengBMCJournal of Cheminformatics1758-29462025-08-0117112010.1186/s13321-025-01059-4Generative artificial intelligence based models optimization towards molecule design enhancementTarek Khater0Sara Awni Alkhatib1Aamna AlShehhi2Charalampos Pitsalidis3Anna Maria Pappa4Son Tung Ngo5Vincent Chan6Vi Khanh Truong7Department of Biomedical Engineering and Biotechnology, Khalifa UniversityDepartment of Biomedical Engineering and Biotechnology, Khalifa UniversityDepartment of Biomedical Engineering and Biotechnology, Khalifa UniversityDepartment of Physics, Khalifa UniversityDepartment of Biomedical Engineering and Biotechnology, Khalifa UniversityLaboratory of Biophysics, Institute for Advanced Study in Technology, Ton Duc Thang UniversityDepartment of Biomedical Engineering and Biotechnology, Khalifa UniversityDepartment of Biomedical Engineering and Biotechnology, Khalifa UniversityAbstract Generative artificial intelligence (GenAI) models have emerged as a transformative tool for addressing the complex challenges of drug discovery, enabling the design of structurally diverse, chemically valid, and functionally relevant molecules. Despite significant advancements, the rapid expansion of GenAI applications still faces challenges related to prediction accuracy, molecular validity, and optimization for drug-like properties. This review provides a comprehensive analysis of recent techniques and strategies aimed at enhancing the performance of GenAI models in molecular design. We explore key generative architectures, including variational autoencoders, generative adversarial networks, and transformer-based models, highlighting their unique contributions to drug discovery. Additionally, we discuss critical advancements such as reinforcement learning, multi-objective optimization, and the integration of domain-specific chemical knowledge, which collectively enhance molecular validity, novelty, and drug-likeness. Also, the review examines persistent challenges, including data quality limitations, model interpretability, and the need for improved objective functions, while offering insights into future research directions. By mapping the evolving landscape of GenAI-driven molecular design and providing strategic guidance for overcoming existing limitations, this review serves as an essential resource for researchers leveraging GenAI in drug discovery.https://doi.org/10.1186/s13321-025-01059-4Generative AIMolecular designOptimizationReinforcement learningChemical informaticsDrug discovery
spellingShingle Tarek Khater
Sara Awni Alkhatib
Aamna AlShehhi
Charalampos Pitsalidis
Anna Maria Pappa
Son Tung Ngo
Vincent Chan
Vi Khanh Truong
Generative artificial intelligence based models optimization towards molecule design enhancement
Journal of Cheminformatics
Generative AI
Molecular design
Optimization
Reinforcement learning
Chemical informatics
Drug discovery
title Generative artificial intelligence based models optimization towards molecule design enhancement
title_full Generative artificial intelligence based models optimization towards molecule design enhancement
title_fullStr Generative artificial intelligence based models optimization towards molecule design enhancement
title_full_unstemmed Generative artificial intelligence based models optimization towards molecule design enhancement
title_short Generative artificial intelligence based models optimization towards molecule design enhancement
title_sort generative artificial intelligence based models optimization towards molecule design enhancement
topic Generative AI
Molecular design
Optimization
Reinforcement learning
Chemical informatics
Drug discovery
url https://doi.org/10.1186/s13321-025-01059-4
work_keys_str_mv AT tarekkhater generativeartificialintelligencebasedmodelsoptimizationtowardsmoleculedesignenhancement
AT saraawnialkhatib generativeartificialintelligencebasedmodelsoptimizationtowardsmoleculedesignenhancement
AT aamnaalshehhi generativeartificialintelligencebasedmodelsoptimizationtowardsmoleculedesignenhancement
AT charalampospitsalidis generativeartificialintelligencebasedmodelsoptimizationtowardsmoleculedesignenhancement
AT annamariapappa generativeartificialintelligencebasedmodelsoptimizationtowardsmoleculedesignenhancement
AT sontungngo generativeartificialintelligencebasedmodelsoptimizationtowardsmoleculedesignenhancement
AT vincentchan generativeartificialintelligencebasedmodelsoptimizationtowardsmoleculedesignenhancement
AT vikhanhtruong generativeartificialintelligencebasedmodelsoptimizationtowardsmoleculedesignenhancement