Curated Papers > High-impact authoritative literature on "AI Drug Discovery"

Concepts of Artificial Intelligence for Computer-Assisted Drug Discovery.

Literature Information

DOI	10.1021/acs.chemrev.8b00728
PMID	31294972
Journal	Chemical reviews
Publication Year	2019
Times Cited	220
Keywords	Artificial Intelligence, Deep Learning, Drug Discovery, Machine Learning, Drug Design
Literature Type	Journal Article, Research Support, Non-U.S. Gov't, Review
ISSN	0009-2665
Pages	10520-10594
Issue	119(18)
Authors	Xin Yang, Yifei Wang, Ryan Byrne, Gisbert Schneider, Shengyong Yang

TL;DR

This review explores the application of artificial intelligence, particularly deep learning, in drug discovery and design, highlighting various machine learning techniques and their roles in areas such as virtual screening, drug repurposing, and property prediction. It also discusses the current advancements, challenges, and potential future directions for AI in medicinal chemistry, underscoring its significance in enhancing the drug development process.

Search for more papers on MaltSci.com

Artificial Intelligence · Deep Learning · Drug Discovery · Machine Learning · Drug Design

Abstract

Artificial intelligence (AI), and, in particular, deep learning as a subcategory of AI, provides opportunities for the discovery and development of innovative drugs. Various machine learning approaches have recently (re)emerged, some of which may be considered instances of domain-specific AI which have been successfully employed for drug discovery and design. This review provides a comprehensive portrayal of these machine learning techniques and of their applications in medicinal chemistry. After introducing the basic principles, alongside some application notes, of the various machine learning algorithms, the current state-of-the art of AI-assisted pharmaceutical discovery is discussed, including applications in structure- and ligand-based virtual screening, de novo drug design, physicochemical and pharmacokinetic property prediction, drug repurposing, and related aspects. Finally, several challenges and limitations of the current methods are summarized, with a view to potential future directions for AI-assisted drug discovery and design.

MaltSci.com AI Research Service

Intelligent ReadingAnswer any question about the paper and explain complex charts and formulas

Locate StatementsFind traces of a specific claim within the paper

Add to KBasePerform data extraction, report drafting, and advanced knowledge mining

Primary Questions Addressed

1. What are the specific deep learning algorithms that have shown the most promise in drug discovery applications?
2. How do the challenges and limitations of current AI methods impact the future of drug discovery?
3. In what ways can AI enhance the efficiency of drug repurposing compared to traditional methods?
4. What role does domain-specific AI play in improving the accuracy of physicochemical property predictions?
5. How can machine learning techniques be integrated with existing medicinal chemistry practices to optimize drug design?

Key Findings

Key Insights

1. Research Background and Purpose
   The field of drug discovery faces numerous challenges, including high costs, lengthy development timelines, and high failure rates in clinical trials. Artificial intelligence (AI), particularly deep learning, has emerged as a transformative tool in this context, offering innovative solutions to enhance the efficiency and effectiveness of drug discovery. The purpose of this review is to provide an in-depth examination of the various machine learning techniques applicable to medicinal chemistry, highlighting their current applications and potential to revolutionize drug discovery and design processes.

2. Main Methods and Findings
   The review categorizes and elaborates on several machine learning approaches that have gained traction in drug discovery, including structure-based and ligand-based virtual screening methods, de novo drug design strategies, and predictive models for physicochemical and pharmacokinetic properties. The authors present a comprehensive overview of state-of-the-art applications of AI in pharmaceutical discovery, underscoring successful case studies where these technologies have led to significant advancements. Key findings show that AI can streamline the identification of promising drug candidates, optimize lead compounds, and facilitate the repurposing of existing drugs for new therapeutic uses.

3. Core Conclusions
   The review concludes that while AI, particularly deep learning, has substantially enhanced the drug discovery process, there remain critical challenges and limitations. These include issues related to data quality, algorithm interpretability, and the need for integration with traditional drug development methodologies. The review emphasizes that a multidisciplinary approach, combining AI with domain expertise in medicinal chemistry, is essential for overcoming these obstacles and maximizing the potential of AI in drug discovery.

4. Research Significance and Impact
   This research is significant as it highlights the transformative potential of AI in addressing longstanding challenges in drug discovery, a field that is crucial for advancing healthcare. By elucidating the capabilities and applications of machine learning techniques, the review serves as a valuable resource for researchers and pharmaceutical companies aiming to leverage AI for more efficient drug development. The insights gathered from this review can guide future research directions, encouraging further exploration and innovation in AI-assisted drug discovery, ultimately leading to more effective treatments and improved patient outcomes.

Literatures Citing This Work

1. Rethinking drug design in the artificial intelligence era. - Petra Schneider;W Patrick Walters;Alleyn T Plowright;Norman Sieroka;Jennifer Listgarten;Robert A Goodnow;Jasmin Fisher;Johanna M Jansen;José S Duca;Thomas S Rush;Matthias Zentgraf;John Edward Hill;Elizabeth Krutoholow;Matthias Kohler;Jeff Blaney;Kimito Funatsu;Chris Luebkemann;Gisbert Schneider - Nature reviews. Drug discovery (2020)
2. Validation Study of QSAR/DNN Models Using the Competition Datasets. - Yoshiki Kato;Shinji Hamada;Hitoshi Goto - Molecular informatics (2020)
3. Machine-Learning-Assisted De Novo Design of Organic Molecules and Polymers: Opportunities and Challenges. - Guang Chen;Zhiqiang Shen;Akshay Iyer;Umar Farooq Ghumman;Shan Tang;Jinbo Bi;Wei Chen;Ying Li - Polymers (2020)
4. Exploration of databases and methods supporting drug repurposing: a comprehensive survey. - Ziaurrehman Tanoli;Umair Seemab;Andreas Scherer;Krister Wennerberg;Jing Tang;Markus Vähä-Koskela - Briefings in bioinformatics (2021)
5. Capsule Networks Showed Excellent Performance in the Classification of hERG Blockers/Nonblockers. - Yiwei Wang;Lei Huang;Siwen Jiang;Yifei Wang;Jun Zou;Hongguang Fu;Shengyong Yang - Frontiers in pharmacology (2019)
6. In silico Strategies to Support Fragment-to-Lead Optimization in Drug Discovery. - Lauro Ribeiro de Souza Neto;José Teófilo Moreira-Filho;Bruno Junior Neves;Rocío Lucía Beatriz Riveros Maidana;Ana Carolina Ramos Guimarães;Nicholas Furnham;Carolina Horta Andrade;Floriano Paes Silva - Frontiers in chemistry (2020)
7. Putting deep learning in perspective for pest management scientists. - Robert D Clark - Pest management science (2020)
8. Virtual screening web servers: designing chemical probes and drug candidates in the cyberspace. - Natesh Singh;Ludovic Chaput;Bruno O Villoutreix - Briefings in bioinformatics (2021)
9. How Computational Chemistry and Drug Delivery Techniques Can Support the Development of New Anticancer Drugs. - Mariangela Garofalo;Giovanni Grazioso;Andrea Cavalli;Jacopo Sgrignani - Molecules (Basel, Switzerland) (2020)
10. Drug Research Meets Network Science: Where Are We? - Maurizio Recanatini;Chiara Cabrelle - Journal of medicinal chemistry (2020)

... (210 more literatures)

---

© 2025 MaltSci - We reshape scientific research with AI technology