A total of 4,059 scientific publications on AI in drug discovery and development were analyzed from 1990 to 2023.
The most prolific authors include Ekins (67 publications), Schneider (52), Hou Tj (43), and Cao Ds (34).
The Chinese Academy of Sciences and the University of California are identified as the most active institutions.
Key journals in the field are the Journal of Chemical Information and Modelling, Briefings in Bioinformatics, and Journal of Cheminformatics.
The average citation count per publication is 28.62, indicating significant impact in the research community.
A notable increase in publications occurred after 2014, peaking in 2022 before a slight decline.
International collaboration comprises 28.06% of all publications, with the USA and China leading in both productivity and influence.
AI simplified
Today, drug discovery and development is one of the fields where Artificial Intelligence (AI) is used extensively. Therefore, this study aims to systematically analyze the scientific literature on the application of AI in drug discovery and development to understand the evolution, trends, and key contributors within this rapidly growing field. By leveraging various bibliometric indicators and visualization techniques, we seek to explore the growth patterns, influential authors and institutions, collaboration networks, and emerging research trends within this domain. Bibliometric and network analysis methods (co-occurrence, co-authorship, and collaboration, etc.) were used to achieve this goal. Bibliometric visualization tools such as Bibliometrix R package software, VOSviewer, and Litmaps were used for comprehensive data analysis. Scientific publications on AI in drug discovery and development were retrieved from the Web of Science Core Collection (WoS CC) database covering 1990-2023. In addition to visualization programs, the InCites database was also used for analysis and visualization. A total of 4059 scientific publications written by 13,932 authors and published in 1071 journals were included in the analysis. The results reveal that the most prolific authors are Ekins (n = 67), Schneider (n = 52), Hou Tj (n = 43), and Cao Ds (n = 34), while the most active institutions are the "Chinese Academy of Science" and "University of California." The leading scientific journals are "Journal of Chemical Information and Modelling," "Briefings in Bioinformatics," and "Journal of Cheminformatics." The most frequently used author keywords include "protein folding," "QSAR," "gene expression data," "coronavirus," and "genome rearrangement." The average number of citations per scientific publication is 28.62, indicating a high impact of research in this field. A significant increase in publications was observed after 2014, with a peak in 2022, followed by a slight decline. International collaboration accounts for 28.06% of the publications, with the USA and China leading in both productivity and influence. The study also identifies key funding organizations, such as the National Natural Science Foundation of China (NSFC) and the United States Department of Health & Human Services, which have significantly supported advancements in this field. In conclusion, this study highlights the transformative role of AI in drug discovery and development, showcasing its potential to accelerate innovation and improve efficiency. The findings provide valuable insights into the current state of research, emerging trends, and future directions, offering a roadmap for researchers, industry professionals, and policymakers to further explore and leverage AI technologies in this domain.Scientific contributionThis study provides a comprehensive of 4,059 scientific publications (1990-2023) to map the evolution, trends, and key contributors in AI-driven drug discovery, identifying prolific authors (e.g., Ekins, Schneider), leading institutions (e.g., Chinese Academy of Sciences, University of California), and high-impact journals (Journal of Chemical Information and Modelling). It reveals critical collaboration patterns (28.06% international co-authorships), dominant funding sources (e.g., NSFC, NIH), and emerging research hotspots (e.g., protein folding, QSAR, coronavirus), while highlighting the transformative role of deep learning post-2014. By synthesizing these insights, the study offers a strategic roadmap for researchers and policymakers to optimize AI applications in drug development, addressing both current challenges and future opportunities in the field.
Key numbers
4059
Total Publications
Number of scientific publications analyzed from 1990 to 2023.
28.62
Average Citations per Document
Average number of citations for each publication in the dataset.
28.06%
International Collaboration Rate
Percentage of publications involving international co-authorship.
Full Text
We can’t show the full text here under this license. Use the link below to read it at the source.
