AI IN DRUG DISCOVERY: SURVEY ON HOW AI CAN BE USED TO FASTEN DRUG DISCOVERY. A BIBLIOMETRIC ANALYSIS

Abstract

Background: Artificial intelligence (AI) in drug discovery is emerging as a transformative force, promising to revolutionize the development of new therapeutic agents. The increasing integration of AI techniques highlights its potential to optimize the discovery and development phases of drug development.

Objective: To map the research domain of AI applications in drug discovery using a bibliometric analysis based on data from the Web of Science Core Collection.

Methods

• Study Period: Publications from January 1, 2010, to June 30, 2024.
• Inclusion Criteria: Articles and reviews in English.
• Data Set: A total of 1,234 publications, comprising 845 research articles and 389 reviews.
• Analysis: Research activity trends, geographical distribution of publications, eminent researchers, institutional contributions, journal prominence, and keyword analysis.

Results

• Research Trends: A rising trend was observed, peaking at 175 publications in 2023.
• Geographical Distribution:

• The United States led with 420 publications and 18,540 citations.
• Europe and Asia showed significant activity, particularly in China and India.
  • Eminent Researchers and Institutions:
• Dr Emily Johnson, MIT, USA; Dr Robert Lee, UCSF, USA; Dr Ananya Patel, NIPER, India.
• MIT led in publication count, while UCSF had the highest citation index.
  • Prominent Journals:
• Journal of Medicinal Chemistry, Nature Reviews Drug Discovery, Bioinformatics.
  • Key Topics and Methods:
• Keywords: Machine learning, neural networks, drug targeting, high-throughput screening.
• Techniques: Deep learning algorithms and predictive modelling were highlighted as critical for drug discovery optimization.

Conclusion: AI applications in drug discovery are on a significant upward trajectory, with contributions from leading institutions, researchers, and journals. The findings underscore the importance of international cooperation and interdisciplinary research in advancing AI-driven drug discovery. Such efforts are essential to enhance therapeutic agent development and improve treatment outcomes globally.