Machine learning in antibacterial discovery and development: A bibliometric and network analysis of research hotspots and trends

• Published in: Computers in biology and medicine Vol. 155; p. 106638
• Main Authors: Diéguez-Santana, Karel, González-Díaz, Humberto
• Format: Journal Article
• Language: English
• Published: United States Elsevier Ltd 01-03-2023; Elsevier Limited
• Subjects: Algorithms; Anti-Bacterial Agents; Antibacterial agents; Antibiotic resistance; Antibiotics; Antimicrobial agents; Artificial intelligence; Bibliographic coupling; Bibliometric analysis; Bibliometrics; Big Data; Cheminformatics; Citations; Computer model in drug design; Drug development; Drug resistance; Informatics; Learning algorithms; Machine Learning; Network analysis; Neural networks; Obsolescence; Pathogens; Pharmaceutical industry; Pharmaceutical sciences; Proteins; R&D; Research & development; Software; Support vector machines; Trends; NN; ANN; CNN; NP; DL; DM; KNN; SVM; Bibliometric analysis; BN; DT; Network analysis; Antibiotic resistance; ChEMBL; MDR; TLS; ML; MN; Computer model in drug design; AD; AMR; AI; MCA; Antibacterial agents; TC; RF; QSAR; DNA; Machine learning; TP; DA
• ISSN: 0010-4825; 1879-0534
• DOI: 10.1016/j.compbiomed.2023.106638

Machine learning (ML) methods are used in cheminformatics processes to predict the activity of an unknown drug and thus discover new potential antibacterial drugs. This article conducts a bibliometric study to analyse the contributions of leading authors, universities/organisations and countries in terms of productivity, citations and bibliographic linkage. A sample of 1596 Scopus documents for the period 2006–2022 is the basis of the study. In order to develop the analysis, bibliometrix R-Tool and VOSviewer software were used. We determined essential topics related to the application of ML in the field of antibacterial development (Computer model in antibacterial drug design, and Learning algorithms and systems for forecasting). We identified obsolete and saturated areas of research. At the same time, we proposed emerging topics according to the various analyses carried out on the corpus of published scientific literature (Title, abstract and keywords). Finally, the applied methodology contributed to building a broader and more specific “big picture” of ML research in antibacterial studies for the focus of future projects.
•A bibliometric study of the use of machine learning in antibacterial activity research.•A sample of 1596 documents from the Scopus Database are analysed for the period 2006–2022.•ANN, DL, SVM and RF are the most explored ML techniques.•“Computer model in antibacterial drug design”, is landscape dominant in machine learning in antibacterial activity research.