<![CDATA[Genomic prediction (GP) has emerged as a transformative methodology in biological, health and agricultural sciences, leveraging genome-wide molecular markers to predict complex traits with increasing accuracy. This bibliometric study aims to analyse the development, collaboration patterns, and thematic trends in GP research in plants between 2015 and 2025. A total of 205 open-access research articles were retrieved from the Scopus database using the PRISMA approach and analysed with the R-based Biblioshiny software. The results show a marked increase in publication output since 2018, peaking in 2024, with an annual growth rate of 14.9%. International collaboration is also substantial, with 41.46% of publications involving authors from different countries. The most prolific authors, including Crossa J, Montesinos-López A, and Montesinos-López OA, demonstrate strong collaborative synergies. Leading journals such as Frontiers in Plant Science and The Plant Genome indicate that the field remains strongly rooted in plant genomics and breeding applications. Keyword co-occurrence analysis identified three major thematic clusters: plant breeding and machine learning, AI-based genomics, and statistical prediction systems. Overall, the findings suggest that GP research has evolved into a mature and highly collaborative interdisciplinary field, with a clear shift from conventional statistical approaches toward machine learning and deep learning-driven methodologies. This study provides a systematic map of the intellectual landscape and highlights promising directions for future research in data-driven plant breeding.]]>
Copyrights © 2025
