Exploring Gene Signature and Expression Trends: A Bibliometric Study Utilizing Biblioshiny and VOSviewer with Deep Learning and Convolutional Neural Networks

Gene Signature and Gene Expression are widely used in the process of disease identification, drug development, classification, etc. This study utilizes a bibliometric approach to explore the research landscape surrounding the integration of gene signatures, gene expression analysis, deep learning and Convolutional Neural Networks (CNNs). Biblioshiny is used for data acquisition, cleaning and descriptive statistics to analyze publication trends, author collaborations, keyword co- occurrence, etc. Subsequently, VOSviewer is used to visualize and analyze co-authorship or citation networks, revealing key research clusters etc. The results highlight valuable insights into the current state and future directions of research utilizing deep learning, particularly CNNs, for gene signature analysis and understanding gene expression patterns, underscoring the conver- gence of computational methods and biological data. Our findings serve as a crucial resource for researchers aiming to navigate the interdisciplinary domain of Bio-informatics, fostering further innovation and collaboration.