Harnessing full-text publications for deep insights into C. elegans and Drosophila connectomes

Abstract

In the rapidly expanding domain of scientific research, tracking and synthesizing information from the rapidly increasing volume of publications pose significant challenges. To address this, we introduce a novel high-throughput pipeline that employs ChatGPT to systematically extract and analyze connectivity information from the full-texts and abstracts of 24,237 and 150,538 research publications concerning Caenorhabditis elegans and Drosophila melanogaster, respectively. This approach has effectively identified 200,219 and 1,194,587 interactions within the C. elegans and Drosophila connectomes, respectively. Utilizing Cytoscape Web, we have developed comprehensive, searchable online connectomes that link relevant keywords to their corresponding PubMed IDs, thus providing seamless access to an extensive knowledge network encompassing C. elegans and Drosophila. Our work highlights the transformative potential of integrating artificial intelligence with bioinformatics to deepen our understanding of complex biological systems. By revealing the intricate web of relationships among key entities in C. elegans and Drosophila, we offer invaluable insights that promise to propel advancements in genetics, developmental biology, neuroscience, longevity, and beyond. We also provide details and discuss significant nodes within both connectomes, including the insulin/IGF-1 signaling (IIS) and the notch pathways. Our innovative methodology sets a robust foundation for future research aimed at unravelling complex biological networks across diverse organisms.