ChatGPT usage in the Reactome curation process
Authors:
- Krishna TiwariKTKrishna Tiwari
- Lisa MatthewsLMLisa Matthews
- Veronica ShamovskyVSVeronica Shamovsky
- Marija Orlic-MilacicMOMarija Orlic-Milacic
- Karen RothfelsKRKaren Rothfels
- Eliot RagueneauEREliot Ragueneau
- Chuqiao GongCGChuqiao Gong
- Ralf StephanRSRalf Stephan
- Guanming WuGWGuanming Wu
- Lincoln SteinLSLincoln Stein
Preprint
Abstract
Appreciating the rapid advancement and ubiquity of generative AI, particularly ChatGPT, a chatbot using large language models like GPT, we endeavour to explore the potential application of ChatGPT in the data collection and annotation stages within the Reactome curation process. This exploration aimed to create an automated or semi-automated framework to mitigate the extensive manual effort traditionally required for gathering and annotating information pertaining to biological pathways, adopting a Reactome “reaction-centric” approach. In this pilot study, we used ChatGPT/GPT4 to address gaps in the pathway annotation and enrichment in parallel with the conventional manual curation process. This approach facilitated a comparative analysis, where we assessed the outputs generated by ChatGPT against manually extracted information. The primary objective of this comparison was to ascertain the efficiency of integrating ChatGPT or other large language models into the Reactome curation workflow and helping plan our annotation pipeline, ultimately improving our protein-to-pathway association in a reliable and automated or semi-automated way. In the process, we identified some promising capabilities and inherent challenges associated with the utilisation of ChatGPT/GPT4 in general and also specifically in the context of Reactome curation processes. We describe approaches and tools for refining the output given by ChatGPT/GPT4 that aid in generating more accurate and detailed output.Keywords
This publication has 26 references indexed in Scilit:
- Artificial Hallucinations in ChatGPT: Implications in Scientific WritingCureus, 2023
- ChatGPT: five priorities for researchNature, 2023
- The Benefits and Challenges of ChatGPT: An OverviewFrontiers in Computing and Intelligent Systems, 2022
- Measuring the time spent on data curationJournal of Documentation, 2022
- Curation of Digital Scientific DataScientific and Technical Information Processing, 2019
- Art, Creativity, and the Potential of Artificial IntelligenceArts, 2019
- Linear ubiquitination is involved in the pathogenesis of optineurin-associated amyotrophic lateral sclerosisNature Communications, 2016
- Optineurin deficiency in mice is associated with increased sensitivity to Salmonella but does not affect proinflammatory NF‐κB signalingEuropean Journal of Immunology, 2015
- Optineurin Insufficiency Impairs IRF3 but Not NF-κB Activation in Immune CellsThe Journal of Immunology, 2013
- Optineurin Negatively Regulates TNFα- Induced NF-κB Activation by Competing with NEMO for Ubiquitinated RIPCurrent Biology, 2007