{"database":"biostudies-literature","file_versions":[],"scores":null,"additional":{"omics_type":["Unknown"],"submitter":["Tiwari K"],"funding":["NHGRI NIH HHS","NCI NIH HHS","NIGMS NIH HHS"],"pubmed_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"],"journal":["bioRxiv : the preprint server for biology"],"pagination":["2023.11.08.566195"],"full_dataset_link":["https://www.ebi.ac.uk/biostudies/studies/S-EPMC10659344"],"repository":["biostudies-literature"],"pubmed_title":["ChatGPT usage in the Reactome curation process."],"pmcid":["PMC10659344"],"funding_grant_id":["U24 HG012198","U01 CA239069","U24 HG011851","U41 HG003751","U54 GM114833"],"pubmed_authors":["Hermjakob H","Matthews L","Stephan R","Wu G","May B","Stein L","Tiwari K","Shamovsky V","Li N","Rothfels K","Gong C","Ragueneau E","D'Eustachio P","Orlic-Milacic M"],"additional_accession":[]},"is_claimable":false,"name":"ChatGPT usage in the Reactome curation process.","description":"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","dates":{"release":"2023-01-01T00:00:00Z","publication":"2023 Nov","modification":"2026-04-08T15:08:57.866Z","creation":"2025-04-06T01:24:39.394Z"},"accession":"S-EPMC10659344","cross_references":{"pubmed":["37986970"],"doi":["10.1101/2023.11.08.566195"]}}