From 995e977bf63d14419e39a1d9d745846c3a1edd40 Mon Sep 17 00:00:00 2001 From: Nomi Harris Date: Thu, 7 Dec 2023 12:16:56 -0800 Subject: [PATCH] add content to stub page about OntoGPT (#464) * add content to stub page about OntoGPT * Update docs/tutorial/ontogpt.md --------- Co-authored-by: Nico Matentzoglu --- docs/tutorial/ontogpt.md | 16 ++++++++++++++-- 1 file changed, 14 insertions(+), 2 deletions(-) diff --git a/docs/tutorial/ontogpt.md b/docs/tutorial/ontogpt.md index 6fe2f87b9..cf23fe074 100644 --- a/docs/tutorial/ontogpt.md +++ b/docs/tutorial/ontogpt.md @@ -1,4 +1,16 @@ # Using OntoGPT to boost ontology curation -- Tool: https://github.com/monarch-initiative/ontogpt -- Preprint: https://arxiv.org/abs/2304.02711 +OntoGPT is a Python package for extracting structured information from text with large language models (LLMs), instruction prompts, and ontology-based grounding. +Two different strategies for knowledge extraction are currently implemented in OntoGPT: +- SPIRES: A Zero-shot learning (ZSL) approach to extracting nested semantic structures from text +- TALISMAN (previously known as SPINDOCTOR): Summarizes gene set descriptions (pseudo gene-set enrichment) + +More info about OntoGPT: +- Documentation: +- Source: +- Preprints: + - Caufield JH, Hegde H, Emonet V, Harris NL, Joachimiak MP, Matentzoglu N, et al. Structured prompt interrogation and recursive extraction of semantics (SPIRES): A method for populating knowledge bases using zero-shot learning. + - Joachimiak MP, Caufield JH, Harris NL, Kim H, Mungall CJ. Gene Set Summarization using Large Language Models. + +We are also working on a curation-specific tool, [CurateGPT](https://github.com/monarch-initiative/curate-gpt), +a prototype web application and framework for performing general purpose AI-guided curation and curation-related operations over collections of objects.