Skip to content

Using OntoGPT to boost ontology curation

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:

We are also working on a curation-specific tool, CurateGPT, a prototype web application and framework for performing general-purpose AI-guided curation and curation-related operations over collections of objects.

Please see this tutorial to learn how to leverage ChatGPT for ontology curation.