Dynamic Retrieval Augmented Generation of Ontologies using Artificial Intelligence (DRAGON-AI)

Table 1 Example JSON structure used in DRAGON-AI

id: CL:1,001,502 name: mitral cell is_a: CL:0000099 ! interneuron relationship: RO:0002100 UBERON:0004186 ! has-soma-location\ olfactory bulb mitral cell layer definition: “The large glutaminergic nerve cells whose dendrites synapse with axons of the olfactory receptor neurons in the glomerular layer of the olfactory bulb, and whose axons pass centrally in the olfactory tract to the olfactory cortex” [MP:0009954]
{ “id”: “MitralCell”, “original_id”: “CL:1,001,502” “relationships”: [ { “predicate”: “SubClassOf”, “target”: “Interneuron”}, { “predicate”: “HasSomaLocation”, “target”: “OlfactoryBulbMitralCellLayer”} ], “definition”: “The large glutaminergic nerve cells whose dendrites synapse with axons of the olfactory receptor neurons in the glomerular layer of the olfactory bulb, and whose axons pass centrally in the olfactory tract to the olfactory cortex” }

In this example, OBO format syntax is shown at the top, including the non-semantic numeric identifier (id), the term label (name), the SubClass_Of relationship (is_a), another relationship using terms from the Relation Ontology (RO) and the Uberon ontology, and the human-readable textual definition
The corresponding JSON object form shown is below, including the camel case format of the term label (id), the non-semantic numeric identifier (original_id), the relationships using a predicate and target properties, also in camel case format, and the term definition. It should be noted that the JSON form omits some information from the OBO Format (e.g. the provenance of the definition)

ISSN: 2041-1480