gpt_annot_check: Check annotations from GPT

In neurogenomics/HPOExplorer: Analysis and Visualisation of the Human Phenotype Ontology

Check annotations from GPT

Description

Check GPT phenotype annotations using a several metrics.

Usage

gpt_annot_check(
  annot = gpt_annot_read(),
  query_hits = search_hpo(),
  response_map = list(no = "never", yes = "always"),
  pos_values = c("sometimes", "often", "always"),
  neg_values = c("never", "rarely"),
  verbose = TRUE
)

Arguments

annot	GPT-generated phenotype annotations.
query_hits	A named list of HPO IDs for each query, generated by search_hpo. These will be used as the ground truth when trying to identify true positive annotations.
response_map	A named list of responses to map onto. Used for standardisation of responses.
pos_values	Positive values.
neg_values	Negative values.
verbose	Print messages.

Value

Named list

Examples

checks <- gpt_annot_check()

neurogenomics/HPOExplorer documentation built on Aug. 24, 2024, 1:39 a.m.