Check GPT phenotype annotations using a several metrics.
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
)
GPT-generated phenotype annotations.
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.
A named list of responses to map onto. Used for standardisation of responses.
Positive values.
Negative values.
Print messages.
Named list
checks <- gpt_annot_check()
#> Translating ontology terms to ids.
#> Reading cached RDS file: phenotype_to_genes.txt
#> + Version: v2024-12-12
#> 383 phenotypes do not have matching HPO IDs.
#> Reading in GPT annotations for 16,753 phenotypes.
#> Querying HPO for matching terms.
#> Number of phenotype hits per query group:
#> - intellectual_disability: 19
#> - impaired_mobility: 326
#> - physical_malformations: 81
#> - blindness: 1
#> - sensory_impairments: 253
#> - immunodeficiency: 29
#> - cancer: 56
#> - reduced_fertility: 9
#> Warning: The `facets` argument of `facet_grid()` is deprecated as of ggplot2 2.2.0.
#> ℹ Please use the `rows` argument instead.
#> ℹ The deprecated feature was likely used in the HPOExplorer package.
#> Please report the issue at
#> <https://github.com/neurogenomics/HPOExplorer/issues>.