{"id":"W2773306025","doi":"10.1186/s13326-017-0163-8","title":"Identifying genotype-phenotype relationships in biomedical text","year":2017,"lang":"en","type":"article","venue":"Journal of Biomedical Semantics","topic":"Biomedical Text Mining and Ontologies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":21,"is_retracted":false,"has_abstract":true,"ca_institutions":"Western University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Automatic summarization; Computer science; Set (abstract data type); Precision and recall; Artificial intelligence; Natural language processing; Recall; Training set; Information retrieval; F1 score; Phenotype; Machine learning; Genotype; Genotype-phenotype distinction; Data mining; Gene; Biology","routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001464823,0.000160435,0.0003364599,0.0002074487,0.0002666267,0.00008875227,0.0007829498,0.0004869922,0.00003983807],"category_scores_gemma":[0.003677121,0.0001245436,0.0001517691,0.0001345538,0.0008299996,0.00001267722,0.000255898,0.0005994643,0.0000239804],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003060652,"about_ca_system_score_gemma":0.0002040157,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001879184,"about_ca_topic_score_gemma":0.00003580893,"domain_scores_codex":[0.9980147,0.000121454,0.0007241303,0.0002237305,0.0005670332,0.0003489243],"domain_scores_gemma":[0.9984543,0.00008349866,0.0005762118,0.0004441573,0.0001293613,0.0003124377],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0009103678,0.002223462,0.1578754,0.0003729831,0.0006875039,0.001683706,0.001349532,0.000009496718,0.4342901,0.001293318,0.05580405,0.3435001],"study_design_scores_gemma":[0.005288359,0.002100895,0.4700727,0.0007100767,0.0001671458,0.0007019471,0.001034825,0.0004740271,0.006886147,0.005004398,0.5067985,0.0007610112],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9648076,0.001878133,0.02373721,0.007148565,0.001848047,0.00009382332,0.00001010792,0.00001254568,0.0004639722],"genre_scores_gemma":[0.9871661,0.0004516334,0.01102159,0.0001337328,0.0009664362,0.000001235986,0.00001744621,0.00001812511,0.0002237229],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.4509944,"threshold_uncertainty_score":0.5078743,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05060272485733645,"score_gpt":0.3265227518376841,"score_spread":0.2759200269803476,"validation_status":"score_only:v0-immature-baseline","note":"Baseline scores from an immature model (maturity gate not passed). Scores rank; they never assert a category."}}