{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003948194,0.0006844905,0.0005481737,0.008369832,0.0007818062,0.001567274,0.0009787127,0.001151512,0.00253963],"category_scores_gemma":[0.01965284,0.0002004023,0.0006047923,0.004596241,0.0006813301,0.002021733,0.001004362,0.0005911644,0.001360584],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007123476,"about_ca_system_score_gemma":0.001286255,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0009834161,"about_ca_topic_score_gemma":0.001442996,"domain_scores_codex":[0.9960623,0.001329175,0.0007850851,0.00103715,0.0007074069,0.00007880763],"domain_scores_gemma":[0.9688028,0.02339632,0.003657477,0.001339499,0.002531716,0.0002722612],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0007451075,0.0004639543,0.07914022,0.009140457,0.0003985038,0.003200026,0.002437999,0.01582314,0.08303929,0.006064673,0.02099637,0.7785503],"study_design_scores_gemma":[0.00019914,0.0007786267,0.2706706,0.002621067,0.00142183,0.01602715,0.00320055,0.3201731,0.1653781,0.06671237,0.1524846,0.0003328396],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3161361,0.01091342,0.6242056,0.003789961,0.0003449175,0.001019395,0.02942453,0.007093387,0.007072602],"genre_scores_gemma":[0.5034561,0.002427725,0.4658162,0.0004627621,0.0004166732,0.0005954167,0.02521846,0.0002520196,0.001354665],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.008369832,"threshold_uncertainty_score":0.02088028,"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."}}