{"id":"W2163980860","doi":"10.1093/bioinformatics/bti493","title":"Discovering patterns to extract protein–protein interactions from the literature: Part II","year":2005,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Biomedical Text Mining and Ontologies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":96,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"Natural Sciences and Engineering Research Council of Canada; Killam Trusts","keywords":"Merge (version control); Computer science; Recall; Protein–protein interaction; Generalization; Precision and recall; Protein expression; Artificial intelligence; Task (project management); Machine learning; Data mining; Computational biology; Information retrieval; Biology; Genetics; Mathematics","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":[0.000114372,0.0001476151,0.0001043258,0.00002267856,0.0001813611,0.00009890465,0.0002806126,0.0001121609,0.00004768446],"category_scores_gemma":[0.000178261,0.00009549084,0.0000761675,0.00008656023,0.00004595703,0.00001546,0.0002314879,0.000166243,0.00006137302],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000160933,"about_ca_system_score_gemma":0.00003039732,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002204863,"about_ca_topic_score_gemma":0.0001120278,"domain_scores_codex":[0.9991907,0.00002190863,0.000278115,0.0001420997,0.0001391669,0.0002279632],"domain_scores_gemma":[0.9993762,0.00001752079,0.00008451651,0.0003960109,0.00003439779,0.00009139125],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0001640045,0.0002531079,0.001256942,0.00009029135,0.0002129469,0.000005429368,0.008323615,0.0001165431,0.1240889,0.0001943241,0.0482084,0.8170855],"study_design_scores_gemma":[0.0002374929,0.0001921659,0.00102421,0.0002703947,0.00001088206,0.00000884368,0.0006462054,0.0004111945,0.06144239,0.0000315168,0.9354988,0.0002258789],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9823816,0.0003270619,0.01272383,0.003187009,0.0001996649,0.0003282842,0.0001980404,0.0000394233,0.0006150477],"genre_scores_gemma":[0.9752176,0.00003512518,0.02045069,0.001323688,0.0008987529,0.00008539109,0.0002559127,0.00001414377,0.001718683],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8872904,"threshold_uncertainty_score":0.3894003,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01510335763338248,"score_gpt":0.2620753649404113,"score_spread":0.2469720073070289,"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."}}