{"id":"W2016928406","doi":"10.1093/bioinformatics/bth451","title":"Discovering patterns to extract protein–protein interactions from full texts","year":2004,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Biomedical Text Mining and Ontologies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":238,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"Computer science; Recall rate; Scientific literature; Matching (statistics); Information retrieval; Natural language processing; Artificial intelligence; Data mining; Biology","routes":{"ca_aff":true,"ca_fund":false,"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":[0.00007094621,0.0001589312,0.0001308512,0.00004709995,0.00008189269,0.00006033304,0.0002226249,0.0001238328,0.00003659057],"category_scores_gemma":[0.0001451208,0.0001344148,0.00007403483,0.00007302662,0.00004551808,0.0000122223,0.0001621443,0.0001238535,0.0001448134],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003216602,"about_ca_system_score_gemma":0.00006085688,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001096491,"about_ca_topic_score_gemma":0.0001727354,"domain_scores_codex":[0.9991258,0.0000110132,0.0002947361,0.0001666714,0.0001468952,0.0002549278],"domain_scores_gemma":[0.9993973,0.000007672244,0.00008920826,0.000335226,0.00003156554,0.0001390287],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0001634541,0.0002125425,0.0006073937,0.0001091584,0.0001262254,0.00001225956,0.001478982,0.0002355377,0.7448636,0.000142983,0.001077578,0.2509703],"study_design_scores_gemma":[0.001987702,0.001488048,0.005996979,0.0007928376,0.00004076964,0.00004732921,0.002574007,0.0004906342,0.7400716,0.001090251,0.2442705,0.001149302],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.826021,0.00005597092,0.1723548,0.0004221142,0.0001488692,0.0002545578,0.00009902176,0.00004210442,0.0006015825],"genre_scores_gemma":[0.9398645,0.000008328059,0.0591281,0.0002917481,0.0002132219,0.00005623933,0.0001456001,0.00001500649,0.0002772959],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.249821,"threshold_uncertainty_score":0.5481275,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01549990955994195,"score_gpt":0.267165727324153,"score_spread":0.251665817764211,"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."}}