{"id":"W2133601033","doi":"10.1093/bioinformatics/btp602","title":"Evaluation of linguistic features useful in extraction of interactions from PubMed; Application to annotating known, high-throughput and predicted interactions in I2D","year":2009,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Biomedical Text Mining and Ontologies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":77,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"U.S. National Library of Medicine; Ontario Genomics; Ontario Genomics Institute; Genome Canada","keywords":"Computer science; Sentence; Identification (biology); Recall; Precision and recall; Software; Natural language processing; Information retrieval; Process (computing); Artificial intelligence; Data mining; Machine learning; Programming language; 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":[0.005985401,0.001101822,0.0008591355,0.009662319,0.001066407,0.00161432,0.001103369,0.001078992,0.001875179],"category_scores_gemma":[0.01829155,0.0002643591,0.0007130536,0.005032147,0.0003870624,0.001508533,0.001210701,0.0004634062,0.0007690819],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008938867,"about_ca_system_score_gemma":0.001433699,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00444016,"about_ca_topic_score_gemma":0.008500827,"domain_scores_codex":[0.996698,0.001218444,0.0008625767,0.0005288853,0.0005683697,0.0001236104],"domain_scores_gemma":[0.9751209,0.01913846,0.001765548,0.0007416039,0.00267752,0.0005560324],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.005479754,0.00211511,0.1081225,0.01052583,0.0009340356,0.003622109,0.002799744,0.009720945,0.1188782,0.001793407,0.04138891,0.6946194],"study_design_scores_gemma":[0.001866796,0.002965466,0.2806349,0.001055869,0.002257258,0.007181465,0.004946539,0.4013218,0.2212154,0.004744726,0.07128467,0.0005252261],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8493561,0.005226396,0.07697894,0.002016686,0.000216756,0.001579483,0.04192663,0.01582026,0.006878734],"genre_scores_gemma":[0.5692654,0.001061069,0.3923007,0.0003391572,0.0001022313,0.0007924326,0.03459542,0.0002971553,0.001246421],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.009662319,"threshold_uncertainty_score":0.03165418,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02690545087677414,"score_gpt":0.3323320965378367,"score_spread":0.3054266456610626,"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."}}