{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004171883,0.00008669576,0.000143318,0.0001571379,0.00002106148,0.00001051249,0.00007352771,0.00008177711,0.000003870206],"category_scores_gemma":[0.001315053,0.00008352444,0.00002207942,0.0001998052,0.00004144882,0.00001794285,0.00003087127,0.0001105655,7.210114e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004433131,"about_ca_system_score_gemma":0.00005448052,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002348248,"about_ca_topic_score_gemma":0.0006741241,"domain_scores_codex":[0.9990643,0.00005197458,0.0004559444,0.0001253442,0.0001866738,0.0001158076],"domain_scores_gemma":[0.9993237,0.00006731104,0.0002133909,0.0001646962,0.0001917128,0.00003920749],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.0002045771,0.000399544,0.01291258,0.00008085277,0.00006205768,5.806223e-7,0.00582157,0.001775689,0.1026544,0.0001197143,0.0007185027,0.8752499],"study_design_scores_gemma":[0.00120392,0.0003084992,0.9274669,0.0002253777,0.00008318397,0.000008941101,0.001757645,0.03466531,0.02958152,0.001145742,0.00334788,0.0002050339],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9854655,0.0001631478,0.01329582,0.0001557206,0.0001544252,0.0003218228,0.00005095495,0.00001018908,0.0003824269],"genre_scores_gemma":[0.9836745,0.0000384864,0.01593089,0.00004696717,0.00006602434,0.00005734764,0.0001700046,0.000003877432,0.00001191833],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9145544,"threshold_uncertainty_score":0.3406028,"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."}}