{"id":"W2166516661","doi":"10.1093/database/bas017","title":"How to link ontologies and protein-protein interactions to literature: text-mining approaches and the BioCreative experience","year":2012,"lang":"en","type":"article","venue":"Database","topic":"Biomedical Text Mining and Ontologies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":34,"is_retracted":false,"has_abstract":true,"ca_institutions":"Institute for Research in Immunology and Cancer","funders":"Biotechnology and Biological Sciences Research Council; National Center for Research Resources; Directorate for Biological Sciences; National Institutes of Health; Office of Research Infrastructure Programs, National Institutes of Health; Canadian Institutes of Health Research; European Commission; Wellcome Trust","keywords":"Computer science; Ontology; Information retrieval; Pipeline (software); Context (archaeology); Data curation; Information extraction; Consistency (knowledge bases); Workflow; Open Biomedical Ontologies; Biomedical text mining; Controlled vocabulary; Process (computing); Annotation; Vocabulary; Natural language processing; Upper ontology; Data science; Suggested Upper Merged Ontology; Artificial intelligence; Text mining; Semantic Web; Database","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":[0.01799475,0.001065399,0.001333164,0.04766393,0.002374283,0.01224306,0.002559373,0.002207926,0.005392216],"category_scores_gemma":[0.05536789,0.0007794875,0.001481645,0.02775859,0.004947551,0.02285472,0.004310654,0.002288684,0.002775411],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002388007,"about_ca_system_score_gemma":0.003015876,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003409953,"about_ca_topic_score_gemma":0.005008338,"domain_scores_codex":[0.9895077,0.004942099,0.001808876,0.001078484,0.002459156,0.0002036196],"domain_scores_gemma":[0.9492692,0.03788367,0.003409016,0.002971347,0.005687299,0.0007794268],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"design_other","study_design_scores_codex":[0.00007429823,0.0001651658,0.004432006,0.006444501,0.0002564743,0.001709347,0.01530522,0.001730132,0.00718023,0.1693756,0.04259516,0.7507318],"study_design_scores_gemma":[0.00003540733,0.00004288951,0.004538702,0.006489417,0.000175195,0.001941721,0.01216545,0.01003831,0.004544891,0.3996022,0.5602973,0.000128501],"study_design_candidate":"design_other","study_design_consensus":"design_other","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.02626887,0.06489862,0.7890201,0.06287145,0.00154929,0.001070871,0.00703098,0.003171172,0.04411873],"genre_scores_gemma":[0.07798959,0.03335342,0.8700514,0.004443796,0.001190363,0.0007403518,0.004905905,0.0008132554,0.006512074],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.04766393,"threshold_uncertainty_score":0.09516644,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04548647227863387,"score_gpt":0.294178056247657,"score_spread":0.2486915839690232,"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."}}