{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002363002,0.0001468006,0.0001368181,0.00004185022,0.0001479533,0.0001169919,0.0001505901,0.00007447702,0.000002866897],"category_scores_gemma":[0.001210766,0.00009076399,0.00002360876,0.0001217056,0.0003229362,0.00001970119,0.0004033156,0.0001123586,0.000002398868],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000005513061,"about_ca_system_score_gemma":0.0000121793,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002341959,"about_ca_topic_score_gemma":0.00002696516,"domain_scores_codex":[0.9991629,0.00009372459,0.000101352,0.0003086152,0.00008087417,0.0002525317],"domain_scores_gemma":[0.9993927,0.00005258112,0.00004036665,0.0003201268,0.00002856929,0.0001656335],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"not_applicable","study_design_scores_codex":[0.001323155,0.0001556543,0.003410094,0.0001298604,0.00015537,0.0000118971,0.02638577,7.720527e-7,0.6326645,0.004296289,0.006673136,0.3247935],"study_design_scores_gemma":[0.001521392,0.0006190072,0.005215343,0.0004223797,0.00004410509,0.0001220632,0.02135658,0.00005862735,0.4009281,0.00009723218,0.5688807,0.0007345551],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9774803,0.004392403,0.008853842,0.008255932,0.00008043815,0.0005337961,0.00014704,0.0000269184,0.0002293227],"genre_scores_gemma":[0.9743015,0.00003952028,0.02368358,0.000397901,0.0002259126,0.0003586652,0.0001058403,0.000008778559,0.0008783588],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.5622075,"threshold_uncertainty_score":0.3701248,"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."}}