{"id":"W2014139771","doi":"10.1016/j.jbi.2014.05.013","title":"Automatic construction of a large-scale and accurate drug-side-effect association knowledge base from biomedical literature","year":2014,"lang":"en","type":"article","venue":"Journal of Biomedical Informatics","topic":"Computational Drug Discovery Methods","field":"Computer Science","cited_by":49,"is_retracted":false,"has_abstract":false,"ca_institutions":"Intertek (Canada)","funders":"National Center for Research Resources; Eunice Kennedy Shriver National Institute of Child Health and Human Development; National Cancer Institute","keywords":"Computer science; Drug; MEDLINE; Artificial intelligence; Parsing; Machine learning; Support vector machine; Natural language processing; Ranking (information retrieval); Set (abstract data type); Knowledge base; Information retrieval; Medicine; Pharmacology; 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":"metacan-v3-hybrid-931329e0061c","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.001716815,0.001372798,0.001980162,0.01606063,0.001369149,0.002704942,0.002206902,0.001523974,0.003676014],"category_scores_gemma":[0.01055913,0.0007880146,0.001606961,0.008082338,0.0004366985,0.002279881,0.002541053,0.001806983,0.003397306],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000876405,"about_ca_system_score_gemma":0.007678501,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0100837,"about_ca_topic_score_gemma":0.02237947,"domain_scores_codex":[0.9984548,0.0001881488,0.0002221778,0.0004433583,0.0005849556,0.0001064495],"domain_scores_gemma":[0.993572,0.003244286,0.0006055044,0.000646179,0.001697327,0.0002348164],"domain_codex":null,"domain_gemma":"methods","domain_candidate":"methods","domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0004992065,0.0009759418,0.01589648,0.003441191,0.00071649,0.002868041,0.0003830953,0.02364254,0.03828001,0.005046334,0.0508988,0.8573518],"study_design_scores_gemma":[0.0004138191,0.0008578948,0.03668554,0.001766748,0.0035637,0.006237102,0.001115076,0.6498916,0.0757778,0.04461945,0.1786725,0.0003988151],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1006107,0.0173609,0.7319784,0.003131225,0.000788848,0.002006265,0.1110076,0.02201446,0.0111016],"genre_scores_gemma":[0.196175,0.006548796,0.6765857,0.0006418157,0.0003445974,0.0007789388,0.116016,0.0003445504,0.002564544],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9982832,"threshold_uncertainty_score":0.02005005,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.006573931731527429,"score_gpt":0.2843456287834984,"score_spread":0.277771697051971,"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."}}