{"id":"W2904022159","doi":"10.1101/500686","title":"Text-mining clinically relevant cancer biomarkers for curation into the CIViC database","year":2018,"lang":"en","type":"preprint","venue":"bioRxiv (Cold Spring Harbor Laboratory)","topic":"Biomedical Text Mining and Ontologies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":4,"is_retracted":false,"has_abstract":true,"ca_institutions":"Simon Fraser University; Canada's Michael Smith Genome Sciences Centre; University of British Columbia","funders":"National Cancer Institute; National Human Genome Research Institute; National Institutes of Health","keywords":"Data curation; Computer science; Precision medicine; Construct (python library); Cancer; Resource (disambiguation); MEDLINE; Information retrieval; Data science; Medicine; Pathology; Biology; Internal medicine","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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.001522938,0.0004974705,0.0004356924,0.00009561647,0.0003426672,0.0001525124,0.0009202852,0.0009001695,0.00002367501],"category_scores_gemma":[0.002018201,0.0003896578,0.0002424621,0.0002187595,0.0006270002,0.00001038388,0.0008515383,0.0004109246,0.00001542751],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00008252562,"about_ca_system_score_gemma":0.0009079973,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00008693738,"about_ca_topic_score_gemma":0.00004419028,"domain_scores_codex":[0.9969739,0.0001925698,0.0007300797,0.001245853,0.0002986638,0.0005589871],"domain_scores_gemma":[0.9969686,0.0001778573,0.0005692769,0.001544991,0.0005285695,0.0002106513],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0003312545,0.000111083,0.003631039,0.0003678261,0.0005738081,0.000006913132,0.00004052223,0.00001075584,0.9754929,0.00005427302,0.01905139,0.0003282405],"study_design_scores_gemma":[0.002229156,0.001081971,0.02141581,0.001405554,0.0006707669,8.559318e-8,0.0000760144,0.002674989,0.5452935,0.00002259594,0.4228387,0.002290828],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.961115,0.006073598,0.02530026,0.002288497,0.003213949,0.001187106,0.0006057042,0.0002037888,0.00001207363],"genre_scores_gemma":[0.9605786,0.001967872,0.03323668,0.0009285649,0.00233594,0.0007950685,0.00001213526,0.0001241271,0.00002105659],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.4301994,"threshold_uncertainty_score":0.9998555,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02491469509453119,"score_gpt":0.2972968484878694,"score_spread":0.2723821533933382,"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."}}