{"id":"W1504124766","doi":"10.1186/1471-2105-14-s3-s14","title":"Protein Function Prediction using Text-based Features extracted from the Biomedical Literature: The CAFA Challenge","year":2013,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Biomedical Text Mining and Ontologies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":46,"is_retracted":false,"has_abstract":true,"ca_institutions":"Queen's University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Protein function prediction; Classifier (UML); Function (biology); DNA microarray; Gene ontology; Artificial intelligence; Data mining; Precision and recall; Protein function; Computational biology; Machine learning; Gene; Biology; Genetics","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":[0.004754442,0.002086808,0.001762835,0.008255143,0.001313058,0.002401283,0.002371386,0.003556804,0.004086746],"category_scores_gemma":[0.02063202,0.000399575,0.001506469,0.004473467,0.0005987975,0.00528289,0.002059528,0.001845652,0.003715975],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001650376,"about_ca_system_score_gemma":0.002428793,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.006204196,"about_ca_topic_score_gemma":0.006866015,"domain_scores_codex":[0.9966357,0.0005087979,0.0005389025,0.001131909,0.001016947,0.0001676286],"domain_scores_gemma":[0.9792244,0.01356758,0.001671099,0.001465858,0.003182848,0.0008882232],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.001495656,0.001350675,0.02799411,0.007044558,0.0004440473,0.003161484,0.001114354,0.008975372,0.07211426,0.001612388,0.1865379,0.6881552],"study_design_scores_gemma":[0.0006993729,0.001785784,0.1113322,0.001396764,0.0007730862,0.01195027,0.003175538,0.5381447,0.135086,0.01118596,0.1838768,0.0005935518],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"methods","genre_scores_codex":[0.4992278,0.01767251,0.1643798,0.01447269,0.001710092,0.002090186,0.1685583,0.1221435,0.009745201],"genre_scores_gemma":[0.3942262,0.003310341,0.4192165,0.001643234,0.0007866656,0.001062259,0.1736282,0.00115084,0.00497589],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.008255143,"threshold_uncertainty_score":0.02514416,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01987038380572221,"score_gpt":0.2384098960389598,"score_spread":0.2185395122332376,"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."}}