{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002620697,0.0001963318,0.0001275716,0.00003389893,0.0002725686,0.0001567542,0.000322144,0.0004345992,0.00004192208],"category_scores_gemma":[0.0003212027,0.00009860393,0.000102998,0.0001881627,0.0003270823,0.00001560257,0.00009007405,0.000308014,0.00003057887],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001740643,"about_ca_system_score_gemma":0.0001213319,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00008322109,"about_ca_topic_score_gemma":0.00003978244,"domain_scores_codex":[0.9988092,0.0001026531,0.000338648,0.0001787446,0.0002978125,0.0002729005],"domain_scores_gemma":[0.9990737,0.0000875503,0.0001638812,0.0004850276,0.0001035949,0.00008627521],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.000966542,0.001019542,0.004658808,0.0007233479,0.0008165407,0.000007047017,0.005171504,0.0005581264,0.207401,0.0006563857,0.2332138,0.5448074],"study_design_scores_gemma":[0.004057933,0.002198922,0.09821472,0.0007712691,0.0003074461,0.00007709605,0.005371997,0.3885515,0.0120891,0.001507999,0.4856507,0.001201358],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5477993,0.007791749,0.4311469,0.007042907,0.001702848,0.002659381,0.0005878464,0.0003049401,0.0009641421],"genre_scores_gemma":[0.9173678,0.00009643867,0.07477614,0.002338666,0.001872499,0.0002534522,0.00280722,0.00004621339,0.000441554],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.543606,"threshold_uncertainty_score":0.4020951,"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."}}