{"id":"W2076460489","doi":"10.1186/1471-2105-10-414","title":"Modular prediction of protein structural classes from sequences of twilight-zone identity with predicting sequences","year":2009,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":96,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"","keywords":"Computer science; Benchmark (surveying); Artificial intelligence; Support vector machine; Modular design; Similarity (geometry); Feature selection; Feature (linguistics); Pattern recognition (psychology); Class (philosophy); Sequence (biology); Contrast (vision); Data mining; Machine learning; Biology; Image (mathematics)","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":[],"consensus_categories":[],"category_scores_codex":[0.0002641913,0.0002240961,0.0002941823,0.00008533739,0.0000854942,0.0000457381,0.0003816294,0.0001873624,0.00001610088],"category_scores_gemma":[0.000168725,0.0001729553,0.00008682906,0.0001923584,0.0002107022,0.0001140844,0.00008043292,0.0001575729,0.000002152314],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001933075,"about_ca_system_score_gemma":0.0001682296,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00009971873,"about_ca_topic_score_gemma":0.00007166038,"domain_scores_codex":[0.9982685,0.00004998824,0.0008198606,0.0001566883,0.0004753672,0.0002296321],"domain_scores_gemma":[0.998455,0.00002283095,0.0008062866,0.0004299079,0.0002161369,0.00006977116],"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":[0.00050312,0.000139297,0.2439422,0.001666712,0.0003140036,0.000002334117,0.003156425,0.04426293,0.6989824,0.00150646,0.0001326316,0.0053915],"study_design_scores_gemma":[0.001477094,0.002696015,0.08932839,0.0005441598,0.0001425327,0.00004517549,0.002105898,0.4293652,0.4725552,0.0008788293,0.0003387001,0.0005227565],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9133903,0.0001952222,0.08507766,0.00002325013,0.00006673965,0.0003580908,0.0001907268,0.0000353627,0.0006626502],"genre_scores_gemma":[0.8010221,0.00002360855,0.1985356,0.00002902733,0.00007373931,0.000005596295,0.0002692163,0.000008730897,0.00003247354],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3851023,"threshold_uncertainty_score":0.7052912,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01020080503328411,"score_gpt":0.2450921923098636,"score_spread":0.2348913872765795,"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."}}