{"id":"W2143507938","doi":"10.1145/956750.956800","title":"Frequent-subsequence-based prediction of outer membrane proteins","year":2003,"lang":"en","type":"article","venue":"","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":78,"is_retracted":false,"has_abstract":true,"ca_institutions":"Simon Fraser University","funders":"","keywords":"Bacterial outer membrane; Subsequence; Support vector machine; Computational biology; Classifier (UML); Bacteria; Membrane protein; Computer science; Artificial intelligence; Biology; Bioinformatics; Machine learning; Biochemistry; Membrane; Mathematics; Gene; Genetics","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":[0.0001888597,0.00009668761,0.0000896571,0.00003363705,0.00002953948,0.000008461321,0.000100034,0.0001090945,0.0001832715],"category_scores_gemma":[0.0001556589,0.0000818679,0.00005897955,0.00006010253,0.00005759388,0.00000311568,0.00001493851,0.00006963839,0.00001188627],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000008280776,"about_ca_system_score_gemma":0.00007449434,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001324168,"about_ca_topic_score_gemma":0.000007089957,"domain_scores_codex":[0.9993322,0.00005057118,0.0002271978,0.0001276126,0.0001272891,0.000135079],"domain_scores_gemma":[0.999497,0.000005310143,0.00009317716,0.0002909745,0.00007032444,0.00004323408],"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":[0.00002751244,0.00007618079,0.0142228,0.0000862284,0.00003662496,0.000001015143,0.00003646425,0.001317469,0.9808853,0.002150726,0.0006379659,0.0005217395],"study_design_scores_gemma":[0.0005116304,0.0002748061,0.0009596338,0.00001256124,0.000009519371,0.000008973685,0.0000181224,0.001361597,0.9752344,0.00004271703,0.02146751,0.00009848314],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8171511,0.00007872345,0.1029101,0.000160347,0.0002027009,0.0005328823,0.00004070929,0.00005030357,0.07887315],"genre_scores_gemma":[0.969466,0.000008325266,0.02904548,0.0002446443,0.00003346242,0.00001846222,0.00009551673,0.00001157009,0.001076536],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.1523149,"threshold_uncertainty_score":0.3338476,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01055053056386303,"score_gpt":0.2280865789526886,"score_spread":0.2175360483888255,"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."}}