{"id":"W2030124080","doi":"10.1186/1471-2164-8-191","title":"C-terminal motif prediction in eukaryotic proteomes using comparative genomics and statistical over-representation across protein families","year":2007,"lang":"en","type":"article","venue":"BMC Genomics","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":16,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"Natural Sciences and Engineering Research Council of Canada; University of Toronto; Ontario Genomics; Ontario Genomics Institute; Genome Canada","keywords":"Biology; Computational biology; Proteome; Human proteome project; Proteomics; Signal peptide; Tripeptide; Genomics; Genetics; Genome; Peptide sequence; Gene; Amino acid","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":[0.001715972,0.0003745079,0.0004464073,0.00226356,0.0003399194,0.0004120356,0.000348016,0.0004502995,0.0004568865],"category_scores_gemma":[0.002786026,0.0001615547,0.0007069433,0.001736485,0.000532647,0.0003650857,0.0005072835,0.0003531983,0.0001765452],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005432561,"about_ca_system_score_gemma":0.000551734,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001315761,"about_ca_topic_score_gemma":0.001044573,"domain_scores_codex":[0.9994636,0.0001901907,0.00003368539,0.0001601338,0.0001018544,0.00005045711],"domain_scores_gemma":[0.9985375,0.0008687124,0.0002993069,0.00007079548,0.0001480669,0.00007560638],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.001652151,0.0002592165,0.05274913,0.0005850802,0.0004303632,0.0006425591,0.0004398832,0.04728681,0.8010114,0.002303289,0.0003930371,0.09224709],"study_design_scores_gemma":[0.00006995588,0.001240969,0.1936671,0.00005150535,0.0004102631,0.002030508,0.0003538461,0.6422441,0.1521162,0.005240566,0.00246999,0.0001050308],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9196166,0.000343109,0.07892608,0.00005442242,0.000004791186,0.00003906793,0.0003239807,0.0003182263,0.0003737872],"genre_scores_gemma":[0.9270875,0.000140887,0.07143909,0.00003426656,0.000008883151,0.00006779643,0.001059513,0.00005576544,0.0001063329],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.00226356,"threshold_uncertainty_score":0.009075046,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02726146379312643,"score_gpt":0.3293585705353219,"score_spread":0.3020971067421955,"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."}}