{"id":"W2132581719","doi":"10.1002/jcc.21053","title":"Prediction of integral membrane protein type by collocated hydrophobic amino acid pairs","year":2008,"lang":"en","type":"article","venue":"Journal of Computational Chemistry","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":89,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"","keywords":"Feature selection; Computer science; Classifier (UML); Benchmark (surveying); Transmembrane protein; Feature (linguistics); Transmembrane domain; Integral membrane protein; Sequence (biology); Artificial intelligence; Pattern recognition (psychology); Membrane protein; Algorithm; Biological system; Chemistry; Amino acid; Membrane; Biology; Biochemistry","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":[0.0001576744,0.0001134609,0.0001710121,0.0000292418,0.00004725847,0.00000601422,0.0001676963,0.0001238001,0.0000491139],"category_scores_gemma":[0.000152529,0.0001038679,0.00009057983,0.0001167645,0.0001037717,0.000008612924,0.00003258,0.000207483,0.000002022763],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002655634,"about_ca_system_score_gemma":0.0002363601,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000001743363,"about_ca_topic_score_gemma":7.318623e-8,"domain_scores_codex":[0.9989747,0.00002713935,0.0005012428,0.000084972,0.0003109435,0.0001010196],"domain_scores_gemma":[0.9988424,0.00001395673,0.0005065539,0.00009723552,0.0004713525,0.00006857127],"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":[0.0001800056,0.00008665826,0.001433523,0.00008930023,0.00008414259,0.000004535644,0.00005008371,0.01628686,0.9761193,0.000001301382,0.005577314,0.00008697021],"study_design_scores_gemma":[0.0008042724,0.0003520927,0.001156559,0.00005102321,0.00001736655,0.0005302533,0.00003496978,0.00309935,0.9905336,0.00007340225,0.003248856,0.00009828162],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9968599,0.0001940703,0.001986767,0.00007021263,0.00006487477,0.00006174788,0.00002686019,0.000006295403,0.0007292875],"genre_scores_gemma":[0.9951514,0.00002715449,0.003857606,0.00003714248,0.0001480019,0.000001357777,0.000248581,0.00001220868,0.0005165319],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.01441427,"threshold_uncertainty_score":0.423561,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.008975504715840538,"score_gpt":0.2198560894298847,"score_spread":0.2108805847140442,"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."}}