{"id":"W1984674282","doi":"10.1109/tnb.2012.2208473","title":"Enhancing Membrane Protein Subcellular Localization Prediction by Parallel Fusion of Multi-View Features","year":2012,"lang":"en","type":"article","venue":"IEEE Transactions on NanoBioscience","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":29,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"University of Illinois at Urbana-Champaign; Nanjing University of Science and Technology; Concordia University","keywords":"Redundancy (engineering); Subcellular localization; Protein subcellular localization prediction; Computer science; Feature vector; Artificial intelligence; Membrane protein; Benchmark (surveying); Feature (linguistics); Molecular biophysics; Pattern recognition (psychology); Support vector machine; Algorithm; Membrane; Biology; Biochemistry","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003514401,0.0001515628,0.0001241587,0.00007227754,0.0002005636,0.00001604748,0.0001783462,0.0001552073,0.00002923195],"category_scores_gemma":[0.00002872683,0.0001368246,0.00007054418,0.000248678,0.0001213434,0.00002935834,0.000003849897,0.0001294392,0.000009492531],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002374864,"about_ca_system_score_gemma":0.00003963697,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000399329,"about_ca_topic_score_gemma":0.00001881071,"domain_scores_codex":[0.9989144,0.00007533293,0.0002922757,0.0002090166,0.0002484076,0.0002605457],"domain_scores_gemma":[0.9994123,0.000009995847,0.0001404345,0.0002768681,0.0000684965,0.00009193436],"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":[0.00002911985,0.0001831845,0.00009920184,0.00007928025,0.000007541218,6.894121e-8,0.0001621492,0.006092559,0.9918295,0.000007913452,0.00009594912,0.001413519],"study_design_scores_gemma":[0.000317798,0.0002080214,0.0001254766,0.00006464212,0.00001495972,0.000008290081,0.00004235927,0.00620824,0.9899946,8.949079e-7,0.002878785,0.000135901],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1453858,0.0002987909,0.8534988,0.00003250324,0.0003033757,0.0003347846,0.00003682063,0.00002794434,0.00008126527],"genre_scores_gemma":[0.9918156,0.0001839711,0.006850785,0.00009121843,0.00003093205,0.0000316307,0.00003731208,0.00001437092,0.0009442127],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.846648,"threshold_uncertainty_score":0.5579547,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.00763423259583247,"score_gpt":0.2376660334986215,"score_spread":0.230031800902789,"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."}}