{"id":"W3037787710","doi":"10.1002/minf.202000033","title":"Using Language Representation Learning Approach to Efficiently Identify Protein Complex Categories in Electron Transport Chain","year":2020,"lang":"en","type":"article","venue":"Molecular Informatics","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":4,"is_retracted":false,"has_abstract":true,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"","keywords":"Computer science; Artificial intelligence; Feature learning; Representation (politics); Word embedding; Natural language processing; Machine learning; Feature (linguistics); Pattern recognition (psychology); Support vector machine; Categorization; Multi-task learning; Embedding; Task (project management)","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":[0.0002985109,0.0002259671,0.000231646,0.0001201506,0.00008645823,0.00006326551,0.0002883544,0.0001357568,0.000005956523],"category_scores_gemma":[0.0002296768,0.0002421394,0.00008463197,0.0004651608,0.00004135546,0.00002048597,0.000120657,0.0003168439,0.00001798744],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003691663,"about_ca_system_score_gemma":0.0000666849,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004652137,"about_ca_topic_score_gemma":0.000006649594,"domain_scores_codex":[0.9983898,0.00008886103,0.0006171964,0.0001924715,0.0003327182,0.0003789292],"domain_scores_gemma":[0.9993162,0.000004847772,0.0002022251,0.0002748138,0.00006352601,0.0001384257],"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":[0.00006707812,0.00003906804,0.00150757,0.0002399968,0.00002769699,0.000005851279,0.009521412,0.4426733,0.5452502,0.0002163602,0.0000331042,0.000418402],"study_design_scores_gemma":[0.001350041,0.0004933517,0.002068862,0.00005008744,0.00003754171,0.00003415267,0.005199778,0.6635243,0.3223388,0.00001397577,0.004122808,0.0007662158],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6733504,0.00003032015,0.3229493,0.00006135764,0.00001254293,0.0005104656,0.000004257813,0.00003384837,0.003047474],"genre_scores_gemma":[0.9486059,0.000002623972,0.04988404,0.0007838116,0.00003625557,0.00002981168,0.0005861628,0.00003281981,0.00003856376],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.2752555,"threshold_uncertainty_score":0.987416,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02120448430788708,"score_gpt":0.3007711008899546,"score_spread":0.2795666165820676,"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."}}