{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006481002,0.0006324084,0.0004978722,0.001864165,0.0003961405,0.0008903043,0.0006841915,0.0005752682,0.001338536],"category_scores_gemma":[0.001554721,0.0001613004,0.0008328981,0.001100975,0.0003842707,0.001984435,0.0007983255,0.0007498265,0.0006443844],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005839841,"about_ca_system_score_gemma":0.0007496632,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002144504,"about_ca_topic_score_gemma":0.001679796,"domain_scores_codex":[0.999539,0.0001260451,0.000043412,0.0001192414,0.00009139261,0.00008098171],"domain_scores_gemma":[0.99945,0.0002023983,0.0001001958,0.00006418097,0.0001511433,0.00003203794],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0003744769,0.0004351904,0.0127177,0.0003572357,0.0001480709,0.0005274544,0.0006309066,0.07081539,0.08318397,0.01999964,0.006354911,0.804455],"study_design_scores_gemma":[0.00002607225,0.0001638521,0.002664255,0.00002370021,0.00005200586,0.0002549245,0.000191063,0.9577211,0.01640219,0.0195491,0.00290473,0.00004707434],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.1791072,0.0006597064,0.8133099,0.0005319896,0.00006894759,0.0001414079,0.0004920769,0.002493899,0.003194954],"genre_scores_gemma":[0.714904,0.0002933015,0.2800876,0.0001963601,0.00005546996,0.000191762,0.001301073,0.00009503154,0.002875464],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.002144504,"threshold_uncertainty_score":0.004477859,"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."}}