{"id":"W4306800518","doi":"10.1007/978-3-031-17024-9_1","title":"TooT-BERT-T: A BERT Approach on Discriminating Transport Proteins from Non-transport Proteins","year":2022,"lang":"en","type":"book-chapter","venue":"Lecture notes in networks and systems","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":7,"is_retracted":false,"has_abstract":false,"ca_institutions":"Concordia University","funders":"","keywords":"Transmembrane protein; Transporter; Transport protein; Classifier (UML); Representation (politics); Membrane transport protein; Membrane; Membrane protein; Chemistry; Computer science; Computational biology; Artificial intelligence; Biology; Biochemistry; Gene","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":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0004629639,0.0007739763,0.0008507022,0.0001284311,0.0002317957,0.00005878627,0.0004150696,0.001104647,0.00006267507],"category_scores_gemma":[0.00003941059,0.0006765911,0.0002436777,0.00007168249,0.0001144277,0.000008701601,0.0001046302,0.001582504,0.000001893026],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007050271,"about_ca_system_score_gemma":0.00008824463,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000777076,"about_ca_topic_score_gemma":0.0004981694,"domain_scores_codex":[0.9971372,0.00007764711,0.0008867801,0.0009019875,0.0004811224,0.0005152479],"domain_scores_gemma":[0.998496,0.00007119017,0.0004780156,0.0007683082,0.00005213586,0.0001343766],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0008809135,0.0002920495,0.008660894,0.002774964,0.0009354518,0.0001941888,0.00319375,0.9574736,0.001192423,0.004341702,0.0004728849,0.01958719],"study_design_scores_gemma":[0.005568726,0.005150985,0.0039288,0.006224101,0.0008450463,0.0003484293,0.00020304,0.4469295,0.0004908213,0.001305766,0.5215366,0.007468109],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01993482,0.01103297,0.6211657,0.0003122593,0.002514587,0.01103271,0.000820456,0.0001829438,0.3330036],"genre_scores_gemma":[0.9801829,0.0004138955,0.0025458,0.0003201523,0.00192772,0.000516685,0.005332272,0.0002250132,0.008535568],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9602481,"threshold_uncertainty_score":0.9995685,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.009424661949098445,"score_gpt":0.2156757947777839,"score_spread":0.2062511328286855,"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."}}