{"id":"W4285023186","doi":"10.22215/etd/2022-15110","title":"Assessing and Improving Protein-Protein Interaction Prediction in E. coli","year":2022,"lang":"en","type":"dissertation","venue":"","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Carleton University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Classifier (UML); Computer science; Artificial intelligence; Machine learning; Interactome; Data mining; Computational biology; Biology; Genetics","routes":{"ca_aff":true,"ca_fund":true,"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":[0.000264859,0.000191946,0.0001480181,0.0001355149,0.0001166159,0.0001281404,0.00009850397,0.0002593688,0.0002795209],"category_scores_gemma":[0.0001780332,0.0002048813,0.00004104085,0.00007754004,0.00001291455,0.00001556133,0.00008112135,0.0004900732,0.00000389776],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006075715,"about_ca_system_score_gemma":0.00008807737,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000220513,"about_ca_topic_score_gemma":0.0002394238,"domain_scores_codex":[0.9989585,0.00007998886,0.0003412238,0.0002959217,0.0001622282,0.0001620826],"domain_scores_gemma":[0.9994577,0.00000596805,0.0002690568,0.0001888287,0.00004343194,0.00003507286],"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":[0.0001980205,0.00006142817,0.000686173,0.0007968788,0.00003830761,0.000004387052,0.0003804213,0.0001634173,0.9673092,0.0001205145,0.0003755271,0.02986566],"study_design_scores_gemma":[0.00440966,0.002939035,0.05217021,0.001646403,0.000182628,0.0001348091,0.03445728,0.05091926,0.7180325,0.0002887848,0.1316496,0.003169782],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9795852,0.0001232897,0.0003288223,0.00002644193,0.000280076,0.0006321378,0.000007645062,0.00002809714,0.01898827],"genre_scores_gemma":[0.9735322,0.00001085219,0.002411567,0.00003443682,0.0001199023,0.0002491649,0.003333194,0.0000423095,0.02026637],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.2492767,"threshold_uncertainty_score":0.8354818,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.007320059679875485,"score_gpt":0.2924007535230604,"score_spread":0.285080693843185,"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."}}