{"id":"W4233935614","doi":"10.1101/462812","title":"PSL-Recommender: Protein Subcellular Localization Prediction using Recommender System","year":2018,"lang":"en","type":"preprint","venue":"bioRxiv (Cold Spring Harbor Laboratory)","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"Princess Margaret Cancer Centre; University Health Network","funders":"","keywords":"Recommender system; PSL; Computer science; Matrix decomposition; Machine learning; Subcellular localization; Artificial intelligence; Information retrieval; Mathematics; Biology; 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":[0.0009923833,0.0006799992,0.0004877246,0.0002238182,0.0003332015,0.0002308561,0.0005913995,0.001185274,0.00003574502],"category_scores_gemma":[0.0002142849,0.0007585178,0.0001930257,0.0002767142,0.0001249085,0.00002123224,0.0007948041,0.0006764684,0.0000504437],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003889213,"about_ca_system_score_gemma":0.000437284,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004992614,"about_ca_topic_score_gemma":0.000001774191,"domain_scores_codex":[0.9967876,0.0003440028,0.0008882436,0.0009745081,0.0004078239,0.0005978097],"domain_scores_gemma":[0.9966956,0.00001113211,0.0008230346,0.001610044,0.0006215776,0.0002385543],"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":[0.000115131,0.0001899865,0.01267988,0.00307018,0.0005299725,0.00001372066,0.00002572421,0.005242686,0.9729046,0.0002399699,0.004982765,0.000005385307],"study_design_scores_gemma":[0.001145703,0.0003538417,0.001846541,0.001511956,0.0002926961,3.83991e-7,0.00002139464,0.2464287,0.6974185,0.000002059365,0.04924784,0.001730436],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6241857,0.0006739934,0.370196,0.0001023684,0.002215171,0.00174087,0.00032119,0.000483519,0.00008118182],"genre_scores_gemma":[0.9770705,0.00007878201,0.02080675,0.0001955687,0.001444773,0.0001593003,0.00002146537,0.0002093195,0.00001354988],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3528848,"threshold_uncertainty_score":0.9994866,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01328849395008648,"score_gpt":0.224955885027758,"score_spread":0.2116673910776715,"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."}}