{"id":"W2502583812","doi":"10.1371/journal.pone.0158712","title":"An Unsupervised kNN Method to Systematically Detect Changes in Protein Localization in High-Throughput Microscopy Images","year":2016,"lang":"en","type":"article","venue":"PLoS ONE","topic":"Cell Image Analysis Techniques","field":"Biochemistry, Genetics and Molecular Biology","cited_by":15,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Artificial intelligence; Pattern recognition (psychology); Protein subcellular localization prediction; Feature vector; Feature (linguistics); Subcellular localization; Proteome; Unsupervised learning; Computational biology; Gene; Bioinformatics; 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":[0.0005490627,0.0001614347,0.0003189833,0.0001722235,0.0000204851,0.00003065589,0.0002316261,0.0001459418,0.00003321624],"category_scores_gemma":[0.0002258504,0.0001288628,0.00003189091,0.0002568296,0.00003114886,0.00001098964,0.00008840834,0.00005125465,0.00001626812],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005251767,"about_ca_system_score_gemma":0.00002789756,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001549469,"about_ca_topic_score_gemma":0.0008662239,"domain_scores_codex":[0.9984876,0.0003267936,0.000304307,0.0004638686,0.0001691812,0.0002482754],"domain_scores_gemma":[0.9991871,0.0000200739,0.000065642,0.0005375626,0.0001177421,0.00007195171],"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":[0.00005380668,0.0003713123,0.001277284,0.0001843552,0.00003771715,0.000005299136,0.00003460867,0.000003488441,0.9967847,0.000009946883,0.00006399236,0.00117346],"study_design_scores_gemma":[0.0003884642,0.0003783059,0.0003257347,0.0005742752,0.00003131086,6.538777e-7,0.00001730551,0.0001858735,0.9977227,0.000127886,0.00005566898,0.0001917999],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7476051,0.0001043078,0.2507454,0.0004853649,0.00000272926,0.0009364046,0.000007768701,0.00004033478,0.00007257436],"genre_scores_gemma":[0.8556139,0.00006567942,0.1433377,0.0002811773,0.0000559641,0.0003718294,0.00003244892,0.00003411403,0.0002072062],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.1080088,"threshold_uncertainty_score":0.5254872,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01478564595809819,"score_gpt":0.2811546069823574,"score_spread":0.2663689610242592,"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."}}