{"id":"W4312192705","doi":"10.1038/s42003-022-04343-3","title":"A statistical framework for high-content phenotypic profiling using cellular feature distributions","year":2022,"lang":"en","type":"article","venue":"Communications Biology","topic":"Cell Image Analysis Techniques","field":"Biochemistry, Genetics and Molecular Biology","cited_by":17,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Tamkeen; Simon Fraser University; New York University Abu Dhabi","keywords":"Workflow; High-content screening; Leverage (statistics); Feature (linguistics); Computer science; Pattern recognition (psychology); Profiling (computer programming); Metric (unit); Phenotype; Data mining; Feature vector; Dimensionality reduction; Computational biology; Artificial intelligence; Biological system; Biology; Cell; Genetics","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002667496,0.000121636,0.0001690168,0.00005628372,0.000691672,0.00001669402,0.0007855719,0.0001327038,0.00003894486],"category_scores_gemma":[0.000338207,0.0001292271,0.00009674187,0.0001624556,0.0002284729,0.000002548737,0.0009801812,0.0002841915,0.00000167352],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000658603,"about_ca_system_score_gemma":0.00008063066,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003996454,"about_ca_topic_score_gemma":0.0000137278,"domain_scores_codex":[0.9989301,0.0002847273,0.0002151907,0.0002979298,0.00004747311,0.0002245925],"domain_scores_gemma":[0.9980584,0.0001277124,0.0001186577,0.0015184,0.0001324499,0.00004435617],"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":[0.00003659097,0.000168091,0.001529458,0.00000660759,0.00009790947,3.587939e-7,0.0000168324,0.00002058058,0.8079895,0.1875922,0.001255786,0.001286057],"study_design_scores_gemma":[0.0009630836,0.0009891674,0.0009013976,0.00001729451,0.0004776302,0.00003492193,0.0007469424,0.007075808,0.6385003,0.1210089,0.228356,0.000928648],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.07252672,0.002200811,0.9232441,0.00084203,0.00004529612,0.0004471974,0.0005605873,0.00004062516,0.00009270263],"genre_scores_gemma":[0.6589782,0.00008039334,0.3330739,0.0001642074,0.00005080221,0.0003614152,0.007195399,0.00001468631,0.00008097165],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.5901701,"threshold_uncertainty_score":0.5319852,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04723667122809626,"score_gpt":0.3397096908726084,"score_spread":0.2924730196445122,"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."}}