{"id":"W4307973218","doi":"10.1016/j.xpro.2022.101791","title":"High-content live-cell multiplex screen for chemogenomic compound annotation based on nuclear morphology","year":2022,"lang":"en","type":"article","venue":"STAR Protocols","topic":"Cell Image Analysis Techniques","field":"Biochemistry, Genetics and Molecular Biology","cited_by":19,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Institute of Cancer Research; Horizon 2020 Framework Programme; Genentech; Innovative Medicines Initiative; Ontario Institute for Cancer Research; Deutschen Konsortium für Translationale Krebsforschung; Kungliga Tekniska Högskolan; Ontario Genomics Institute; Takeda Pharmaceutical Company; European Federation of Pharmaceutical Industries and Associations; Janssen Pharmaceuticals; Merck KGaA; Genome Canada; Boehringer Ingelheim; Deutsche Forschungsgemeinschaft; Bristol-Myers Squibb; Deutsches Krebsforschungszentrum; Pfizer","keywords":"High-content screening; Multiplex; Computer science; Scalability; Protocol (science); Annotation; Software; Cell; Computational biology; Bioinformatics; Biology; Artificial intelligence; Genetics; Operating system","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":[0.0003131574,0.0001711053,0.0001983581,0.00007784988,0.0002094571,0.00002822944,0.0003039627,0.00007660467,0.0002669765],"category_scores_gemma":[0.00003720142,0.0001849532,0.0001645988,0.00006907521,0.00005531049,0.000003623124,0.0001513868,0.0001192943,0.00001598555],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007345105,"about_ca_system_score_gemma":0.00005696659,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001186937,"about_ca_topic_score_gemma":0.00001449272,"domain_scores_codex":[0.9987661,0.000124439,0.0002517005,0.000468391,0.0001493078,0.0002401251],"domain_scores_gemma":[0.9991492,0.00002270375,0.000168477,0.0005046016,0.0001030663,0.00005194212],"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":[0.000941727,0.0003335963,0.0001757659,0.00002867462,0.00003042896,0.000006070986,0.00002656868,0.0008193059,0.9858596,0.00002102833,0.01099642,0.0007607896],"study_design_scores_gemma":[0.003319306,0.003294706,0.0005012387,0.000009070397,0.00002824315,0.000004219888,0.0001140197,0.004807317,0.7986028,0.00005207424,0.1889243,0.0003427285],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8824143,0.0000225546,0.007955582,0.0003422766,0.00002972243,0.1081565,0.0003357405,0.000120708,0.0006226284],"genre_scores_gemma":[0.8713266,0.000001203808,0.02073116,0.001423042,0.0001068634,0.1047615,0.001005389,0.00006614839,0.00057814],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.1872568,"threshold_uncertainty_score":0.7542174,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02707069748260971,"score_gpt":0.2832572696607571,"score_spread":0.2561865721781474,"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."}}