{"id":"W3194189918","doi":"10.3389/fimmu.2021.727626","title":"Strategies for Accurate Cell Type Identification in CODEX Multiplexed Imaging Data","year":2021,"lang":"en","type":"article","venue":"Frontiers in Immunology","topic":"Single-cell and spatial transcriptomics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":158,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"National Human Genome Research Institute; Juno Therapeutics; U.S. Food and Drug Administration; National Institutes of Health; Cancer Research UK; Parker Institute for Cancer Immunotherapy; National Institute of Allergy and Infectious Diseases; Celgene; U.S. Department of Defense; Silicon Valley Community Foundation; Defence Science and Technology Laboratory; Hamilton Health Sciences Foundation; Bill and Melinda Gates Foundation; National Heart, Lung, and Blood Institute; Pfizer; Cancer Research Institute; National Cancer Institute; Kenneth Rainin Foundation","keywords":"Cluster analysis; Computer science; Normalization (sociology); Artificial intelligence; Segmentation; Multiplexing; Cell type; Pattern recognition (psychology); Identification (biology); Biclustering; Cell; Fuzzy clustering; Biology","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":[0.0001673798,0.0001068726,0.000157262,0.00006865842,0.00003648182,0.00003805995,0.0003445348,0.0001322191,0.000004655805],"category_scores_gemma":[0.00008712812,0.0001239061,0.00002881351,0.0001286953,0.00007502189,0.00001702129,0.000102717,0.0001052328,0.000002013387],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000225066,"about_ca_system_score_gemma":0.0001865943,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005872404,"about_ca_topic_score_gemma":0.000296848,"domain_scores_codex":[0.9989952,0.00007457637,0.0002581103,0.000406217,0.00003520759,0.0002306636],"domain_scores_gemma":[0.999304,0.00001323656,0.00006327915,0.0005280563,0.00007705791,0.00001437607],"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":[0.0002098576,0.00009065798,0.01387677,0.00002327978,0.00002281922,0.000005704735,0.000100381,0.0001613503,0.979216,0.00005074116,0.003183847,0.00305863],"study_design_scores_gemma":[0.006431056,0.0001950927,0.02764111,0.00004896577,0.00004665459,0.00001971487,0.007658786,0.0281029,0.8218136,0.002340693,0.1049323,0.0007691613],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8762639,0.01495025,0.1039111,0.0002967116,0.003653325,0.0003611786,0.0001224815,0.00001873965,0.0004223335],"genre_scores_gemma":[0.9869132,0.0008530892,0.00983365,0.00009476119,0.00005528546,0.00001933278,0.001883555,0.00001976186,0.0003273477],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.1574024,"threshold_uncertainty_score":0.5052745,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02550901066348076,"score_gpt":0.269444644960008,"score_spread":0.2439356342965273,"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."}}