{"id":"W3131383906","doi":"10.1038/s41467-021-21453-4","title":"Optimal marker gene selection for cell type discrimination in single cell analyses","year":2021,"lang":"en","type":"article","venue":"Nature Communications","topic":"Single-cell and spatial transcriptomics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":115,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"National Heart, Lung, and Blood Institute; Princeton University; York University; National Institutes of Health; National Science Foundation; U.S. Department of Health and Human Services; European Office of Aerospace Research and Development; Air Force Office of Scientific Research; Leona M. and Harry B. Helmsley Charitable Trust","keywords":"Cell type; Computer science; Set (abstract data type); Identification (biology); Computational biology; Cell; Data set; Hierarchy; Selection (genetic algorithm); Artificial intelligence; Pattern recognition (psychology); Biology; 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":[0.00009060642,0.00009009445,0.00008849805,0.00004731039,0.0001140765,0.00002797267,0.0002496557,0.0002529827,0.000007971581],"category_scores_gemma":[0.00008170491,0.00009670253,0.00006983487,0.0002325946,0.00003081335,0.000005919417,0.00007354475,0.0002179264,0.000001688664],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002931496,"about_ca_system_score_gemma":0.0000843301,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002128335,"about_ca_topic_score_gemma":0.001170781,"domain_scores_codex":[0.9993914,0.00008340386,0.0001519735,0.0001923923,0.00005778495,0.0001230646],"domain_scores_gemma":[0.9991129,0.00003790368,0.00005003842,0.0005084837,0.0002621306,0.0000285417],"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":[0.00004088711,0.0004014848,0.00227667,0.00001401458,0.00001166632,1.849097e-7,0.00005163114,0.000273076,0.9955093,0.00004217533,0.00108369,0.0002951848],"study_design_scores_gemma":[0.000486204,0.0001079153,0.002747718,0.000006978095,0.00004134647,0.000003065725,0.0001101046,0.002308836,0.9529408,0.0000247008,0.04108002,0.00014231],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9728524,0.01328875,0.007872829,0.0007760372,0.0002698685,0.0002686037,0.00005514018,0.00002069336,0.004595642],"genre_scores_gemma":[0.9581212,0.0006587005,0.03845496,0.0001842098,0.00006245293,0.00002262492,0.001570924,0.00001725992,0.0009076262],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.04256853,"threshold_uncertainty_score":0.3943415,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04364400665063414,"score_gpt":0.3223347145313431,"score_spread":0.278690707880709,"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."}}