{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009444877,0.0006103425,0.0008764802,0.000748146,0.0003566794,0.000897722,0.0007945187,0.0007555993,0.0008630008],"category_scores_gemma":[0.00241326,0.0003353773,0.0005381392,0.0009112422,0.0008555154,0.0006834655,0.0009189195,0.001038813,0.0006129544],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005396568,"about_ca_system_score_gemma":0.0009008641,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001037761,"about_ca_topic_score_gemma":0.002215601,"domain_scores_codex":[0.9994412,0.0001059191,0.0000267293,0.0001945696,0.0001718596,0.00005982797],"domain_scores_gemma":[0.999378,0.0002793703,0.00007044643,0.0001215075,0.0001046566,0.00004607169],"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":[0.0003780871,0.0001834746,0.005141965,0.0002017994,0.00006388372,0.0001660067,0.0002515708,0.1660951,0.5726665,0.01655171,0.002232791,0.2360672],"study_design_scores_gemma":[0.00002438382,0.0000711432,0.001600823,0.00001686458,0.00002299545,0.00008612614,0.00005725093,0.8566628,0.1228795,0.01548611,0.003058972,0.00003292005],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.05413917,0.0001914306,0.9439766,0.00008665026,0.00001946613,0.00004065765,0.0001978196,0.0006837602,0.0006643005],"genre_scores_gemma":[0.3086919,0.0003271056,0.6875857,0.0001906031,0.0000307759,0.0002451563,0.001044878,0.0003416465,0.001542283],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.001037761,"threshold_uncertainty_score":0.004994929,"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."}}