{"id":"W4322503821","doi":"10.3390/genes14030596","title":"Cell Type Annotation Model Selection: General-Purpose vs. Pattern-Aware Feature Gene Selection in Single-Cell RNA-Seq Data","year":2023,"lang":"en","type":"article","venue":"Genes","topic":"Single-cell and spatial transcriptomics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":4,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Windsor","funders":"Natural Sciences and Engineering Research Council of Canada; Compute Canada; University of Windsor","keywords":"Support vector machine; Computer science; Annotation; Scalability; Feature selection; Cluster analysis; Artificial intelligence; Machine learning; Boosting (machine learning); Identification (biology); Data mining; Pattern recognition (psychology); Biology","routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0001520049,0.0002348561,0.000174618,0.0001242044,0.0001243879,0.00005826601,0.0003066449,0.0003016022,0.00001332618],"category_scores_gemma":[0.00001260542,0.0002500265,0.00005593389,0.0005093512,0.00002554558,0.00001929215,0.0001143381,0.0001575652,0.00003328969],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003883786,"about_ca_system_score_gemma":0.0001269241,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001337337,"about_ca_topic_score_gemma":0.000539399,"domain_scores_codex":[0.998534,0.00006817634,0.0002292698,0.0006466294,0.0001676542,0.0003543269],"domain_scores_gemma":[0.9993446,0.000007405778,0.00008089982,0.0003523302,0.0001404383,0.00007425509],"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":[0.0001010287,0.0001203761,0.006324027,0.00004961623,0.00001425664,0.000004556667,0.00006436313,0.02031736,0.9564391,8.827714e-7,0.01214992,0.00441456],"study_design_scores_gemma":[0.0007164039,0.0002551753,0.001272977,0.000009360982,0.00002787143,0.00001058002,0.00002588587,0.1683621,0.8196837,0.00002205801,0.009278827,0.0003350902],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9859658,0.000908228,0.01190061,0.0001719459,0.0004278337,0.0002414871,0.0001099893,0.00008237157,0.000191763],"genre_scores_gemma":[0.9878384,0.0009842821,0.002017993,0.0003471285,0.0006888084,0.00002005598,0.003312686,0.0000665533,0.004724021],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.1480447,"threshold_uncertainty_score":0.9999952,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03822515900193371,"score_gpt":0.2565437040174258,"score_spread":0.2183185450154921,"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."}}