{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002443559,0.0009137483,0.00131295,0.0009802426,0.0003885516,0.0007112026,0.001021,0.001022085,0.0005759065],"category_scores_gemma":[0.00205582,0.0001999044,0.001079783,0.000855009,0.0003539042,0.0006309027,0.0004551237,0.0007286862,0.0004883708],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004517623,"about_ca_system_score_gemma":0.0007252966,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004760483,"about_ca_topic_score_gemma":0.004397544,"domain_scores_codex":[0.9993088,0.0002116261,0.00003473346,0.0002199629,0.0001002887,0.000124469],"domain_scores_gemma":[0.9993871,0.0003085538,0.00004904678,0.00008473214,0.0001334172,0.00003703827],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.001669817,0.0006694145,0.04138783,0.0002792878,0.000568296,0.0003952869,0.0002281771,0.2857029,0.05333189,0.001163322,0.01321595,0.6013877],"study_design_scores_gemma":[0.00003065704,0.00009442215,0.006005376,0.00001190939,0.00005060435,0.00008465707,0.0000399966,0.9829661,0.008719672,0.0009627598,0.001017463,0.00001646861],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.3985494,0.002012123,0.5887498,0.0005962293,0.0002333036,0.0002211449,0.001667672,0.006710405,0.001259886],"genre_scores_gemma":[0.8468762,0.0003644205,0.1441005,0.0003902572,0.0001013778,0.0002641846,0.005325898,0.0002662897,0.002310889],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.004760483,"threshold_uncertainty_score":0.01292288,"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."}}