{"id":"W2952568226","doi":"10.1101/562082","title":"Evaluation of methods to assign cell type labels to cell clusters from single-cell RNAsequencing data","year":2019,"lang":"en","type":"preprint","venue":"bioRxiv (Cold Spring Harbor Laboratory)","topic":"Single-cell and spatial transcriptomics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":8,"is_retracted":false,"has_abstract":true,"ca_institutions":"Toronto General Hospital; Princess Margaret Cancer Centre; Ontario Institute for Cancer Research; University of Toronto; University Health Network","funders":"","keywords":"Cell type; Computer science; Cell; Cluster analysis; Normalization (sociology); Hierarchical clustering; Computational biology; Data mining; Artificial intelligence; Biology; Genetics","routes":{"ca_aff":true,"ca_fund":false,"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":[0.002949045,0.0006293189,0.0006792544,0.0002190857,0.00008021725,0.0001358827,0.001583876,0.0008021953,0.00004637121],"category_scores_gemma":[0.0004972022,0.0007127628,0.0001479781,0.0004003758,0.0000543554,0.00001895673,0.001314482,0.0004481342,0.00006945308],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000258949,"about_ca_system_score_gemma":0.001465257,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0003345735,"about_ca_topic_score_gemma":0.00001912081,"domain_scores_codex":[0.995443,0.0007730869,0.0007671377,0.001783298,0.0006846562,0.0005487612],"domain_scores_gemma":[0.9942525,0.00008273766,0.0004970567,0.00339296,0.001409629,0.0003650902],"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":[0.000107818,0.0002818261,0.000611208,0.0002383391,0.0001078541,0.000002362843,0.00002357018,0.005178405,0.992318,8.827008e-7,0.001089212,0.00004046562],"study_design_scores_gemma":[0.0008976783,0.000318189,0.0007057251,0.0001916401,0.0005054636,5.84617e-9,0.000009567832,0.00348004,0.9878258,0.000001019172,0.005265004,0.0007999199],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9194776,0.002361175,0.07303327,0.00006165907,0.002400293,0.001451495,0.001038172,0.00005684695,0.0001195267],"genre_scores_gemma":[0.8787283,0.0001006703,0.1200498,0.0004103908,0.0004477879,0.00004636836,0.00003012299,0.0001646989,0.00002176715],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.04701658,"threshold_uncertainty_score":0.9995323,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.07608679451152739,"score_gpt":0.3034211514138141,"score_spread":0.2273343569022867,"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."}}