{"id":"W4380550560","doi":"10.1101/2023.06.13.544850","title":"The impacts of active and self-supervised learning on efficient annotation of single-cell expression data","year":2023,"lang":"en","type":"preprint","venue":"bioRxiv (Cold Spring Harbor Laboratory)","topic":"Single-cell and spatial transcriptomics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"Vector Institute; Sinai Health System; Lunenfeld-Tanenbaum Research Institute; Institute of Cancer Research; Ontario Institute for Cancer Research; University of Toronto","funders":"Canadian Institutes of Health Research; Natural Sciences and Engineering Research Council of Canada; Canada Research Chairs; Princess Margaret Cancer Foundation","keywords":"Annotation; Computer science; Benchmarking; Classifier (UML); Machine learning; Artificial intelligence; Heuristic; Supervised learning; Active learning (machine learning); Similarity (geometry); Data mining","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":[0.0128045,0.001060636,0.001193203,0.001128416,0.0007723542,0.001901875,0.002745171,0.001952118,0.0008997469],"category_scores_gemma":[0.02587212,0.0005099047,0.000837206,0.001130618,0.0021402,0.00296068,0.00201638,0.001893141,0.0007818525],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001121833,"about_ca_system_score_gemma":0.001045221,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002162602,"about_ca_topic_score_gemma":0.003047142,"domain_scores_codex":[0.9953875,0.002318755,0.0001843313,0.00100836,0.0008911272,0.0002099716],"domain_scores_gemma":[0.9717272,0.01940178,0.001430984,0.004510105,0.002359713,0.0005702155],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.001632493,0.0007810714,0.01638935,0.000747901,0.0004278319,0.0001951124,0.0006674181,0.5260273,0.06035132,0.01205034,0.007498074,0.3732318],"study_design_scores_gemma":[0.00002961309,0.0000889021,0.001365685,0.0000232808,0.00001988532,0.00004114963,0.00005485458,0.9720043,0.01892226,0.006422877,0.001007478,0.00001974848],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2115857,0.001189703,0.7784519,0.0009766473,0.0001746457,0.0001319534,0.0004973572,0.004710727,0.00228146],"genre_scores_gemma":[0.6251834,0.0003197821,0.3691271,0.0005256592,0.00009885522,0.0002319705,0.00169196,0.0008637239,0.001957606],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.0128045,"threshold_uncertainty_score":0.06771743,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02303407408858868,"score_gpt":0.2301645880025953,"score_spread":0.2071305139140066,"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."}}