{"id":"W4303672047","doi":"10.1101/2022.10.06.511156","title":"The differential impacts of dataset imbalance in single-cell data integration","year":2022,"lang":"en","type":"preprint","venue":"bioRxiv (Cold Spring Harbor Laboratory)","topic":"Single-cell and spatial transcriptomics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":7,"is_retracted":false,"has_abstract":true,"ca_institutions":"Lunenfeld-Tanenbaum Research Institute; Vector Institute; University of Toronto; University Health Network","funders":"","keywords":"Cluster analysis; Data integration; Benchmarking; Computer science; Pipeline (software); Data mining; Sample (material); Annotation; Data type; Sample size determination; Artificial intelligence; Statistics; Mathematics","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.01564195,0.001111313,0.001252915,0.001792119,0.00159007,0.003141353,0.001904155,0.0009279188,0.001029483],"category_scores_gemma":[0.03922292,0.0006093003,0.001458665,0.002671432,0.001327372,0.002277399,0.00440738,0.001998159,0.0006698603],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001743498,"about_ca_system_score_gemma":0.001636083,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002634304,"about_ca_topic_score_gemma":0.004033234,"domain_scores_codex":[0.9858118,0.004448564,0.001416927,0.003042196,0.004622165,0.0006582348],"domain_scores_gemma":[0.9828116,0.008658517,0.001480444,0.003428065,0.003107054,0.0005142572],"domain_codex":null,"domain_gemma":"methods","domain_candidate":"methods","domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.002677993,0.0005829989,0.1781679,0.002068374,0.001564033,0.001046776,0.002473447,0.1914494,0.405238,0.01069578,0.01382551,0.1902098],"study_design_scores_gemma":[0.0001320512,0.0006922313,0.08590452,0.0002511281,0.0003901462,0.0008482496,0.001076289,0.567176,0.2950204,0.02629228,0.02194761,0.0002690622],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5547679,0.001932062,0.4212386,0.001153021,0.0005127973,0.0005834537,0.006969129,0.009614441,0.003228546],"genre_scores_gemma":[0.7315432,0.0004645669,0.2481184,0.000824801,0.00008295036,0.0007793295,0.01597363,0.001615655,0.0005975395],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9843581,"threshold_uncertainty_score":0.08272356,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02242270811863101,"score_gpt":0.2370273541591535,"score_spread":0.2146046460405225,"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."}}