{"id":"W4392356342","doi":"10.1038/s41587-023-02097-9","title":"Characterizing the impacts of dataset imbalance on single-cell data integration","year":2024,"lang":"en","type":"article","venue":"Nature Biotechnology","topic":"Single-cell and spatial transcriptomics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":45,"is_retracted":false,"has_abstract":false,"ca_institutions":"Ontario Institute for Cancer Research; Lunenfeld-Tanenbaum Research Institute; Simon Fraser University; Vector Institute; University of Toronto; University Health Network","funders":"Natural Sciences and Engineering Research Council of Canada; Government of Canada","keywords":"Data integration; Cluster analysis; Computer science; Inference; Benchmarking; Data mining; Robustness (evolution); Annotation; Computational biology; Biology; Artificial intelligence; Gene; Genetics","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":[],"consensus_categories":[],"category_scores_codex":[0.0001815067,0.0001459132,0.0001255923,0.00007394724,0.00004457768,0.0000310203,0.0007111887,0.0008223701,0.000006352514],"category_scores_gemma":[0.0001268775,0.00009791789,0.00003941804,0.0001716205,0.0001400801,0.000007756815,0.0001758753,0.0006244018,0.000009700432],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001308926,"about_ca_system_score_gemma":0.00004528815,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001513616,"about_ca_topic_score_gemma":0.00005077086,"domain_scores_codex":[0.9990916,0.00003082898,0.000172311,0.0004297392,0.00009600998,0.000179474],"domain_scores_gemma":[0.998817,0.00002764764,0.00006017237,0.001048168,0.00002444179,0.00002259078],"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":[0.000056073,0.00004841684,0.00004512277,0.0000332125,0.00002496903,0.000004327669,0.00001400459,3.098727e-7,0.9817541,0.0005544138,0.009796576,0.00766847],"study_design_scores_gemma":[0.0001075082,0.0002398919,0.0001036424,0.00004102828,0.00001531276,0.00001384382,0.00001801345,0.0001656082,0.7751672,0.00003288974,0.2240081,0.00008691852],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9748113,0.009740422,0.001695212,0.007512611,0.001460487,0.0002891637,0.003947344,0.0001018013,0.000441639],"genre_scores_gemma":[0.9930461,0.0005759153,0.0003416022,0.0007300847,0.0002099592,0.000002974706,0.005032076,0.00002009109,0.00004118527],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.2142115,"threshold_uncertainty_score":0.6342872,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01714862689806865,"score_gpt":0.2666866661535022,"score_spread":0.2495380392554336,"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."}}