{"id":"W4401289167","doi":"10.1038/s41467-024-50963-0","title":"A unified model for interpretable latent embedding of multi-sample, multi-condition single-cell data","year":2024,"lang":"en","type":"article","venue":"Nature Communications","topic":"Single-cell and spatial transcriptomics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":7,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill Genome Centre; McGill University Health Centre; Jewish General Hospital; University of Toronto; McGill University","funders":"Canadian Institutes of Health Research; Alliance de recherche numérique du Canada; Government of Canada","keywords":"Computer science; Generative model; Sample (material); Gene regulatory network; Embedding; Computational biology; Artificial intelligence; Data mining; Generative grammar; Biology; Genetics; Gene; Gene expression","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":[0.0001898656,0.0001276086,0.0001312305,0.00006276467,0.0001111021,0.00004299726,0.001075577,0.0002906239,0.000002722532],"category_scores_gemma":[0.0001716385,0.0001261693,0.00009402673,0.0001052488,0.00008226961,0.00001592147,0.0003625391,0.0003077346,0.000001273601],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002008207,"about_ca_system_score_gemma":0.00008581945,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002963374,"about_ca_topic_score_gemma":0.0004449691,"domain_scores_codex":[0.9991952,0.00004400171,0.0002478021,0.0002988591,0.00006619783,0.0001479097],"domain_scores_gemma":[0.9979426,0.0001154395,0.00006350332,0.001698328,0.0001389549,0.0000411969],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00004052088,0.0005216334,0.0001438599,0.000123185,0.0001017481,1.702253e-7,0.0002650004,0.002330786,0.9922045,0.0007160936,0.002011062,0.0015414],"study_design_scores_gemma":[0.0004821231,0.00005311731,0.00002150698,0.00006639136,0.0000817539,0.000001184938,0.00004951391,0.9403124,0.04401413,0.00007468328,0.01469887,0.0001443048],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02426174,0.01720445,0.9534957,0.0004386895,0.000363519,0.00056318,0.003387589,0.00006659217,0.0002185413],"genre_scores_gemma":[0.8320789,0.0004625407,0.1609769,0.000109809,0.00003132105,0.00003149352,0.005934997,0.00002834118,0.0003456363],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9481904,"threshold_uncertainty_score":0.5145035,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.09431706963637562,"score_gpt":0.3528506406107726,"score_spread":0.258533570974397,"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."}}