{"id":"W4416866234","doi":"10.1016/j.xgen.2025.101073","title":"CellUntangler: Separating distinct biological signals in single-cell data with deep generative models","year":2025,"lang":"en","type":"article","venue":"Cell Genomics","topic":"Single-cell and spatial transcriptomics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia","funders":"Canadian Institutes of Health Research; Natural Sciences and Engineering Research Council of Canada; University of British Columbia; Canada Research Chairs; Canada Foundation for Innovation","keywords":"Process (computing); Generative model; Generative grammar; Space (punctuation); Pattern recognition (psychology); Data-driven; Deep learning","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":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0002337972,0.0003163509,0.0003094444,0.00007124734,0.0001241645,0.00007344077,0.0006651632,0.0002638599,0.00001450657],"category_scores_gemma":[0.00001941645,0.0002751634,0.00006527684,0.0001854681,0.0001363094,0.00001216967,0.0003112219,0.0002030521,0.000007069351],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006549313,"about_ca_system_score_gemma":0.0001774916,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004501309,"about_ca_topic_score_gemma":0.0003674016,"domain_scores_codex":[0.998134,0.0001106903,0.0003958787,0.0008459649,0.00009384931,0.0004196854],"domain_scores_gemma":[0.9989089,0.0000485666,0.0001142117,0.000773932,0.00006722926,0.00008710295],"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":[0.00023687,0.0003647475,0.003634868,0.0000360661,0.00003057413,0.00001413918,0.0001684489,0.01555469,0.9785875,0.00003471412,0.0003032214,0.001034131],"study_design_scores_gemma":[0.002261702,0.0006258842,0.0002078236,0.00003735103,0.00006042837,0.000008458144,0.0004220988,0.06647907,0.9183879,0.000411957,0.01035082,0.0007465347],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8891903,0.002321757,0.09395321,0.0000419137,0.0001526117,0.0003426626,0.00008763526,0.00002132016,0.0138886],"genre_scores_gemma":[0.9853867,0.0002412934,0.01202781,0.0004060353,0.0001525451,0.00001879247,0.0009356085,0.00003596803,0.0007952234],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.09619644,"threshold_uncertainty_score":0.9999701,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04202290260976577,"score_gpt":0.2481356562394736,"score_spread":0.2061127536297078,"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."}}