{"id":"W4407602955","doi":"10.1101/2025.02.11.637700","title":"Deconvolution of Sample Identity in Single-Cell RNA Sequencing <i>via</i> Genome Imputation","year":2025,"lang":"en","type":"preprint","venue":"bioRxiv (Cold Spring Harbor Laboratory)","topic":"Single-cell and spatial transcriptomics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University Health Network; Princess Margaret Cancer Centre; University of Toronto","funders":"","keywords":"Deconvolution; Imputation (statistics); Computational biology; Sample (material); Genome; Computer science; Biology; Genetics; Algorithm; Gene; Chromatography; Missing data; Machine learning; Chemistry","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":[],"consensus_categories":[],"category_scores_codex":[0.008729674,0.0008524538,0.001366612,0.001063854,0.0008844866,0.002100284,0.001997319,0.001249387,0.001987377],"category_scores_gemma":[0.01326875,0.0006541849,0.001386847,0.001349952,0.001083725,0.0007666481,0.001986381,0.002382956,0.001686897],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001220083,"about_ca_system_score_gemma":0.001969686,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001643753,"about_ca_topic_score_gemma":0.001954397,"domain_scores_codex":[0.9955912,0.001286866,0.0002704503,0.001414816,0.001108981,0.0003277403],"domain_scores_gemma":[0.9914886,0.002965775,0.001019277,0.00295591,0.001388685,0.000181744],"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":[0.001696126,0.0003755589,0.05318892,0.0008733962,0.0008129365,0.0006720424,0.001039053,0.1125105,0.4546164,0.0332882,0.006811923,0.334115],"study_design_scores_gemma":[0.00004060895,0.0001229079,0.01750685,0.00007095935,0.0001738436,0.0004988933,0.0001204134,0.446528,0.500648,0.02294618,0.01123476,0.0001085298],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.04303075,0.0001486318,0.9535832,0.0001386833,0.00008106332,0.00005150409,0.0006691253,0.001566086,0.0007310082],"genre_scores_gemma":[0.2527813,0.0001803438,0.7399364,0.0003110743,0.00004189185,0.0002130284,0.003568563,0.001241365,0.00172596],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.008729674,"threshold_uncertainty_score":0.04616749,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01476697498235585,"score_gpt":0.2227519234455816,"score_spread":0.2079849484632257,"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."}}