{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0004904105,0.0003964742,0.0004578564,0.0002607745,0.00007128575,0.00006792769,0.000461912,0.0006598073,0.000007983137],"category_scores_gemma":[0.00016165,0.0004966196,0.0001967914,0.0003836777,0.00009481236,0.00002230841,0.0003078188,0.0003834884,0.000003576911],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003168445,"about_ca_system_score_gemma":0.0006841898,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0006490431,"about_ca_topic_score_gemma":0.0001351887,"domain_scores_codex":[0.9977233,0.0001344141,0.0006988345,0.0008168216,0.0002285978,0.0003980137],"domain_scores_gemma":[0.9983322,0.000034191,0.0004116498,0.0007434457,0.0003722236,0.0001063121],"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":[0.00005129429,0.0001734384,0.008120271,0.0005614843,0.00005480972,0.000004528451,0.00001407929,0.00164137,0.989317,0.00004620289,0.00001048321,0.00000502224],"study_design_scores_gemma":[0.0006749166,0.0001014034,0.01192739,0.0001936386,0.00007254338,1.17332e-8,0.000004568033,0.0007453915,0.9854183,0.00001703939,0.0003505018,0.0004943283],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9161983,0.001655502,0.08055431,0.00001775239,0.0007158212,0.0004479272,0.0003383525,0.00004642823,0.00002565898],"genre_scores_gemma":[0.9912556,0.0003421094,0.007959379,0.0001109945,0.0002175279,0.00004601333,0.000009626552,0.00005293093,0.00000578024],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.07505739,"threshold_uncertainty_score":0.9997485,"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."}}