{"id":"W4280619597","doi":"10.1101/2022.05.13.491858","title":"More accurate estimation of cell composition in bulk expression through robust integration of single-cell information","year":2022,"lang":"en","type":"preprint","venue":"bioRxiv (Cold Spring Harbor Laboratory)","topic":"Single-cell and spatial transcriptomics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Ottawa; Health Canada","funders":"Health Canada","keywords":"Covariance; Collinearity; Univariate; Computer science; RNA-Seq; Expression (computer science); Computational biology; Data mining; Analysis of covariance; Biological system; Gene expression; Algorithm; Mathematics; Gene; Transcriptome; Biology; Multivariate statistics; Statistics; Machine learning; 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":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0002924541,0.0003344323,0.0003865992,0.00020017,0.00006830419,0.00005048201,0.000337591,0.0004529552,0.00001942695],"category_scores_gemma":[0.00005850782,0.0003741556,0.0001339829,0.0002693332,0.00008079738,0.00006464501,0.000240996,0.0003693813,0.000001757845],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001202313,"about_ca_system_score_gemma":0.0002258497,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00009703635,"about_ca_topic_score_gemma":0.000002616419,"domain_scores_codex":[0.9981008,0.0001335977,0.0008297333,0.0004082209,0.000306619,0.0002210345],"domain_scores_gemma":[0.9981022,0.00002019764,0.0008647403,0.0006128169,0.0003467443,0.00005322812],"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":[0.0001587562,0.0003618686,0.0005814508,0.0006122007,0.00001379547,0.000001155039,0.00009417505,0.05277931,0.9453275,0.00001969908,0.00004521592,0.000004840011],"study_design_scores_gemma":[0.0007570405,0.0001900924,0.002919292,0.0002803022,0.00003907931,1.122156e-8,0.00002667971,0.006387161,0.988883,0.000001450675,0.0001823176,0.0003335825],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9402655,0.0002547618,0.05814438,0.00002461342,0.0004375408,0.0005535518,0.0002502175,0.00003085764,0.00003860366],"genre_scores_gemma":[0.982492,0.0001845692,0.01702145,0.00005283753,0.00006128984,0.00007708385,0.000065488,0.00004332383,0.000001968622],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.04639215,"threshold_uncertainty_score":0.999871,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01809209736436533,"score_gpt":0.2236513184758412,"score_spread":0.2055592211114758,"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."}}