{"id":"W4399780516","doi":"10.1038/s41598-024-65053-w","title":"NNICE: a deep quantile neural network algorithm for expression deconvolution","year":2024,"lang":"en","type":"article","venue":"Scientific Reports","topic":"Single-cell and spatial transcriptomics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":4,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Winnipeg; Western University; University of Manitoba","funders":"Natural Sciences and Engineering Research Council of Canada; Canada Research Chairs; CancerCare Manitoba Foundation; University of Winnipeg","keywords":"Deconvolution; Computer science; Estimator; Artificial intelligence; Inference; Quantile; Ground truth; Deep learning; Pattern recognition (psychology); Quantile regression; Statistic; Algorithm; Pearson product-moment correlation coefficient; Data mining; Machine learning; Computational biology; Statistics; Mathematics; Biology","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":[0.0005527292,0.000122273,0.0001042417,0.00004158235,0.0002517681,0.0002336429,0.00009205179,0.0001199378,0.00001967759],"category_scores_gemma":[0.00003335925,0.0001083475,0.0001568867,0.0001489192,0.00009502537,0.00001013922,0.00004113285,0.00006392822,0.000005606312],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001364707,"about_ca_system_score_gemma":0.00008731457,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000006984767,"about_ca_topic_score_gemma":0.00001862442,"domain_scores_codex":[0.9985618,0.00002307565,0.0002824728,0.0006819892,0.0001516987,0.0002989616],"domain_scores_gemma":[0.9993624,0.00001199779,0.00006437474,0.0003971221,0.00008514576,0.00007895522],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00001712201,0.00003821742,0.0003568792,0.00004176149,0.0000196782,0.0000465431,0.00006269104,0.0008247895,0.9114075,0.0000199246,0.04217474,0.04499014],"study_design_scores_gemma":[0.0002022092,0.0001499332,0.000103221,0.00006488631,0.00003512251,0.0002161531,0.00003012926,0.1444427,0.4176997,0.002890381,0.433835,0.0003305356],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.686285,0.008276805,0.2743149,0.00006841388,0.03007235,0.0005445659,0.00001433073,0.000103681,0.0003199481],"genre_scores_gemma":[0.9848291,0.00002219211,0.01029625,0.00004752224,0.0009443788,0.00005561507,0.0005844851,0.00003090733,0.003189581],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.4937078,"threshold_uncertainty_score":0.4418281,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01379792541591171,"score_gpt":0.2590949066529448,"score_spread":0.2452969812370331,"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."}}