{"id":"W3211479370","doi":"10.1101/2021.11.08.467820","title":"scDeepHash: An automatic cell type annotation and cell retrieval method for large-scale scRNA-seq datasets using neural network-based hashing","year":2021,"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":"Vector Institute; University of Toronto; University Health Network","funders":"","keywords":"Annotation; Scalability; Computer science; Hash function; Profiling (computer programming); Benchmarking; Treebank; Artificial intelligence; RNA-Seq; Data mining; Pattern recognition (psychology); Transcriptome; Database; Gene; Biology; Gene expression","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":[0.0009794857,0.0005622718,0.000553684,0.0001057489,0.0003279539,0.0004359378,0.0004075541,0.0007331842,0.00001024817],"category_scores_gemma":[0.000136774,0.0006564502,0.0001662531,0.0002933938,0.00006200369,0.00003596777,0.0002645527,0.0004497446,9.799578e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007304383,"about_ca_system_score_gemma":0.0005948445,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004196849,"about_ca_topic_score_gemma":0.00002164866,"domain_scores_codex":[0.9969311,0.0003278951,0.0005602186,0.001265368,0.0002535998,0.0006618522],"domain_scores_gemma":[0.9976256,0.00005491108,0.0005050935,0.001056293,0.0004679432,0.0002901577],"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":[0.0001541834,0.0002268445,0.002473665,0.0007472945,0.00005427885,0.00001495481,0.00001361327,0.009319691,0.9868525,0.000002713163,0.0001347774,0.000005503418],"study_design_scores_gemma":[0.001346906,0.0001894491,0.002852942,0.0001587321,0.0002635003,6.982902e-8,0.00001003905,0.3670502,0.6266022,8.495899e-7,0.0007854848,0.0007395752],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8868965,0.001796392,0.1085561,0.00002717645,0.00107652,0.0006844061,0.0008767699,0.00008506353,0.00000109353],"genre_scores_gemma":[0.8052068,0.00005921353,0.1933487,0.0004377488,0.0006515174,0.00002467681,0.0001219184,0.0001474068,0.000001992788],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3602502,"threshold_uncertainty_score":0.9995887,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02205135408416869,"score_gpt":0.2622009394731476,"score_spread":0.2401495853889789,"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."}}