{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001164967,0.0008713789,0.001011854,0.001696641,0.0006271988,0.001248153,0.00172336,0.0008774975,0.004812586],"category_scores_gemma":[0.002893403,0.000434773,0.0007997307,0.001294366,0.0004706249,0.001426423,0.002220781,0.001066244,0.003235872],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007856027,"about_ca_system_score_gemma":0.001340298,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003371083,"about_ca_topic_score_gemma":0.00536568,"domain_scores_codex":[0.9992192,0.00008421684,0.00005735132,0.0002578358,0.0003114166,0.00007013728],"domain_scores_gemma":[0.9989662,0.000266517,0.00008976614,0.0003428346,0.0002512299,0.00008338589],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000804648,0.0001903253,0.007179441,0.0006362983,0.0002969695,0.0003047364,0.0002896288,0.04097348,0.1711866,0.004678073,0.05433352,0.7191263],"study_design_scores_gemma":[0.0001261174,0.0001805053,0.005388617,0.00002971972,0.00004990345,0.0003735173,0.0001859817,0.8663551,0.08879895,0.01348519,0.02491155,0.0001148947],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.03500636,0.0008962921,0.9222842,0.0002509329,0.0002991944,0.0003462679,0.005941174,0.03349821,0.001477281],"genre_scores_gemma":[0.1705678,0.0003555454,0.8007555,0.0003506397,0.0001458051,0.0005748115,0.01885853,0.001423565,0.006967827],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.004812586,"threshold_uncertainty_score":0.01609975,"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."}}