{"id":"W2950983802","doi":"10.1093/bioinformatics/btz095","title":"Dhaka: variational autoencoder for unmasking tumor heterogeneity from single cell genomic data","year":2019,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Single-cell and spatial transcriptomics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":61,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia; BC Cancer Agency","funders":"National Institute of General Medical Sciences; National Institutes of Health; Microsoft Research","keywords":"Autoencoder; Computer science; Computational biology; Dimensionality reduction; Feature (linguistics); Single cell sequencing; Biology; Genomics; Gene; Artificial intelligence; Mutation; Genetics; Genome; Exome sequencing; Deep learning","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":[],"consensus_categories":[],"category_scores_codex":[0.000164377,0.0001745215,0.0001695807,0.00002970876,0.00008151216,0.00007239429,0.0005002823,0.0001266993,0.00003690139],"category_scores_gemma":[0.00003373998,0.0001704347,0.00008448521,0.00004034946,0.00002842489,0.00002265504,0.0002046695,0.00006625283,0.00007090598],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002724395,"about_ca_system_score_gemma":0.000120619,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002738879,"about_ca_topic_score_gemma":0.0000305328,"domain_scores_codex":[0.9989523,0.00001538387,0.0003665884,0.0002756408,0.0001345001,0.0002555977],"domain_scores_gemma":[0.9989378,0.0000335717,0.0001605281,0.0007318521,0.00006577445,0.00007047863],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0002220601,0.0003219956,0.01133481,0.0002518767,0.000176848,8.820409e-7,0.0003436015,0.002969598,0.9764178,0.00009394972,0.005013894,0.002852667],"study_design_scores_gemma":[0.002952031,0.0004498881,0.00275021,0.00003290902,0.00009897772,0.000008826059,0.0001579319,0.664998,0.1910941,0.0001474645,0.1365757,0.0007340554],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7615729,0.0001962051,0.2343276,0.00004152693,0.0007636938,0.0004557175,0.001331567,0.00002857265,0.001282192],"genre_scores_gemma":[0.7714778,0.00002326,0.2204425,0.0009153823,0.0004586668,0.00001247496,0.006365642,0.00004285729,0.0002614135],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.7853237,"threshold_uncertainty_score":0.6950126,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03147508797227019,"score_gpt":0.2393536263880751,"score_spread":0.2078785384158049,"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."}}