{"id":"W2949272108","doi":"10.1038/s41467-018-04368-5","title":"Interpretable dimensionality reduction of single cell transcriptome data with deep generative models","year":2018,"lang":"en","type":"article","venue":"Nature Communications","topic":"Single-cell and spatial transcriptomics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":382,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia; BC Cancer Agency","funders":"Natural Sciences and Engineering Research Council of Canada; Terry Fox Research Institute; Canada Research Chairs; Michael Smith Health Research BC; BC Cancer Foundation; Canadian Cancer Society Research Institute; Canadian Institutes of Health Research; Genome Canada","keywords":"Dimensionality reduction; Computer science; Cluster analysis; Probabilistic logic; Generative model; Embedding; Computational biology; Single cell sequencing; Artificial intelligence; Data mining; Pattern recognition (psychology); Generative grammar; Biology; Gene; Genetics; Phenotype","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":[0.000144369,0.0001161804,0.0001267508,0.0000324336,0.0001737285,0.00001517161,0.0009670538,0.0002093783,0.000009788571],"category_scores_gemma":[0.00001850713,0.0001009573,0.00003838931,0.0001355393,0.0003515935,0.00002098931,0.0002121025,0.0002435157,0.00000123799],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001358721,"about_ca_system_score_gemma":0.00006836621,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000428674,"about_ca_topic_score_gemma":0.0005952134,"domain_scores_codex":[0.999203,0.00009832872,0.0001884558,0.0002769505,0.000111706,0.0001215348],"domain_scores_gemma":[0.9973317,0.00001557219,0.00008778152,0.002201787,0.0003195119,0.00004367955],"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":[0.0001111924,0.0003281435,0.0001024321,0.00000765929,0.00004888215,7.061237e-8,0.0002528603,0.00009229498,0.9970102,0.0005616635,0.001157805,0.0003267489],"study_design_scores_gemma":[0.0007930005,0.0006556957,0.0001896413,0.00004253246,0.0001162437,0.00001662124,0.00028631,0.01477176,0.9478675,0.0005126917,0.03442373,0.0003243287],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8370576,0.01830511,0.1180196,0.00184822,0.0006789581,0.0007323006,0.0007183791,0.00006639041,0.02257339],"genre_scores_gemma":[0.962675,0.0002520583,0.03540111,0.0001365749,0.00009139534,0.000007997779,0.001259206,0.00001716066,0.0001595224],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.1256174,"threshold_uncertainty_score":0.4116919,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04044070147336464,"score_gpt":0.2841181105598681,"score_spread":0.2436774090865035,"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."}}