{"id":"W3135155916","doi":"10.1101/2021.03.08.434446","title":"Latent representation of the human pan-celltype epigenome through a deep recurrent neural network","year":2021,"lang":"en","type":"preprint","venue":"bioRxiv (Cold Spring Harbor Laboratory)","topic":"Epigenetics and DNA Methylation","field":"Biochemistry, Genetics and Molecular Biology","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"Simon Fraser University","funders":"","keywords":"Epigenomics; Epigenome; Recurrent neural network; Autoencoder; Representation (politics); Computer science; Artificial intelligence; Epigenetics; Deep learning; Artificial neural network; Variety (cybernetics); Computational biology; Biology; Machine learning; DNA methylation; Gene; Genetics; 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":[0.000221691,0.0003124126,0.0002379781,0.000360059,0.00006436231,0.0002923225,0.000464485,0.0003574517,0.0009173454],"category_scores_gemma":[0.0005772702,0.0001673486,0.0003398836,0.0003310658,0.0001839152,0.000400682,0.0003599486,0.0004557516,0.0002717678],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003520677,"about_ca_system_score_gemma":0.0002773788,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003827428,"about_ca_topic_score_gemma":0.00628169,"domain_scores_codex":[0.9999259,0.00001493552,0.000002631949,0.0000280116,0.00001502117,0.00001357777],"domain_scores_gemma":[0.999885,0.00004596867,0.000021406,0.00001632286,0.00002215118,0.000009053089],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0004029116,0.00008871298,0.006305314,0.0001129644,0.0001129093,0.0003467075,0.000112448,0.7276595,0.09233656,0.00841348,0.003252796,0.1608557],"study_design_scores_gemma":[0.000002492885,0.00001347758,0.0008849559,0.000002665045,0.000006985745,0.0000269899,0.000004338499,0.9932693,0.003878648,0.001648055,0.0002572123,0.000004930978],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2438734,0.0006018666,0.7509245,0.0004235856,0.00004579294,0.00001705659,0.001364437,0.001404148,0.001345237],"genre_scores_gemma":[0.92813,0.0002833995,0.06591398,0.0001285418,0.00002437349,0.00003233965,0.001780981,0.00007117807,0.003635195],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.003827428,"threshold_uncertainty_score":0.007610261,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02390084598951556,"score_gpt":0.2610657307915959,"score_spread":0.2371648848020803,"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."}}