{"id":"W2904438966","doi":"10.1101/492926","title":"An Unsupervised Learning Method for Disease Classification Based on DNA Methylation Signatures","year":2018,"lang":"en","type":"preprint","venue":"bioRxiv (Cold Spring Harbor Laboratory)","topic":"Tracheal and airway disorders","field":"Medicine","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"Hospital for Sick Children; University of Toronto","funders":"","keywords":"Cluster analysis; dNaM; Computer science; Identification (biology); Artificial intelligence; Unsupervised learning; Computational biology; DNA methylation; Disease; Machine learning; Biology; Pattern recognition (psychology); Genetics; Gene; Medicine; 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":[0.002127261,0.001011471,0.001195638,0.003996145,0.0007427552,0.001002891,0.002034484,0.001476028,0.001548077],"category_scores_gemma":[0.004475649,0.0003666775,0.001827267,0.002157189,0.0006406298,0.0007325055,0.001032409,0.001679103,0.001278485],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007759864,"about_ca_system_score_gemma":0.002022812,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004891864,"about_ca_topic_score_gemma":0.00735497,"domain_scores_codex":[0.998305,0.0003757412,0.0001567421,0.0006086134,0.0004240633,0.0001299031],"domain_scores_gemma":[0.9981142,0.0007387773,0.0002195506,0.0003291718,0.000501572,0.00009684816],"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":[0.0003048118,0.0003195508,0.01314554,0.0001643045,0.0003869514,0.0001992655,0.000179927,0.03793557,0.01308374,0.004890192,0.01113822,0.9182519],"study_design_scores_gemma":[0.00008111063,0.0001184409,0.004992709,0.00003056596,0.00008815803,0.0004862532,0.00005427862,0.9640234,0.008549069,0.01570269,0.005815135,0.00005809633],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0167548,0.0004369235,0.9773659,0.0003833593,0.000109384,0.0002331599,0.0008289982,0.002949035,0.0009384388],"genre_scores_gemma":[0.1940933,0.000300457,0.7973621,0.0003824497,0.0003268973,0.0006569701,0.002948895,0.0002525032,0.003676354],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.004891864,"threshold_uncertainty_score":0.01125014,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02561748667876556,"score_gpt":0.2902390160936705,"score_spread":0.264621529414905,"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."}}