{"id":"W4403862062","doi":"10.1101/2024.10.24.619766","title":"CpGPT: a Foundation Model for DNA Methylation","year":2024,"lang":"en","type":"preprint","venue":"bioRxiv (Cold Spring Harbor Laboratory)","topic":"Epigenetics and DNA Methylation","field":"Biochemistry, Genetics and Molecular Biology","cited_by":29,"is_retracted":false,"has_abstract":true,"ca_institutions":"Vector Institute; Toronto Rehabilitation Institute; University Health Network","funders":"","keywords":"Foundation (evidence); DNA methylation; Computational biology; DNA; Biology; Genetics; Computer science; History; Gene; Archaeology; 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":[0.0007385714,0.0009553177,0.0007141498,0.0006182327,0.0003276602,0.0006473384,0.001958628,0.001074964,0.003722377],"category_scores_gemma":[0.003246433,0.0005337636,0.00131098,0.0005346218,0.0005645967,0.001030213,0.00106709,0.002056147,0.001160882],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001025366,"about_ca_system_score_gemma":0.001629437,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01570292,"about_ca_topic_score_gemma":0.01920516,"domain_scores_codex":[0.9997459,0.00006281544,0.00001188088,0.0000900454,0.00004826512,0.00004105316],"domain_scores_gemma":[0.9993715,0.0002964944,0.00004654498,0.00008755763,0.0001501922,0.00004763686],"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":[0.0001900564,0.00006703906,0.003727454,0.0000831463,0.0001173043,0.0001216326,0.00004251001,0.9151365,0.002971189,0.005758552,0.009476134,0.06230852],"study_design_scores_gemma":[0.000007350594,0.00001420997,0.0001317327,0.000005055026,0.000006161245,0.00001639236,0.00000242279,0.9962752,0.0004720195,0.002673435,0.000392094,0.000003999834],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.1234361,0.001034265,0.854003,0.001310662,0.0002389199,0.0001610513,0.005807485,0.008244294,0.005764212],"genre_scores_gemma":[0.8298842,0.0005680308,0.1477556,0.0008626084,0.0001099341,0.0004029542,0.01064233,0.0006958806,0.009078526],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.01570292,"threshold_uncertainty_score":0.03122306,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0205328778621368,"score_gpt":0.2612348686515148,"score_spread":0.240701990789378,"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."}}