{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0006827693,0.0004317728,0.0003118064,0.0001793893,0.0001272758,0.0002218119,0.0002902207,0.0007440419,0.000007139291],"category_scores_gemma":[0.0002425723,0.0004832675,0.0002480517,0.0001667195,0.00005462193,0.000007160145,0.0004440155,0.0003098031,0.00003130646],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001078308,"about_ca_system_score_gemma":0.0005715088,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000007073657,"about_ca_topic_score_gemma":0.000005394373,"domain_scores_codex":[0.9978052,0.00006862886,0.0004769206,0.001040005,0.0002410919,0.000368128],"domain_scores_gemma":[0.9981375,0.00002403621,0.0002772149,0.00090368,0.0005148196,0.0001426966],"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":[0.00003766657,0.00004406004,0.000134704,0.0003449807,0.0001286595,9.984748e-7,0.000007087323,0.004022228,0.9941559,0.0008836295,0.0002172506,0.0000228014],"study_design_scores_gemma":[0.0003401032,0.00009105242,0.001206322,0.0001069925,0.0001830819,1.994115e-9,8.360377e-7,0.07740281,0.911388,0.0003141222,0.008341341,0.0006253705],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7610074,0.003939829,0.2321083,0.0002120164,0.001208514,0.001074929,0.0002950892,0.000127297,0.00002662672],"genre_scores_gemma":[0.9805867,0.0005285157,0.01713562,0.00008477624,0.0009631304,0.0004631691,0.00001577345,0.0001646835,0.00005760067],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.2195793,"threshold_uncertainty_score":0.9997619,"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."}}