{"id":"W4388620502","doi":"10.1101/2023.11.09.566403","title":"GFETM: Genome Foundation-based Embedded Topic Model for scATAC-seq Modeling","year":2023,"lang":"en","type":"preprint","venue":"bioRxiv (Cold Spring Harbor Laboratory)","topic":"Single-cell and spatial transcriptomics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"Mila - Quebec Artificial Intelligence Institute; McGill University","funders":"","keywords":"Computational biology; Chromatin; Generalizability theory; Computer science; Inference; Genome; Biology; Artificial intelligence; Genetics; DNA; Gene; Mathematics","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":[0.0004401489,0.0005761574,0.0004857869,0.0001839119,0.0002365943,0.0002007451,0.0006905627,0.000784261,0.000008517757],"category_scores_gemma":[0.0001705977,0.0006718076,0.0003472838,0.0001772599,0.00007731612,0.0000107861,0.0002481066,0.0003653946,0.0000259913],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001273531,"about_ca_system_score_gemma":0.001045122,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004388029,"about_ca_topic_score_gemma":0.00001922826,"domain_scores_codex":[0.9971962,0.00005532233,0.000597898,0.001267403,0.0002645089,0.0006186618],"domain_scores_gemma":[0.9976084,0.00002676017,0.0002377366,0.001339154,0.0005694352,0.0002185317],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00008625755,0.00009168261,0.0003473159,0.000369247,0.0001308671,0.000002810372,0.000007203476,0.2234004,0.7753822,0.00008175083,0.00009826924,0.000001920517],"study_design_scores_gemma":[0.000914826,0.00007481148,0.0003399058,0.0001061309,0.0001224384,5.082187e-9,0.000001868364,0.8225506,0.1742086,0.00001905605,0.0008373939,0.0008243863],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.513372,0.0003141747,0.4841386,0.0001337391,0.0007512472,0.0008008315,0.0003063086,0.0001792077,0.000003860492],"genre_scores_gemma":[0.977821,0.0001557204,0.01992485,0.0003591821,0.0008903861,0.0004925622,0.0000384757,0.0002481026,0.00006972241],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.6011736,"threshold_uncertainty_score":0.9995733,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03973624895910505,"score_gpt":0.2474649931426325,"score_spread":0.2077287441835275,"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."}}