{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001425905,0.001004141,0.0008915072,0.0008704906,0.0004299347,0.001107862,0.002053488,0.001972944,0.004483911],"category_scores_gemma":[0.004798568,0.0006327272,0.00183105,0.001179318,0.0006460139,0.001229406,0.001169305,0.002622051,0.00154606],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001178575,"about_ca_system_score_gemma":0.001508506,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01274168,"about_ca_topic_score_gemma":0.02096293,"domain_scores_codex":[0.9996519,0.00009795896,0.00002020133,0.0001400668,0.00004608211,0.00004368446],"domain_scores_gemma":[0.9989458,0.0007287625,0.00006796682,0.0000893695,0.0001159444,0.00005213543],"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":[0.0002087913,0.00007275071,0.006742422,0.0002429058,0.0002456006,0.0001987283,0.0002753008,0.8530849,0.006882233,0.03323146,0.01459027,0.08422467],"study_design_scores_gemma":[0.00001029841,0.00001040842,0.0003169286,0.000009609019,0.00001237656,0.00002365592,0.00001126341,0.9832798,0.0005116725,0.01421398,0.001590115,0.000009897141],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.019633,0.0004484422,0.9715844,0.0004769472,0.00008750636,0.00005512571,0.00427528,0.002679479,0.0007597904],"genre_scores_gemma":[0.4652281,0.001225005,0.4900597,0.001018419,0.0003340414,0.001277615,0.02785133,0.001936207,0.01106969],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.01274168,"threshold_uncertainty_score":0.02533501,"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."}}