{"id":"W4409712505","doi":"10.1101/2025.04.16.649101","title":"Improved CRISPR/Cas9 Off-target Prediction with DNABERT and Epigenetic Features","year":2025,"lang":"en","type":"preprint","venue":"bioRxiv (Cold Spring Harbor Laboratory)","topic":"CRISPR and Genetic Engineering","field":"Biochemistry, Genetics and Molecular Biology","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Institute of Genetics; University of Tokyo","keywords":"CRISPR; Epigenetics; Computational biology; Computer science; Cas9; Genetics; Biology; Gene","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008756913,0.001318704,0.0008032508,0.0005469887,0.0002496128,0.0006361345,0.0007971738,0.0008614772,0.001086118],"category_scores_gemma":[0.00182192,0.0002849911,0.0007943537,0.0002790922,0.0002733685,0.0006393599,0.0005235506,0.001293031,0.0005508733],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006953517,"about_ca_system_score_gemma":0.0007414038,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00888799,"about_ca_topic_score_gemma":0.01076321,"domain_scores_codex":[0.9996774,0.00007564852,0.00001498862,0.0001112336,0.00007409965,0.00004662588],"domain_scores_gemma":[0.9990776,0.0005629645,0.00007278042,0.00008335782,0.0001494419,0.00005386093],"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":[0.0004034975,0.0001554546,0.007709303,0.0001172128,0.000174009,0.0002744041,0.00004729208,0.8482827,0.04665774,0.0009863697,0.002819411,0.09237272],"study_design_scores_gemma":[0.000005063603,0.00005563171,0.0006730141,0.000003743882,0.00002015016,0.00002747922,0.00000413726,0.9862299,0.0120864,0.0005234004,0.0003584597,0.00001261536],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5024356,0.00179141,0.4730029,0.0007879026,0.0002262356,0.0001049335,0.001819406,0.01534261,0.004489041],"genre_scores_gemma":[0.9391696,0.0002408076,0.05439686,0.0002706706,0.00003354702,0.00006887118,0.001526169,0.0003454359,0.003948],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.00888799,"threshold_uncertainty_score":0.01767248,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.00402534860391135,"score_gpt":0.2235694260729754,"score_spread":0.219544077469064,"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."}}