{"id":"W4410212252","doi":"10.1186/s13059-025-03586-7","title":"Predicting adenine base editing efficiencies in different cellular contexts by deep learning","year":2025,"lang":"en","type":"article","venue":"Genome biology","topic":"CRISPR and Genetic Engineering","field":"Biochemistry, Genetics and Molecular Biology","cited_by":4,"is_retracted":false,"has_abstract":true,"ca_institutions":"Acuitas Therapeutics (Canada)","funders":"National Institute of Allergy and Infectious Diseases; Functional Genomics Center Zurich; Schweizerischer Nationalfonds zur Förderung der Wissenschaftlichen Forschung; Staatssekretariat für Bildung, Forschung und Innovation; Université de Genève; National Institutes of Health; National Science Foundation","keywords":"Biology; Genome editing; Computational biology; Guide RNA; In vivo; Base (topology); RNA editing; CRISPR; Computer science; Genetics; Messenger RNA; Gene","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":[],"consensus_categories":[],"category_scores_codex":[0.0001726544,0.0001697053,0.000193556,0.00008852954,0.00007775504,0.00001221587,0.0001646681,0.0001722277,0.00001982742],"category_scores_gemma":[0.0002189274,0.000158201,0.00005667323,0.0001071958,0.00006224572,0.000001387132,0.0001609161,0.0001712233,0.00000313899],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002324477,"about_ca_system_score_gemma":0.00001691968,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002102222,"about_ca_topic_score_gemma":0.00003457461,"domain_scores_codex":[0.9989063,0.00006997187,0.0002495899,0.0003678197,0.00004187799,0.0003644439],"domain_scores_gemma":[0.9996691,0.00003371371,0.00004845911,0.0001673872,0.00003342595,0.00004789799],"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":[0.00001423572,0.00002420069,0.06391327,0.00002037453,0.00002076643,0.00000184445,0.00007770298,0.001489471,0.9323579,0.00002058404,0.00005420521,0.002005421],"study_design_scores_gemma":[0.001550568,0.0005090235,0.0373562,0.00004717735,0.00002998956,0.000006818769,0.0007510622,0.005271993,0.9104308,0.00004622495,0.04352766,0.000472474],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9542354,0.009399654,0.03536955,0.00007325277,0.0003465516,0.0001290727,0.00001002353,0.00002449679,0.000411956],"genre_scores_gemma":[0.9987668,0.0001020556,0.0001236775,0.0001060293,0.0003132454,0.00002470407,0.0001741295,0.00001309489,0.0003762238],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.0445314,"threshold_uncertainty_score":0.6451248,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.003540530828262324,"score_gpt":0.256867700341476,"score_spread":0.2533271695132137,"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."}}