{"id":"W4391970295","doi":"10.1038/s41421-023-00624-1","title":"Deep learning models incorporating endogenous factors beyond DNA sequences improve the prediction accuracy of base editing outcomes","year":2024,"lang":"en","type":"article","venue":"Cell Discovery","topic":"CRISPR and Genetic Engineering","field":"Biochemistry, Genetics and Molecular Biology","cited_by":22,"is_retracted":false,"has_abstract":true,"ca_institutions":"Ministry of Agriculture","funders":"Chinese Academy of Agricultural Sciences; China Postdoctoral Science Foundation; Natural Science Foundation of Guangdong Province; National Natural Science Foundation of China","keywords":"Endogeny; Genome editing; Computational biology; DNA sequencing; DNA; Base (topology); Biology; Genome; Genomics; Base pair; genomic DNA; Computer science; Genetics; 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":[0.0001461135,0.0001527824,0.0001215479,0.00003546792,0.0001041643,0.00008968454,0.0001391171,0.00007874361,0.000004112971],"category_scores_gemma":[0.0001029018,0.0001074856,0.0001234288,0.00007792089,0.00005372383,0.00003065086,0.000101401,0.0001540404,0.000001069969],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000138077,"about_ca_system_score_gemma":0.00006143154,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003948161,"about_ca_topic_score_gemma":0.00001313036,"domain_scores_codex":[0.9991603,0.00003286795,0.0002331884,0.0002602577,0.0001334846,0.0001798591],"domain_scores_gemma":[0.9995754,0.00008990101,0.00008293288,0.0001884108,0.00002889279,0.00003443088],"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":[0.000003993616,0.00001238197,0.003849476,0.0001123274,0.00003723827,0.000002890351,0.0004159389,0.08427502,0.9100359,0.00007826723,0.00002184937,0.00115469],"study_design_scores_gemma":[0.0001079791,0.0001182864,0.0004082755,0.00003177275,0.00004709318,0.000005183465,0.001965213,0.04353708,0.9531156,0.0003635687,0.0001534685,0.000146493],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9411408,0.002174526,0.05454896,0.00002368068,0.0005952822,0.0001434729,0.00003981042,0.0000284395,0.001305081],"genre_scores_gemma":[0.9989789,0.0001308051,0.0001889122,0.00001748801,0.0002852446,0.00001399851,0.000117538,0.00002493367,0.0002422385],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.05783809,"threshold_uncertainty_score":0.4383136,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01538285298943366,"score_gpt":0.2512635982122209,"score_spread":0.2358807452227872,"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."}}