{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001142713,0.001152043,0.001011502,0.0006801173,0.0002763104,0.0009914596,0.001004561,0.001185846,0.001256812],"category_scores_gemma":[0.00258537,0.0003668372,0.0008736902,0.0004542618,0.0003457934,0.0008414693,0.0006509136,0.002106412,0.0004143173],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007585338,"about_ca_system_score_gemma":0.001185843,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.006913726,"about_ca_topic_score_gemma":0.008844007,"domain_scores_codex":[0.9997095,0.00006272869,0.00001934771,0.0001140857,0.00004114036,0.00005317159],"domain_scores_gemma":[0.9990805,0.0006143842,0.000073931,0.00005470912,0.0001242373,0.00005217649],"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":[0.0003195868,0.0003428758,0.01278343,0.000127101,0.0001833538,0.0001196493,0.00003711834,0.8456621,0.006146322,0.001614582,0.003322768,0.129341],"study_design_scores_gemma":[0.000006313869,0.00002043564,0.0002910989,0.000004892384,0.00001207283,0.000006916674,0.000002973103,0.9978387,0.0008200707,0.00078258,0.0002101387,0.000003760567],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4473805,0.003546063,0.5376178,0.001184026,0.0002321635,0.000125488,0.001721165,0.003709005,0.00448373],"genre_scores_gemma":[0.9126372,0.0008675784,0.07892343,0.000596215,0.00008171421,0.0001354917,0.003122703,0.0001400039,0.003495639],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.006913726,"threshold_uncertainty_score":0.01374698,"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."}}