{"id":"W6920881994","doi":"10.6084/m9.figshare.28975055","title":"Additional file 1 of Predicting adenine base editing efficiencies in different cellular contexts by deep learning","year":2025,"lang":"en","type":"article","venue":"Figshare","topic":"CRISPR and Genetic Engineering","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Acuitas Therapeutics (Canada)","funders":"","keywords":"Deep learning; Base (topology); File format; Focus (optics); Key (lock)","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":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.001063186,0.001736447,0.001728164,0.001719853,0.0007739132,0.001840978,0.002588728,0.001346175,0.7932573],"category_scores_gemma":[0.009542051,0.0008190934,0.001056647,0.00263053,0.0003000694,0.001603648,0.001017486,0.001430174,0.2387476],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009539525,"about_ca_system_score_gemma":0.001490033,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005234403,"about_ca_topic_score_gemma":0.01157381,"domain_scores_codex":[0.99946,0.00007065636,0.0000516931,0.0001886201,0.0001514005,0.00007757308],"domain_scores_gemma":[0.9944577,0.004018981,0.0002437922,0.0004794124,0.0005950629,0.0002049788],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0002963964,0.0001023014,0.002036064,0.002773195,0.00008901991,0.00007748269,0.00003396227,0.002191879,0.0008851355,0.001032336,0.9782401,0.01224221],"study_design_scores_gemma":[0.003392687,0.0004346097,0.01931902,0.00171243,0.0003245733,0.000620687,0.000201889,0.01602159,0.008171476,0.02349109,0.9260218,0.0002882372],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"dataset","genre_gemma":"other","genre_scores_codex":[0.0001921756,0.00003234659,0.0008215618,0.00004314706,0.00002438621,0.00002239548,0.9970095,0.00129319,0.0005612964],"genre_scores_gemma":[0.005260771,0.0001318261,0.005359169,0.0002517768,0.00004455255,0.0004528831,0.9819131,0.002193261,0.004392618],"genre_candidate":"other","genre_consensus":null,"teacher_disagreement_score":0.7932573,"threshold_uncertainty_score":0.2948933,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.004653377892996529,"score_gpt":0.2302587821132444,"score_spread":0.2256054042202478,"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."}}