{"id":"W4405910570","doi":"10.1093/bioadv/vbae184","title":"Predicting CRISPR-Cas9 off-target effects in human primary cells using bidirectional LSTM with BERT embedding","year":2024,"lang":"en","type":"article","venue":"Bioinformatics Advances","topic":"CRISPR and Genetic Engineering","field":"Biochemistry, Genetics and Molecular Biology","cited_by":9,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Ottawa; National Research Council Canada; McGill University","funders":"National Research Council Canada","keywords":"CRISPR; Embedding; Primary (astronomy); Computer science; Computational biology; Biology; Artificial intelligence; Genetics; Gene; Physics","routes":{"ca_aff":true,"ca_fund":true,"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":[0.0001497918,0.0001887293,0.0001590323,0.000126738,0.0000896742,0.0000679433,0.0001035752,0.00008477353,0.000005201399],"category_scores_gemma":[0.0000182325,0.0001659921,0.00005450226,0.0001752078,0.00003960133,0.00003495581,0.00006817904,0.0001263538,0.000002844834],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004208161,"about_ca_system_score_gemma":0.00006092187,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000008518764,"about_ca_topic_score_gemma":0.00001836339,"domain_scores_codex":[0.9990521,0.00001276646,0.0002874671,0.0002017425,0.0001695894,0.000276344],"domain_scores_gemma":[0.9996699,0.00003215879,0.00005353951,0.0001554538,0.0000293112,0.0000596441],"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":[0.00005055763,0.00006357628,0.007573706,0.002587584,0.0001410722,0.00003208904,0.0006760165,0.2601697,0.7004493,0.00009060244,0.0003638718,0.02780189],"study_design_scores_gemma":[0.0006927984,0.000448217,0.001614312,0.0008506181,0.00005302465,0.0001025119,0.0003640699,0.4145714,0.5429031,0.00008029793,0.03765237,0.0006673271],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8568426,0.01383226,0.1248222,0.00001224474,0.0006627049,0.0002732283,0.00002293106,0.00008520202,0.003446573],"genre_scores_gemma":[0.9284951,0.0004301344,0.07025481,0.00006840391,0.0003490994,0.00002748426,0.00009339159,0.00004569472,0.000235869],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.1575463,"threshold_uncertainty_score":0.6768962,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.004768933118316525,"score_gpt":0.2879238221660577,"score_spread":0.2831548890477412,"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."}}