{"id":"W4387251159","doi":"10.1109/cibcb56990.2023.10264893","title":"A Comparison of Machine Learning Models for Predicting CRISPR/Cas On-target Efficacy","year":2023,"lang":"en","type":"article","venue":"","topic":"CRISPR and Genetic Engineering","field":"Biochemistry, Genetics and Molecular Biology","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"Simon Fraser University","funders":"","keywords":"CRISPR; Computer science; Cas9; Artificial intelligence; Convolutional neural network; Deep learning; Machine learning; Guide RNA; Palindrome; Nuclease; Computational biology; Feature (linguistics); DNA; Biology; 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":[0.003498744,0.002538084,0.001328394,0.002113353,0.000364597,0.00104242,0.001755206,0.001788574,0.001469038],"category_scores_gemma":[0.006891954,0.0003867334,0.001294545,0.001175751,0.0003638725,0.001486102,0.000694374,0.001724242,0.0005588148],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002103503,"about_ca_system_score_gemma":0.001413375,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.02370956,"about_ca_topic_score_gemma":0.01866834,"domain_scores_codex":[0.9988528,0.0003418838,0.0001153687,0.0003077813,0.0002476776,0.0001344085],"domain_scores_gemma":[0.995331,0.003346676,0.0002117625,0.0002572357,0.0007142344,0.000139038],"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":[0.001012672,0.0005012734,0.01417821,0.0003678243,0.0004799817,0.00009608464,0.00002713425,0.8491775,0.001139623,0.0007143517,0.007365071,0.1249402],"study_design_scores_gemma":[0.00002741413,0.0001842032,0.001827096,0.00003399548,0.00005153933,0.00002094972,0.00001749757,0.9956331,0.001052,0.0005525971,0.0005832476,0.00001643416],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8165858,0.02138517,0.1269296,0.003397379,0.001035271,0.0002955192,0.0144566,0.005585725,0.01032886],"genre_scores_gemma":[0.9061267,0.003979802,0.06114589,0.0007047522,0.0002060002,0.000252671,0.0235502,0.0002639541,0.003770046],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.02370956,"threshold_uncertainty_score":0.0471431,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03296878057420358,"score_gpt":0.3615992609551353,"score_spread":0.3286304803809318,"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."}}