{"id":"W4386499154","doi":"10.1038/s41467-023-41143-7","title":"A generalizable Cas9/sgRNA prediction model using machine transfer learning with small high-quality datasets","year":2023,"lang":"en","type":"article","venue":"Nature Communications","topic":"CRISPR and Genetic Engineering","field":"Biochemistry, Genetics and Molecular Biology","cited_by":29,"is_retracted":false,"has_abstract":true,"ca_institutions":"Western University","funders":"Canadian Institutes of Health Research; Mitacs; Government of Canada","keywords":"Cas9; CRISPR; Computer science; Nuclease; Genome editing; Genome engineering; Guide RNA; Computational biology; Artificial intelligence; Machine learning; Biology; DNA; Genetics","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002178934,0.001291649,0.0008147691,0.0006364926,0.0003781942,0.0007539964,0.001681914,0.001351714,0.001284653],"category_scores_gemma":[0.00455694,0.0003978812,0.0009012715,0.0006014881,0.0004463373,0.001163093,0.0008889396,0.002199816,0.00076463],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009090205,"about_ca_system_score_gemma":0.000984951,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.006986198,"about_ca_topic_score_gemma":0.00741831,"domain_scores_codex":[0.9993708,0.0001804019,0.00003569195,0.0002751108,0.0000888135,0.00004926649],"domain_scores_gemma":[0.998435,0.0008008698,0.0001185454,0.0002412516,0.0003319377,0.00007242566],"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":[0.0002993898,0.0003728656,0.008420927,0.0001049891,0.0001968626,0.0001506003,0.00003414961,0.8680692,0.007627178,0.001000859,0.003995424,0.1097276],"study_design_scores_gemma":[0.000008397275,0.00004000207,0.0003483995,0.000002605996,0.00000719734,0.000009622044,0.000003041016,0.9973455,0.001391882,0.0006472071,0.0001909229,0.000005227545],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.3295423,0.00101313,0.6527744,0.001388341,0.0001660851,0.000309089,0.003228021,0.008444978,0.003133651],"genre_scores_gemma":[0.8213204,0.0003001427,0.165485,0.0005158279,0.00006348917,0.0004047872,0.007895646,0.0001836174,0.003831099],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.006986198,"threshold_uncertainty_score":0.0138911,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03431413720950719,"score_gpt":0.3448775609917875,"score_spread":0.3105634237822802,"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."}}