{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002175821,0.0001227391,0.0001030336,0.0000575456,0.0002465156,0.00002258707,0.000371781,0.0002033257,0.000003121634],"category_scores_gemma":[0.00003835334,0.0001163799,0.00003948094,0.0002286028,0.00004409036,0.000005114437,0.0001735178,0.0004283067,0.000002400132],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001551389,"about_ca_system_score_gemma":0.00004650697,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001184271,"about_ca_topic_score_gemma":0.001030086,"domain_scores_codex":[0.9992743,0.00007783761,0.0001583645,0.0002148086,0.00009695838,0.0001777161],"domain_scores_gemma":[0.9988331,0.00001786201,0.00002491828,0.001005179,0.0000629862,0.00005597001],"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":[0.00002285357,0.000034959,0.001461696,0.00001786706,0.00005648163,7.594292e-7,0.00007111499,0.6383947,0.358746,0.0003421631,0.0005875797,0.0002637883],"study_design_scores_gemma":[0.00107112,0.0001307518,0.004713917,0.00004213826,0.0001240921,0.0000337281,0.0001010965,0.8582319,0.07210881,0.00006569487,0.0629018,0.0004749609],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8543335,0.003280667,0.1405801,0.0004144577,0.00007801064,0.0002232359,0.0007690818,0.0001209215,0.0001999605],"genre_scores_gemma":[0.9674008,0.0008946165,0.02422407,0.00009404794,0.00005141237,0.00002427974,0.007088289,0.00002923074,0.0001932869],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.2866372,"threshold_uncertainty_score":0.4745834,"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."}}