{"id":"W4415524957","doi":"10.1371/journal.pcbi.1013606","title":"Similarity-based transfer learning with deep learning networks for accurate CRISPR-Cas9 off-target prediction","year":2025,"lang":"en","type":"article","venue":"PLoS Computational Biology","topic":"CRISPR and Genetic Engineering","field":"Biochemistry, Genetics and Molecular Biology","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"Mila - Quebec Artificial Intelligence Institute; Université du Québec à Montréal","funders":"Fonds de recherche du Québec – Nature et technologies; Natural Sciences and Engineering Research Council of Canada","keywords":"Transfer of learning; Deep learning; Convolutional neural network; Artificial neural network; Source code; Metric (unit); Similarity (geometry); Multilayer perceptron; Field (mathematics)","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":[0.001995553,0.001068589,0.0009052732,0.0006746041,0.0004664957,0.0007934375,0.00166441,0.001135238,0.001325526],"category_scores_gemma":[0.006824378,0.0003997335,0.0006089337,0.0006732421,0.0006340306,0.001910015,0.001417847,0.001859453,0.0003897513],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001508258,"about_ca_system_score_gemma":0.001287287,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.006252585,"about_ca_topic_score_gemma":0.005229894,"domain_scores_codex":[0.9992937,0.0001633306,0.00004659599,0.0001979992,0.0001989597,0.0000994869],"domain_scores_gemma":[0.9985049,0.0007613495,0.0001779528,0.0002013016,0.0002808817,0.00007362533],"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":[0.0001873631,0.0001807009,0.002856907,0.00007183893,0.00005447156,0.0001054434,0.00005881726,0.8838735,0.009330088,0.002689168,0.0008525704,0.0997392],"study_design_scores_gemma":[0.000003497098,0.00003437748,0.0001695123,0.000002385656,0.000003379869,0.000006877779,0.000004669413,0.9961183,0.002463586,0.001105225,0.00008362285,0.00000449864],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1915209,0.0005973887,0.8004027,0.0003819902,0.00007765806,0.0001394559,0.0002404853,0.004347074,0.002292408],"genre_scores_gemma":[0.9163814,0.0001102357,0.0818555,0.0001217631,0.00001396729,0.0001413365,0.0002821517,0.00007068304,0.001022833],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.006252585,"threshold_uncertainty_score":0.0124324,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.008433297848496543,"score_gpt":0.2886752976664759,"score_spread":0.2802419998179793,"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."}}