{"id":"W7114904848","doi":"10.5281/zenodo.17900952","title":"crisprHAL — Better data for better predictions: data curation improves deep learning for sgRNA/Cas9 prediction","year":2025,"lang":"","type":"article","venue":"Zenodo (CERN European Organization for Nuclear Research)","topic":"RNA regulation and disease","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Western University","funders":"","keywords":"Deep learning; Data curation; Training set; Data modeling; Missing data","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":[0.01061432,0.002326749,0.002047575,0.004295739,0.001386251,0.00335342,0.002675168,0.00303238,0.01125938],"category_scores_gemma":[0.038994,0.001198208,0.001981577,0.002617441,0.0009915535,0.004612382,0.004157811,0.004601248,0.007898868],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001398305,"about_ca_system_score_gemma":0.004452396,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.007004711,"about_ca_topic_score_gemma":0.01316463,"domain_scores_codex":[0.9905933,0.002320108,0.001072693,0.002789849,0.002752271,0.0004718163],"domain_scores_gemma":[0.9647344,0.01372716,0.001603678,0.01166898,0.007269661,0.0009960372],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00241693,0.001530862,0.03646708,0.004732078,0.001901937,0.000737599,0.0004292942,0.0327185,0.1230224,0.007322021,0.440234,0.3484873],"study_design_scores_gemma":[0.001261024,0.0006530544,0.0181408,0.0009087069,0.001030911,0.000763633,0.0003002717,0.3897631,0.2812256,0.03619543,0.2691722,0.0005853863],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.1400235,0.005484564,0.4063032,0.01342548,0.002326029,0.0008985755,0.2785929,0.1419727,0.01097304],"genre_scores_gemma":[0.210739,0.001394613,0.4084269,0.003781183,0.0003382325,0.001062421,0.3570589,0.01127175,0.005927041],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.01125938,"threshold_uncertainty_score":0.05613458,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03732011026066585,"score_gpt":0.2887285183086397,"score_spread":0.2514084080479738,"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."}}