{"id":"W6893302055","doi":"10.5281/zenodo.16583523","title":"Dataset for \"NanoVar: a Comprehensive Workflow for Structural Variant Detection to uncover the Genome's Hidden Patterns\"","year":2025,"lang":"en","type":"dataset","venue":"Zenodo (CERN European Organization for Nuclear Research)","topic":"Genomics and Rare Diseases","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Memorial University of Newfoundland","funders":"","keywords":"Directory; Pipeline (software); Workflow; Sample (material); Annotation; Stage (stratigraphy); Filter (signal processing)","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":[0.001341292,0.002209493,0.001277731,0.001922013,0.001182189,0.001870387,0.002846547,0.00192121,0.06755894],"category_scores_gemma":[0.005077035,0.0007395392,0.001784967,0.00270214,0.000358593,0.00118494,0.002153522,0.002001383,0.06044773],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001146924,"about_ca_system_score_gemma":0.002110629,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01107792,"about_ca_topic_score_gemma":0.02218054,"domain_scores_codex":[0.9988149,0.0001485014,0.0001633419,0.0004085448,0.0002995011,0.0001652338],"domain_scores_gemma":[0.9982394,0.0005809862,0.0001682588,0.0003708442,0.0004992271,0.000141291],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0003265626,0.00004637177,0.002666733,0.001003872,0.00007466632,0.00008215223,0.00004121732,0.0006235036,0.00196946,0.0006880792,0.9875264,0.004950959],"study_design_scores_gemma":[0.001043107,0.0001084811,0.01210606,0.0004275442,0.0001122154,0.0002906204,0.000143198,0.00234444,0.004731191,0.00397459,0.9746243,0.00009421837],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"dataset","genre_gemma":"dataset","genre_scores_codex":[0.0003867996,0.00004140425,0.0003911542,0.00006539845,0.00002856739,0.00002518062,0.9972951,0.001299891,0.0004665887],"genre_scores_gemma":[0.0004726012,0.00002399653,0.0009238648,0.00006768059,0.000004969464,0.00009740681,0.9979135,0.0002060276,0.000289907],"genre_candidate":"dataset","genre_consensus":"dataset","teacher_disagreement_score":0.06755894,"threshold_uncertainty_score":0.2260072,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01815554342510738,"score_gpt":0.2566867669564853,"score_spread":0.2385312235313779,"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."}}