{"id":"W4410216721","doi":"10.1093/bib/bbaf203","title":"SVHunter: long-read-based structural variation detection through the transformer model","year":2025,"lang":"en","type":"article","venue":"Briefings in Bioinformatics","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":10,"is_retracted":false,"has_abstract":true,"ca_institutions":"Science North","funders":"National Key Research and Development Program of China; National Natural Science Foundation of China; National Science Fund for Distinguished Young Scholars; National Science Foundation","keywords":"Computer science; Cluster analysis; Robustness (evolution); Convolutional neural network; Data mining; Artificial intelligence; Pattern recognition (psychology); Transformer; Machine learning; Biology","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001278931,0.0001378973,0.000111834,0.00003935666,0.0001505866,0.00004057501,0.0001616812,0.0001130598,0.000002525238],"category_scores_gemma":[0.00003842455,0.0001055712,0.00006978662,0.0001284515,0.00006965293,0.000004045753,0.00003466781,0.00008931658,0.000001594807],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002466402,"about_ca_system_score_gemma":0.00007449393,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001143552,"about_ca_topic_score_gemma":0.0002691379,"domain_scores_codex":[0.9992664,0.00001555418,0.0003131971,0.0001253301,0.00008786313,0.0001916251],"domain_scores_gemma":[0.9996116,0.00001794164,0.00007992998,0.0002207148,0.00005573898,0.00001408626],"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":[0.0009198694,0.0002125855,0.009817098,0.000986269,0.0007114181,0.000002174902,0.01587623,0.4488725,0.3465244,0.008968181,0.003812839,0.1632964],"study_design_scores_gemma":[0.002551286,0.0002254212,0.03977529,0.0000807601,0.0001032422,0.00001109649,0.0004322821,0.7995061,0.13231,0.006673436,0.01772259,0.0006084736],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5904296,0.0004010108,0.4028153,0.001257566,0.0002197955,0.0003975377,0.00002587961,0.000009067971,0.004444241],"genre_scores_gemma":[0.9911721,0.0001010275,0.005711514,0.002783947,0.00002975323,0.00002656069,0.00002492237,0.000008174085,0.0001420386],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.4007425,"threshold_uncertainty_score":0.4305069,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.008046675174853059,"score_gpt":0.2402647947131276,"score_spread":0.2322181195382746,"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."}}