{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002202792,0.001140271,0.001093027,0.001592636,0.0004803826,0.001356679,0.002172722,0.001167194,0.003241579],"category_scores_gemma":[0.005937967,0.0005923141,0.001360114,0.001176632,0.0008094959,0.001937987,0.001555595,0.001622593,0.001551962],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009657937,"about_ca_system_score_gemma":0.001543196,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005610228,"about_ca_topic_score_gemma":0.008560981,"domain_scores_codex":[0.9990153,0.0002457817,0.00004634156,0.000348313,0.0002534183,0.00009078353],"domain_scores_gemma":[0.9982686,0.001065078,0.0001483868,0.0002330763,0.0001915087,0.00009332523],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.001418079,0.0003019618,0.01644711,0.0005137714,0.0006401493,0.0008098322,0.0003540041,0.3435957,0.04848,0.03824924,0.01570857,0.5334815],"study_design_scores_gemma":[0.00002045915,0.00005604607,0.0005516569,0.000009699314,0.00002264835,0.0001224013,0.0000126852,0.9816349,0.005115895,0.01100892,0.001422463,0.00002219208],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01710142,0.0003784802,0.9721299,0.0002024296,0.00006962354,0.00008299782,0.0006512118,0.008325918,0.001058074],"genre_scores_gemma":[0.4425938,0.0007751146,0.5445883,0.0006167424,0.0001063352,0.0004144605,0.003690437,0.001401036,0.005813845],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.005610228,"threshold_uncertainty_score":0.01164961,"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."}}