{"id":"W4392853205","doi":"10.7717/peerj.17101","title":"The impact of FASTQ and alignment read order on structural variant calling from long-read sequencing data","year":2024,"lang":"en","type":"article","venue":"PeerJ","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Calgary","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Sensitivity (control systems); Computational biology; Data mining; DNA sequencing; Biology; Genetics; DNA","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001324888,0.0001116323,0.0001035899,0.00001063951,0.00008204163,0.00004537766,0.0001819086,0.00004523619,0.00001181265],"category_scores_gemma":[0.00004738247,0.00006801329,0.00003772798,0.00003203267,0.00005539678,8.364784e-7,0.0002354243,0.00005247552,0.000001432259],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001746984,"about_ca_system_score_gemma":0.00006954208,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001274285,"about_ca_topic_score_gemma":0.0001918894,"domain_scores_codex":[0.9993337,0.00002257822,0.0001314415,0.0002872338,0.00008154417,0.0001434577],"domain_scores_gemma":[0.9994322,0.00004798602,0.00003296761,0.0004188662,0.00003370334,0.00003428611],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","study_design_scores_codex":[0.00009633033,0.00001212191,0.00724499,0.00002817935,0.001006876,0.00002193807,0.0005811231,0.001620063,0.9573727,0.0002766421,0.001540243,0.03019878],"study_design_scores_gemma":[0.002934493,0.003466182,0.6019911,0.0005515146,0.0009004329,0.0002629118,0.002351448,0.09748574,0.2309464,0.01092055,0.04574348,0.002445816],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9911684,0.007447334,0.0003533337,0.0001747749,0.0001674418,0.00008142271,0.0003789687,0.000002598632,0.0002257297],"genre_scores_gemma":[0.9983032,0.0007716119,0.0004011068,0.00002225013,0.0001816894,0.000002793894,0.0001470647,0.00001210507,0.0001582019],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.7264264,"threshold_uncertainty_score":0.2773501,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03191575059749882,"score_gpt":0.3077561699573567,"score_spread":0.2758404193598578,"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."}}