{"id":"W4361199835","doi":"10.1101/2023.03.27.534439","title":"The impact of FASTQ and alignment read order on structural variation calling from long-read sequencing data","year":2023,"lang":"en","type":"preprint","venue":"bioRxiv (Cold Spring Harbor Laboratory)","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Calgary","funders":"Natural Sciences and Engineering Research Council of Canada; University of Calgary","keywords":"Order (exchange); Structural variation; Computer science; Variation (astronomy); DNA sequencing; Benchmarking; Biology; Ambiguity; Computational biology; Genetics; DNA; Genome; Gene","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0266228,0.0008890337,0.0008292324,0.00124602,0.00114221,0.002781234,0.001198624,0.001120419,0.001660765],"category_scores_gemma":[0.1012968,0.0007770542,0.001220733,0.001398787,0.000911402,0.002032429,0.001280502,0.001884452,0.000987067],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001056974,"about_ca_system_score_gemma":0.001634871,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003774741,"about_ca_topic_score_gemma":0.006864285,"domain_scores_codex":[0.9688271,0.01676568,0.002932248,0.004438254,0.005948477,0.001088196],"domain_scores_gemma":[0.8671572,0.103697,0.005617187,0.01113014,0.01144106,0.0009575462],"domain_codex":null,"domain_gemma":"methods","domain_candidate":"methods","domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.005067613,0.0009124242,0.235327,0.001958577,0.001519112,0.0005937093,0.002589703,0.06184528,0.4762741,0.002299104,0.003842503,0.2077709],"study_design_scores_gemma":[0.0001512116,0.001785576,0.1676393,0.0003894966,0.0007198869,0.0007814269,0.0005609627,0.2186962,0.5984254,0.00252796,0.007887064,0.0004354625],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8786319,0.001376031,0.1123648,0.0004338423,0.0001935407,0.0002886032,0.002028585,0.003102311,0.001580484],"genre_scores_gemma":[0.8874062,0.0003776964,0.1053892,0.0004134152,0.0000426776,0.0002422298,0.003938434,0.001519262,0.0006708493],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9733772,"threshold_uncertainty_score":0.1407965,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03339902256493189,"score_gpt":0.2668099656793789,"score_spread":0.233410943114447,"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."}}