{"id":"W4221035067","doi":"10.1186/s13015-022-00210-2","title":"Fast characterization of segmental duplication structure in multiple genome assemblies","year":2022,"lang":"en","type":"article","venue":"Algorithms for Molecular Biology","topic":"Genome Rearrangement Algorithms","field":"Biochemistry, Genetics and Molecular Biology","cited_by":87,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia; University of Victoria","funders":"Natural Sciences and Engineering Research Council of Canada; Canada Research Chairs; Michael Smith Health Research BC; Canada Foundation for Innovation","keywords":"Computer science; Gene duplication; Characterization (materials science); Genome; Segmental duplication; Computational biology; Data mining; Biology; Genetics; Gene; Materials science","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":[],"consensus_categories":[],"category_scores_codex":[0.002532151,0.001482392,0.001317746,0.003022879,0.0008474051,0.001610484,0.001958349,0.001127319,0.00545088],"category_scores_gemma":[0.007659573,0.001164875,0.001477607,0.002163278,0.0005716215,0.002241904,0.001852942,0.001769872,0.005188741],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008964292,"about_ca_system_score_gemma":0.00122229,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002107976,"about_ca_topic_score_gemma":0.003406252,"domain_scores_codex":[0.9985738,0.0001963169,0.0000922555,0.0004456552,0.0005972664,0.00009472219],"domain_scores_gemma":[0.9955669,0.001721748,0.0007087506,0.0006243394,0.001127456,0.000250774],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00153031,0.0002779001,0.03333368,0.003247744,0.0007437532,0.001390962,0.0009046897,0.08128259,0.3606984,0.01859942,0.04646022,0.4515303],"study_design_scores_gemma":[0.0001506038,0.0003576107,0.01796944,0.0002477287,0.0002831017,0.00122339,0.0003071492,0.631837,0.2650408,0.02381384,0.05853512,0.0002342053],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0848865,0.001996086,0.8221675,0.0006283722,0.0002685724,0.0002456201,0.009524686,0.0749602,0.005322477],"genre_scores_gemma":[0.1380048,0.0006543643,0.8373684,0.0002915095,0.00007928527,0.0001861514,0.01655626,0.004581806,0.002277274],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.00545088,"threshold_uncertainty_score":0.01823497,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01047950850782903,"score_gpt":0.2527592989903266,"score_spread":0.2422797904824976,"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."}}