{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001730855,0.0001720835,0.0002103252,0.0001609866,0.00009335332,0.000007204369,0.0002746226,0.0001224689,0.00003842956],"category_scores_gemma":[0.00002867071,0.0001940239,0.0001014133,0.000202713,0.00006522267,0.00000456022,0.0002403969,0.00009400321,9.384395e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004909367,"about_ca_system_score_gemma":0.00004880096,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001799145,"about_ca_topic_score_gemma":0.00001051754,"domain_scores_codex":[0.9987458,0.0001066981,0.0003147265,0.000444435,0.0001068326,0.000281538],"domain_scores_gemma":[0.9993873,0.00001005059,0.0001840228,0.0003075258,0.00007269258,0.00003839693],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.00006335419,0.00008536788,0.002767141,0.00001634522,0.00005803211,0.000001211942,0.0000719422,0.0003361809,0.991901,0.0001235013,0.000004889654,0.004570992],"study_design_scores_gemma":[0.002329721,0.001265251,0.01967472,0.000003422845,0.00003211703,0.0000292395,0.0002378197,0.002367385,0.9607378,0.0004592745,0.01243197,0.0004312566],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9365355,0.0002690058,0.06121333,0.00008273902,0.0001732548,0.0007546977,0.0009399884,0.00001031526,0.00002113565],"genre_scores_gemma":[0.9838135,0.00003691716,0.005752482,0.0001235659,0.00007697014,0.0003158589,0.009774067,0.0000359756,0.00007062108],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.05546085,"threshold_uncertainty_score":0.7912066,"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."}}