{"id":"W2810570362","doi":"10.1093/bioinformatics/bty586","title":"Fast characterization of segmental duplications in genome assemblies","year":2018,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Genome Rearrangement Algorithms","field":"Biochemistry, Genetics and Molecular Biology","cited_by":107,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia","funders":"National Institute of General Medical Sciences; National Institutes of Health","keywords":"Genome; Structural variation; Computer science; Sequence assembly; Computational biology; Segmental duplication; Gene duplication; Jaccard index; Biology; Genetics; Artificial intelligence; Pattern recognition (psychology); Gene","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00008201881,0.00006927014,0.00007426847,0.00007391736,0.00002672506,0.0000112649,0.0001122734,0.00005634182,0.00002449434],"category_scores_gemma":[0.00001133513,0.0000692621,0.00002480814,0.0001233106,0.00005911059,0.000008758772,0.00006690378,0.00002236286,0.00004173902],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001254922,"about_ca_system_score_gemma":0.00002699686,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000002163538,"about_ca_topic_score_gemma":0.00000734173,"domain_scores_codex":[0.9994848,0.000007519399,0.0002431959,0.00007001346,0.00008050336,0.0001139901],"domain_scores_gemma":[0.9996065,0.00000166911,0.0001054848,0.000194578,0.00006646597,0.00002529766],"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":[0.000006338793,0.00003645349,0.00259049,0.00002551621,0.00001249057,5.849035e-8,0.0004334335,0.000003741038,0.9945099,0.00003889292,0.00003136827,0.002311338],"study_design_scores_gemma":[0.001103583,0.0006223602,0.2945741,0.00003141913,0.00002135582,0.00001120336,0.001081502,0.005281434,0.6738744,0.00002727487,0.02296554,0.0004058388],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9865226,0.00001710109,0.01050416,0.00003487167,0.00005716723,0.0001890217,0.00004943208,0.000006652791,0.002618957],"genre_scores_gemma":[0.9916752,0.00007475698,0.007141993,0.00006384437,0.000101604,0.00001451725,0.0006480937,0.000008765996,0.0002712565],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3206355,"threshold_uncertainty_score":0.2824427,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0101539284658066,"score_gpt":0.2367411480797236,"score_spread":0.226587219613917,"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."}}