{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002136112,0.001103572,0.0008439557,0.003321964,0.0006933698,0.001416053,0.001112029,0.0007670383,0.002324264],"category_scores_gemma":[0.007840788,0.0004319735,0.0008110799,0.001836728,0.0003808247,0.001581015,0.001077682,0.0008989482,0.001527762],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005919633,"about_ca_system_score_gemma":0.0008254691,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002793447,"about_ca_topic_score_gemma":0.003870036,"domain_scores_codex":[0.9984819,0.0002176558,0.0001109397,0.0004223459,0.0006397035,0.0001275336],"domain_scores_gemma":[0.9959656,0.001396822,0.0005739781,0.0004895352,0.001375117,0.0001989798],"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":[0.0008850893,0.0002037961,0.05178427,0.001347256,0.0004272017,0.0007789863,0.0008766853,0.04545311,0.3084005,0.007436589,0.01644901,0.5659575],"study_design_scores_gemma":[0.00006132034,0.0003869362,0.04536889,0.0001513924,0.0001498134,0.001408822,0.000387303,0.6456215,0.2739969,0.007135583,0.02515841,0.0001731712],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.225563,0.001700034,0.7333973,0.0002256436,0.0001255935,0.0002628865,0.004440501,0.03088299,0.00340197],"genre_scores_gemma":[0.3197565,0.0004361386,0.6655418,0.000101575,0.00004500455,0.0001373831,0.01081579,0.001729989,0.00143578],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.003321964,"threshold_uncertainty_score":0.01129699,"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."}}