{"id":"W3093072871","doi":"10.1186/s12859-020-03779-w","title":"RepAHR: an improved approach for de novo repeat identification by assembly of the high-frequency reads","year":2020,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":7,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Saskatchewan","funders":"Higher Education Discipline Innovation Project; King Abdullah University of Science and Technology; National Natural Science Foundation of China","keywords":"Sequence assembly; Hybrid genome assembly; Identification (biology); Genome; Computational biology; Reference genome; Computer science; DNA sequencing; DNA microarray; Biology; Genetics; DNA; 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":[0.0002152366,0.0001144943,0.0001298889,0.00001002251,0.00008499751,0.00001842454,0.0003035249,0.0001089039,6.353064e-7],"category_scores_gemma":[0.0001683939,0.00008807662,0.0000925809,0.00006968717,0.00005883706,0.000002997387,0.00009424805,0.00004176216,5.575731e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001017872,"about_ca_system_score_gemma":0.00008425385,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001370584,"about_ca_topic_score_gemma":0.000007555544,"domain_scores_codex":[0.999196,0.00002510192,0.0003790563,0.0001568005,0.0000810005,0.0001620307],"domain_scores_gemma":[0.9991405,0.00001057165,0.0002432813,0.0004377459,0.0001090445,0.00005887006],"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":[0.00004106795,0.0000387943,0.001677089,0.000183726,0.00004218975,1.448268e-8,0.0004600494,0.0001954635,0.994414,0.0001709971,0.002153958,0.0006225943],"study_design_scores_gemma":[0.001260287,0.0006931439,0.00614394,0.000009254008,0.0001259196,0.0000100609,0.001242798,0.1059211,0.8796986,0.0002460734,0.004236401,0.0004123631],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7477105,0.0002992651,0.2499859,0.0002144743,0.0001090796,0.0006912344,0.0005152752,0.000008776266,0.000465497],"genre_scores_gemma":[0.8358787,0.00006792739,0.1631136,0.0004075588,0.0001014666,0.00005007183,0.0002757879,0.00001605446,0.00008881408],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.1147154,"threshold_uncertainty_score":0.359166,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01856362151659104,"score_gpt":0.2363889508222706,"score_spread":0.2178253293056795,"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."}}