{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003179168,0.002098965,0.001550131,0.003038526,0.0008653979,0.001495667,0.002900196,0.001507737,0.004659909],"category_scores_gemma":[0.003814458,0.001121092,0.002491578,0.001847876,0.000596351,0.002079201,0.002221111,0.001833223,0.003454321],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004805186,"about_ca_system_score_gemma":0.001092645,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002050438,"about_ca_topic_score_gemma":0.003392525,"domain_scores_codex":[0.996716,0.0003920631,0.0002660932,0.0009589131,0.001463137,0.0002037271],"domain_scores_gemma":[0.9968796,0.0009713391,0.0004414146,0.0007726463,0.0007845006,0.0001505896],"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":[0.001226278,0.0004502747,0.008088717,0.001813125,0.0007891,0.001094502,0.0005932289,0.01520367,0.2751026,0.004230535,0.01489953,0.6765084],"study_design_scores_gemma":[0.0003155432,0.001030533,0.01190669,0.0001210886,0.0005000217,0.00297614,0.000282099,0.5702339,0.347279,0.005387044,0.05950816,0.0004598428],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.01911313,0.0009773272,0.9438519,0.0001059882,0.0001893999,0.000282066,0.0009320627,0.03346435,0.00108381],"genre_scores_gemma":[0.03783788,0.0002695951,0.9556333,0.0001892246,0.00007959326,0.0001601155,0.002588404,0.001197493,0.002044416],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.004659909,"threshold_uncertainty_score":0.01681322,"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."}}