{"id":"W3174489946","doi":"10.1093/nar/gkab563","title":"A sensitive repeat identification framework based on short and long reads","year":2021,"lang":"en","type":"article","venue":"Nucleic Acids Research","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":19,"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":"Biology; Identification (biology); Computational biology; Genetics","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":[0.001383068,0.001001083,0.0009858209,0.001806449,0.0005627273,0.001001852,0.001888406,0.0009605272,0.002013509],"category_scores_gemma":[0.001818349,0.0004457949,0.0008997014,0.001024581,0.0006250935,0.001826997,0.001831392,0.001195919,0.0013457],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005419388,"about_ca_system_score_gemma":0.00103123,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001921585,"about_ca_topic_score_gemma":0.002139099,"domain_scores_codex":[0.9980271,0.0002020888,0.00009019501,0.0007038285,0.0008065779,0.0001701679],"domain_scores_gemma":[0.9989583,0.0002658381,0.0001750631,0.0001901541,0.0003226199,0.00008804314],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.000586235,0.0002049595,0.002497545,0.000573956,0.0001330869,0.0008629278,0.000371552,0.0284154,0.4009886,0.03648692,0.004802258,0.5240766],"study_design_scores_gemma":[0.00007288676,0.0006306672,0.003464499,0.0000892216,0.0001724641,0.00191888,0.0002056645,0.6366046,0.2692123,0.04220656,0.04512055,0.0003017398],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.007233562,0.0004604924,0.9877552,0.00005132475,0.00004964959,0.0000972,0.0002189824,0.003181179,0.0009523457],"genre_scores_gemma":[0.1140475,0.00045181,0.879353,0.000274358,0.0001091845,0.0002379174,0.001210221,0.0003283798,0.003987607],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.002013509,"threshold_uncertainty_score":0.007314444,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03497118956297619,"score_gpt":0.3371469086751533,"score_spread":0.3021757191121772,"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."}}