{"id":"W4391176020","doi":"10.1101/2024.01.21.576581","title":"REPrise: <i>de novo</i> interspersed repeat detection using inexact seeding","year":2024,"lang":"en","type":"preprint","venue":"bioRxiv (Cold Spring Harbor Laboratory)","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Japan Society for the Promotion of Science; Institute of Genetics; Japan Agency for Medical Research and Development","keywords":"Reprise; Annotation; Genome; Computer science; Genetics; Biology; Computational biology; Gene; Humanities","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002755712,0.001747203,0.00118603,0.001361849,0.0007242686,0.001547801,0.002266432,0.00121686,0.008682993],"category_scores_gemma":[0.006342004,0.000954633,0.001670847,0.0009623744,0.0007397041,0.001886019,0.00220234,0.002161526,0.005695899],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004982285,"about_ca_system_score_gemma":0.0008361912,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001142612,"about_ca_topic_score_gemma":0.001688606,"domain_scores_codex":[0.9984652,0.0002367956,0.0001070625,0.0006327463,0.000457962,0.0001002312],"domain_scores_gemma":[0.9972199,0.001336417,0.0003695709,0.0005428135,0.0004054617,0.0001257285],"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":[0.003099145,0.0005249199,0.01512172,0.002622073,0.00119925,0.001364316,0.001063851,0.05186094,0.3628494,0.01091173,0.1483969,0.4009858],"study_design_scores_gemma":[0.0004051989,0.0004709572,0.007865543,0.0001472052,0.0001603241,0.001084545,0.0001714122,0.4912383,0.4090549,0.01126121,0.07777371,0.0003667135],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"software","genre_scores_codex":[0.0518427,0.0005136775,0.7041905,0.00024162,0.0002035882,0.0002626408,0.006231605,0.2329021,0.003611652],"genre_scores_gemma":[0.1503126,0.0002567451,0.8039156,0.0003957527,0.0000681642,0.0005974386,0.01741641,0.02262233,0.004414985],"genre_candidate":"software","genre_consensus":null,"teacher_disagreement_score":0.008682993,"threshold_uncertainty_score":0.02904749,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01396151885755186,"score_gpt":0.2301953462824343,"score_spread":0.2162338274248825,"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."}}