{"id":"W4392894260","doi":"10.1101/2024.03.15.585313","title":"Benchmarking reveals superiority of deep learning variant callers on bacterial nanopore sequence data","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":11,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Institute of Infection and Immunity; Australian Government","keywords":"Indel; Nanopore sequencing; Benchmarking; Deep sequencing; Deep learning; Computational biology; Genomics; Computer science; Artificial intelligence; DNA sequencing; Genome; Whole genome sequencing; Identification (biology); Machine learning; Data mining; Biology; Genetics; Single-nucleotide polymorphism; Gene; Genotype","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":[0.006117233,0.0008770349,0.0005818415,0.0009530249,0.0004649983,0.001284556,0.001189187,0.001058633,0.0009049769],"category_scores_gemma":[0.01550963,0.0002344897,0.0006292831,0.0009457326,0.0006814341,0.001206586,0.001089365,0.001045453,0.0005769281],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007430394,"about_ca_system_score_gemma":0.0007096789,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.006982425,"about_ca_topic_score_gemma":0.007773828,"domain_scores_codex":[0.9954563,0.001524426,0.0003697768,0.001089843,0.001221098,0.0003385156],"domain_scores_gemma":[0.9929369,0.003928982,0.0003944444,0.001164636,0.001314886,0.0002601664],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.002447378,0.0006572022,0.118798,0.0008274525,0.001237309,0.0003891626,0.0004842297,0.5418978,0.09336679,0.004227716,0.00915934,0.2265077],"study_design_scores_gemma":[0.00004259819,0.0004483654,0.01934431,0.00005189568,0.00007176543,0.000175594,0.0001573933,0.9178677,0.05507769,0.003700402,0.002973958,0.00008834777],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"methods","genre_scores_codex":[0.9217014,0.001132886,0.0675169,0.0003607634,0.0001407189,0.00005343501,0.002849017,0.003379576,0.00286527],"genre_scores_gemma":[0.9432132,0.0001830123,0.04812629,0.0002562904,0.00002347256,0.00004237582,0.007103719,0.000271473,0.0007802753],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.006982425,"threshold_uncertainty_score":0.03235143,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02408183641720502,"score_gpt":0.2438137082093501,"score_spread":0.2197318717921451,"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."}}