{"id":"W2908220830","doi":"10.7717/peerj.6142","title":"Fully automated sequence alignment methods are comparable to, and much faster than, traditional methods in large data sets: an example with hepatitis B virus","year":2019,"lang":"en","type":"article","venue":"PeerJ","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"","keywords":"Phylogenetic tree; Multiple sequence alignment; Alignment-free sequence analysis; Computer science; Sequence alignment; Sequence (biology); Tree (set theory); Genome; Computational biology; Inference; Data mining; Biology; Artificial intelligence; Genetics; Mathematics","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":[0.0006368728,0.0001639776,0.0002413454,0.00003762892,0.00005839245,0.00002740805,0.0002487435,0.00006775418,0.00004802779],"category_scores_gemma":[0.0000182519,0.0001447189,0.0000181208,0.0000770955,0.00003705077,0.000004481822,0.0002518295,0.00005875751,0.000005111072],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001218101,"about_ca_system_score_gemma":0.00004856137,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001131245,"about_ca_topic_score_gemma":0.002546576,"domain_scores_codex":[0.9986758,0.0002177717,0.0001781395,0.0005592659,0.0001067313,0.0002622447],"domain_scores_gemma":[0.9991907,0.0000387753,0.00005634937,0.0005694263,0.00005084385,0.00009388865],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","study_design_scores_codex":[0.00008078466,0.0001243659,0.110095,0.00003212182,0.0001089051,0.000005512976,0.0003997708,0.0004823119,0.8850179,0.00009619822,0.001725353,0.001831877],"study_design_scores_gemma":[0.001933464,0.001176973,0.7590641,0.00005580456,0.00006123204,0.0000714398,0.001001304,0.02790592,0.1583453,0.0003959246,0.04918722,0.0008012885],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9863741,0.0007246834,0.01141076,0.0001341004,0.00008837501,0.0002939003,0.0007008944,0.00001112181,0.0002620076],"genre_scores_gemma":[0.7741579,0.0001533796,0.2246236,0.0003950728,0.00003445099,0.00003423446,0.0004940268,0.00001756286,0.00008982851],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.7266725,"threshold_uncertainty_score":0.5901464,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1235077244675482,"score_gpt":0.3777330263138278,"score_spread":0.2542253018462797,"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."}}