{"id":"W2909669832","doi":"10.1186/s12862-019-1350-2","title":"Evaluating the usefulness of alignment filtering methods to reduce the impact of errors on evolutionary inferences","year":2019,"lang":"en","type":"article","venue":"BMC Evolutionary Biology","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":175,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université de Montréal","funders":"Agence Nationale de la Recherche; Compute Canada","keywords":"Inference; Computer science; Sequence (biology); Multiple sequence alignment; Filter (signal processing); Artificial intelligence; Sequence alignment; Biology; Software; Block (permutation group theory); Pattern recognition (psychology); Data mining; Genetics; Mathematics; Computer vision","routes":{"ca_aff":true,"ca_fund":true,"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":[0.0006572418,0.0001562342,0.0002117943,0.00004405474,0.0001099924,0.000002622926,0.0003670897,0.00009503923,0.00003852962],"category_scores_gemma":[0.0002269641,0.00008708129,0.0001730344,0.0001204574,0.0001993803,9.510497e-7,0.0003201287,0.00006638886,0.000006543376],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003361524,"about_ca_system_score_gemma":0.0001974106,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001650619,"about_ca_topic_score_gemma":0.000007534275,"domain_scores_codex":[0.99858,0.0004876622,0.0003174736,0.0002980049,0.00009946567,0.0002173532],"domain_scores_gemma":[0.9989087,0.0002564284,0.0001877276,0.0004806779,0.0001346868,0.0000317731],"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":[0.0002309239,0.00004787907,0.07384271,0.00001154528,0.0001413517,3.227355e-8,0.000142014,0.02479309,0.8982059,0.0008584236,0.0003342669,0.001391851],"study_design_scores_gemma":[0.0003600703,0.003534835,0.9189812,0.00002638398,0.00003023283,0.00001153737,0.0005161677,0.00176283,0.0717585,0.002041726,0.0007826785,0.0001938396],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.995783,0.001368929,0.001532754,0.0001523471,0.0002743139,0.0004015834,0.00007442342,0.000002083094,0.0004106235],"genre_scores_gemma":[0.9896387,0.0000422151,0.00995938,0.00005023782,0.0001048629,0.00006390769,0.00002753754,0.000009473811,0.0001037215],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8451385,"threshold_uncertainty_score":0.3551072,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.09897132812452442,"score_gpt":0.4079142001218601,"score_spread":0.3089428719973357,"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."}}