{"id":"W4213220107","doi":"10.1016/j.xpro.2022.101175","title":"TreeTuner: A pipeline for minimizing redundancy and complexity in large phylogenetic datasets","year":2022,"lang":"en","type":"article","venue":"STAR Protocols","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":4,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University; Western University; Dalhousie University","funders":"Natural Sciences and Engineering Research Council of Canada; Gordon and Betty Moore Foundation","keywords":"Phylogenetic tree; Pipeline (software); Redundancy (engineering); Trimming; Computer science; Multiple sequence alignment; Data mining; Protocol (science); Computational biology; Biology; Sequence alignment; Genetics","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":[0.0003533396,0.0001442619,0.0001860817,0.00004151259,0.0002330984,0.0000162836,0.0001777141,0.00003810926,0.0000232089],"category_scores_gemma":[0.00003989813,0.0001528114,0.00004772392,0.00007073645,0.00006096842,6.399927e-7,0.0004530404,0.00007413174,4.865408e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001572428,"about_ca_system_score_gemma":0.00005552988,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002304833,"about_ca_topic_score_gemma":0.0002615857,"domain_scores_codex":[0.9988896,0.00008024733,0.0002372484,0.0003996897,0.00008856956,0.0003046412],"domain_scores_gemma":[0.9995351,0.00001536577,0.00007618176,0.0002981102,0.00002542085,0.00004980044],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"not_applicable","study_design_scores_codex":[0.001656892,0.0008309723,0.03540613,0.0003432564,0.0001245941,0.00001374083,0.0007009149,0.0001790109,0.928838,0.0009877415,0.01813738,0.01278135],"study_design_scores_gemma":[0.006406869,0.001453742,0.0220316,0.00002501469,0.00002104534,0.00001946289,0.0005628778,0.001098749,0.0216584,0.002586492,0.9435906,0.0005450977],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9248641,0.001449768,0.0008053266,0.0003912915,0.00008974892,0.06477988,0.007301879,0.000008167808,0.0003098978],"genre_scores_gemma":[0.8871735,0.00002849427,0.005470093,0.0003571757,0.0001309814,0.1058182,0.0008221646,0.00003305884,0.0001663388],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9254532,"threshold_uncertainty_score":0.6231467,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05669721992346096,"score_gpt":0.3277885316308824,"score_spread":0.2710913117074215,"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."}}