{"id":"W2056251063","doi":"10.1089/cmb.2014.0156","title":"PASTA: Ultra-Large Multiple Sequence Alignment for Nucleotide and Amino-Acid Sequences","year":2014,"lang":"en","type":"article","venue":"Journal of Computational Biology","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":463,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"National Institute of General Medical Sciences; National Human Genome Research Institute; Howard Hughes Medical Institute; National Science Foundation; National Institutes of Health; National Institute on Aging; University of Alberta; Pennsylvania Department of Health","keywords":"Scalability; Multiple sequence alignment; Parallelizable manifold; Computer science; Sequence (biology); Alignment-free sequence analysis; Sequence alignment; Tree (set theory); Algorithm; Computational biology; Data mining; Biology; Mathematics; Peptide sequence; Genetics","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":[0.001779282,0.002186312,0.001940837,0.002041468,0.001742635,0.002357734,0.003189798,0.001598443,0.009685293],"category_scores_gemma":[0.0074421,0.001542999,0.001917331,0.002626024,0.000711169,0.00364309,0.002145918,0.004389331,0.01154871],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006137494,"about_ca_system_score_gemma":0.001543613,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001060265,"about_ca_topic_score_gemma":0.001756555,"domain_scores_codex":[0.9987226,0.0004651448,0.0001311184,0.000312034,0.0003021515,0.00006697385],"domain_scores_gemma":[0.9982575,0.0006545579,0.0002442256,0.0004729968,0.0002530506,0.0001178383],"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":[0.001656685,0.0003503605,0.004579003,0.003997467,0.001718264,0.00155126,0.0009213295,0.0680927,0.124498,0.06317033,0.1961024,0.5333623],"study_design_scores_gemma":[0.0003440355,0.0003557925,0.001695595,0.0004267751,0.0002582981,0.002021485,0.0001624051,0.5128191,0.04901577,0.08398648,0.3486494,0.000264888],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.006321382,0.002684684,0.9233872,0.0004391462,0.0005921589,0.0001399017,0.004703834,0.05929677,0.002434973],"genre_scores_gemma":[0.02435937,0.001376391,0.9526307,0.0002892072,0.000180537,0.0005243854,0.01356981,0.005180215,0.001889326],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.009685293,"threshold_uncertainty_score":0.03240061,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01704934772177304,"score_gpt":0.2699171632434254,"score_spread":0.2528678155216524,"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."}}