{"id":"W1409613305","doi":"10.14293/s2199-1006.1.sor-life.a67837.v2","title":"FASTA Herder: a web application to trim protein sequence sets","year":2015,"lang":"en","type":"preprint","venue":"ScienceOpen Research","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Ottawa; Ottawa Hospital","funders":"Ontario Ministry of Research and Innovation; Government of Ontario","keywords":"Computer science; Usability; Sequence (biology); Sequence alignment; Protein sequencing; Redundancy (engineering); Set (abstract data type); Homology (biology); Data mining; Multiple sequence alignment; Theoretical computer science; Computational biology; Peptide sequence; Biology; Genetics; Amino acid; Programming language; Human–computer interaction","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":[0.003660977,0.0002192583,0.0002288305,0.0001770681,0.0002949249,0.0002271249,0.001718406,0.0002384769,0.00001307259],"category_scores_gemma":[0.000419054,0.000200007,0.00006774348,0.000482503,0.0004093924,0.000001001034,0.004773567,0.0004237441,0.0001373089],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001020569,"about_ca_system_score_gemma":0.002238587,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0004623348,"about_ca_topic_score_gemma":0.0003710145,"domain_scores_codex":[0.9968069,0.000240048,0.0002552989,0.001211791,0.0008462352,0.0006397313],"domain_scores_gemma":[0.9974512,0.00001548182,0.00007420206,0.001160664,0.0009705125,0.0003279136],"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":[0.0000517969,0.00004383709,0.000418734,0.00004313837,0.00001893841,0.000002314048,0.0001794519,0.0005077312,0.9840894,0.0001205971,0.00590205,0.00862199],"study_design_scores_gemma":[0.001233636,0.002264084,0.004107052,0.0002713777,0.00002299289,0.00002223198,0.001668292,0.003840955,0.3274749,0.02139622,0.6358038,0.001894453],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9860824,0.0007904768,0.0002680369,0.001789147,0.000148056,0.002857131,0.0002146363,0.000005017027,0.007845117],"genre_scores_gemma":[0.9928073,0.0001217553,0.003022723,0.0001043264,0.000203907,0.001179594,0.00006865314,0.00002406303,0.002467685],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.6566145,"threshold_uncertainty_score":0.8156046,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1451036084236526,"score_gpt":0.4314434779087243,"score_spread":0.2863398694850717,"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."}}