{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003128548,0.002307367,0.002099204,0.004325478,0.001405208,0.001839445,0.003948228,0.001818514,0.1031391],"category_scores_gemma":[0.00926017,0.002385716,0.00187394,0.002871576,0.0005250996,0.002768117,0.00315511,0.002743388,0.04302484],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001224164,"about_ca_system_score_gemma":0.001732737,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003386351,"about_ca_topic_score_gemma":0.003518617,"domain_scores_codex":[0.9991663,0.0001187459,0.0000970396,0.0002461219,0.0002524054,0.000119414],"domain_scores_gemma":[0.9983196,0.0008017232,0.0001821322,0.0003109713,0.0002644023,0.0001212465],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","study_design_scores_codex":[0.002634907,0.0005495919,0.009841639,0.003110329,0.0009838012,0.001069648,0.0009261428,0.006676001,0.03880593,0.00936099,0.57697,0.3490711],"study_design_scores_gemma":[0.00290241,0.0005936535,0.01753857,0.0009061558,0.0004453473,0.002802924,0.0004215477,0.3688585,0.09184169,0.03575688,0.4773388,0.0005935417],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"software","genre_gemma":"software","genre_scores_codex":[0.00808354,0.0005020027,0.1909814,0.0002758463,0.0001910232,0.0003145733,0.02113871,0.775586,0.002926911],"genre_scores_gemma":[0.06542121,0.0007931554,0.7386796,0.0006751764,0.0001596825,0.002776114,0.06985931,0.1096739,0.01196179],"genre_candidate":"software","genre_consensus":"software","teacher_disagreement_score":0.1031391,"threshold_uncertainty_score":0.3450345,"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."}}