{"id":"W4244769383","doi":"10.14293/s2199-1006.1.sor-life.a67837.v1","title":"FASTA Herder: a web application to trim protein sequence sets","year":2014,"lang":"en","type":"preprint","venue":"ScienceOpen Research","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"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); Protein sequencing; Sequence alignment; Set (abstract data type); Redundancy (engineering); Data mining; Homology (biology); Computational biology; Theoretical computer science; 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":[0.002658793,0.002694884,0.002057573,0.00409621,0.001524949,0.002009414,0.004685993,0.001920895,0.1573183],"category_scores_gemma":[0.00837623,0.002742819,0.001972275,0.002966252,0.0005704361,0.00334503,0.003709496,0.003316931,0.07840011],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001430161,"about_ca_system_score_gemma":0.001973697,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003980631,"about_ca_topic_score_gemma":0.005121523,"domain_scores_codex":[0.9990903,0.0001094383,0.0001042625,0.0002583182,0.000299604,0.0001381042],"domain_scores_gemma":[0.9985152,0.0006394678,0.0001523396,0.0002897013,0.0002889999,0.0001142724],"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":[0.001203223,0.0002368598,0.004022719,0.001767876,0.0005062803,0.0005632745,0.0005584552,0.002336997,0.01577293,0.005435968,0.8076307,0.1599647],"study_design_scores_gemma":[0.001903306,0.0003041572,0.009847117,0.0006605071,0.0002589332,0.001939423,0.0003479034,0.1249168,0.05552911,0.03191858,0.7719316,0.0004425305],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"software","genre_gemma":"software","genre_scores_codex":[0.004318648,0.0004498138,0.14202,0.0003607589,0.0002199413,0.0003112074,0.04614687,0.8013408,0.004831986],"genre_scores_gemma":[0.04111666,0.0009086465,0.5732777,0.001080245,0.0001885292,0.003036023,0.1660627,0.1952682,0.0190613],"genre_candidate":"software","genre_consensus":"software","teacher_disagreement_score":0.1573183,"threshold_uncertainty_score":0.526282,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.08922982887083865,"score_gpt":0.4093995267781108,"score_spread":0.3201696979072722,"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."}}