{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003127611,0.000223487,0.0002378669,0.0001747591,0.0003770167,0.0002294513,0.001741687,0.0002404,0.00001682016],"category_scores_gemma":[0.0003587656,0.0002042748,0.00008141134,0.0003917892,0.0004144707,7.610802e-7,0.004160754,0.0004238473,0.0001424551],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006278917,"about_ca_system_score_gemma":0.001064539,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0003512776,"about_ca_topic_score_gemma":0.0002819164,"domain_scores_codex":[0.9968148,0.0002709182,0.0002638711,0.001272832,0.0007262629,0.0006513422],"domain_scores_gemma":[0.9978447,0.00002414952,0.00008003194,0.001231333,0.0005725174,0.0002472651],"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":[0.00003496627,0.00003229023,0.0004106167,0.00005583113,0.0000163861,0.000001080854,0.00009140473,0.0005461798,0.9857672,0.0001773569,0.002122348,0.01074431],"study_design_scores_gemma":[0.000873756,0.001768061,0.006934133,0.0002710924,0.00001888591,0.00001459132,0.0005793539,0.005663581,0.4157059,0.01138004,0.5551928,0.001597742],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.988167,0.0003867704,0.0009826689,0.001849023,0.0001384786,0.002643633,0.0001244005,0.000004991387,0.005703013],"genre_scores_gemma":[0.9930634,0.0001182648,0.003279057,0.0001607297,0.0002273234,0.001197343,0.00005410315,0.00002442828,0.001875385],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.5700613,"threshold_uncertainty_score":0.8330083,"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."}}