{"id":"W2790405355","doi":"10.1186/s13068-018-1027-x","title":"SACCHARIS: an automated pipeline to streamline discovery of carbohydrate active enzyme activities within polyspecific families and de novo sequence datasets","year":2018,"lang":"en","type":"article","venue":"Biotechnology for Biofuels","topic":"Glycosylation and Glycoproteins Research","field":"Biochemistry, Genetics and Molecular Biology","cited_by":96,"is_retracted":false,"has_abstract":true,"ca_institutions":"Agriculture and Agri-Food Canada","funders":"Agriculture and Agri-Food Canada; Alberta Innovates; Alberta Innovates Bio Solutions; Beef Cattle Research Council","keywords":"Biology; In silico; Computational biology; Carbohydrate-binding module; Multiple sequence alignment; Consensus sequence; Sequence alignment; Sequence analysis; Sequence (biology); Phylogenetic tree; Conserved sequence; Protein family; Genetics; Glycoside hydrolase; Peptide sequence; Gene","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":[0.0002051171,0.0001932606,0.0002183089,0.0002491754,0.0001285183,0.00003286328,0.0003082556,0.0004471301,0.000006045312],"category_scores_gemma":[0.0002223337,0.0001770179,0.0000388823,0.0002522055,0.000639434,0.0000275052,0.0002184181,0.0001182378,0.000002719461],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002713731,"about_ca_system_score_gemma":0.0001440014,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001848488,"about_ca_topic_score_gemma":0.0005540474,"domain_scores_codex":[0.99875,0.00004862456,0.0002479719,0.000496143,0.0001077993,0.0003494213],"domain_scores_gemma":[0.9991381,0.00001923203,0.000113734,0.0005375887,0.00009856505,0.00009273685],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.000507588,0.00007556071,0.0001112667,0.00002608227,0.00004252915,0.000002701206,0.000128291,0.000007238889,0.9930023,0.0002898863,0.000236353,0.005570235],"study_design_scores_gemma":[0.0004947803,0.00137204,0.0001733832,0.0000168549,0.00001129646,0.0000198719,0.0005706887,0.001214973,0.9914742,0.0001942013,0.004262964,0.0001947728],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9899079,0.0001619275,0.005498821,0.0005430051,0.00006994665,0.0005036024,0.003198974,0.00009906558,0.00001681873],"genre_scores_gemma":[0.9945111,0.0001735823,0.004107223,0.0001416241,0.0001016941,0.00006140429,0.0007617912,0.00002371196,0.0001178801],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.005375462,"threshold_uncertainty_score":0.7218581,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02146523532221202,"score_gpt":0.3247519228078892,"score_spread":0.3032866874856772,"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."}}