{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002451866,0.003065092,0.001600888,0.003242192,0.0013739,0.002438285,0.001924224,0.001097311,0.01103321],"category_scores_gemma":[0.003412429,0.001409013,0.002221865,0.002309179,0.0005315152,0.002025489,0.002310326,0.002490107,0.009271249],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001139747,"about_ca_system_score_gemma":0.003296822,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003639054,"about_ca_topic_score_gemma":0.006107531,"domain_scores_codex":[0.9989422,0.0001171985,0.00008800982,0.0005099032,0.0002483576,0.00009429496],"domain_scores_gemma":[0.9990032,0.0003086654,0.0001944029,0.000154454,0.0001951703,0.000144069],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.005067817,0.0008631551,0.01922223,0.004705838,0.001417336,0.001819841,0.002067048,0.01231704,0.3826539,0.008129067,0.1702732,0.3914635],"study_design_scores_gemma":[0.001317897,0.001730021,0.04300189,0.0004278395,0.0007396126,0.002046328,0.000876318,0.3436707,0.2560042,0.02034056,0.3292075,0.0006369842],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.05938017,0.002034614,0.4832617,0.0007188782,0.0002717996,0.001639036,0.1184006,0.3292789,0.005014236],"genre_scores_gemma":[0.08256645,0.001090635,0.6630875,0.0003362147,0.00007921478,0.001450243,0.2359439,0.01142271,0.004023117],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.01103321,"threshold_uncertainty_score":0.03690976,"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."}}