{"id":"W2413508140","doi":"10.1016/j.sbi.2016.05.017","title":"Novel function discovery through sequence and structural data mining","year":2016,"lang":"en","type":"review","venue":"Current Opinion in Structural Biology","topic":"Protein Structure and Dynamics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":40,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Waterloo","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computational biology; Inference; Protein structure database; Protein function prediction; Function (biology); Sequence (biology); Context (archaeology); Similarity (geometry); Protein domain; Biology; Phylogenetic tree; Data mining; Protein sequencing; Computer science; Protein function; Genetics; Artificial intelligence; Peptide sequence; Sequence database; 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":[0.001534274,0.001585181,0.002627948,0.002616337,0.0002046542,0.001572199,0.00244937,0.001126819,0.00169391],"category_scores_gemma":[0.002222488,0.0004998766,0.00111655,0.003006855,0.0008146627,0.002107084,0.001213833,0.002283088,0.001569521],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005779504,"about_ca_system_score_gemma":0.001171695,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0006465353,"about_ca_topic_score_gemma":0.0008423096,"domain_scores_codex":[0.9995635,0.00004554695,0.00004576107,0.0001223912,0.0001862814,0.00003652395],"domain_scores_gemma":[0.9991654,0.0004658123,0.0001170075,0.00005484296,0.0001549565,0.0000419848],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00007215719,0.00008786249,0.0005290844,0.004960323,0.0001773685,0.000240321,0.00002633099,0.001383097,0.004582026,0.004866017,0.009072524,0.9740029],"study_design_scores_gemma":[0.0001634533,0.0004169693,0.004330757,0.008747794,0.001723374,0.009444082,0.0001948794,0.02538712,0.02116116,0.07304788,0.8551427,0.000239848],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"review","genre_gemma":"review","genre_scores_codex":[0.002536931,0.9544519,0.03696724,0.001630172,0.0005760825,0.00005536521,0.0004021083,0.0003434822,0.003036728],"genre_scores_gemma":[0.01071985,0.9530093,0.03203087,0.001051599,0.0005843626,0.00005211984,0.001117008,0.00003814838,0.001396747],"genre_candidate":"review","genre_consensus":"review","teacher_disagreement_score":0.002627948,"threshold_uncertainty_score":0.0081141,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1232174642999022,"score_gpt":0.412347827177593,"score_spread":0.2891303628776908,"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."}}