{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0001469008,0.0006515664,0.0009903311,0.0001115705,0.0001131532,0.00006318092,0.0008354314,0.000715724,0.00001282589],"category_scores_gemma":[0.0001542587,0.0004331243,0.0001551337,0.0001610177,0.0003908115,0.00005364705,0.001256461,0.00039201,0.000003053455],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005642576,"about_ca_system_score_gemma":0.0002348317,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002110426,"about_ca_topic_score_gemma":0.00001251569,"domain_scores_codex":[0.9970722,0.0001776548,0.0007216543,0.001403787,0.0001120485,0.0005127242],"domain_scores_gemma":[0.9982701,0.00006872046,0.0004730677,0.001063932,0.00004643706,0.00007772519],"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":[0.00004067097,0.000003341623,0.0002219991,0.002366745,0.00008697243,3.381167e-7,0.00001245438,5.135309e-7,0.0006241139,0.001747032,0.0001699738,0.9947258],"study_design_scores_gemma":[0.0005543039,0.0001677212,0.0001708833,0.003063803,0.00007973711,0.0002385463,0.00001026604,0.00004675757,0.000007750687,0.001619843,0.9932783,0.0007620803],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"review","genre_gemma":"review","genre_scores_codex":[0.0008454652,0.9849139,0.002878766,0.00001876666,0.008086562,0.0005694925,0.002642343,0.00001924969,0.00002544746],"genre_scores_gemma":[0.001185429,0.9816507,0.001059642,0.00001948328,0.001882793,0.00004199748,0.01409147,0.00004492806,0.00002362496],"genre_candidate":"review","genre_consensus":"review","teacher_disagreement_score":0.9939638,"threshold_uncertainty_score":0.9998121,"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."}}