{"id":"W2338352874","doi":"10.1101/047167","title":"Functional metagenomics reveals novel β-galactosidases not predictable from gene sequences","year":2016,"lang":"en","type":"preprint","venue":"bioRxiv (Cold Spring Harbor Laboratory)","topic":"Enzyme Production and Characterization","field":"Biochemistry, Genetics and Molecular Biology","cited_by":4,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Sinorhizobium meliloti; Biology; Glycoside hydrolase; Complementation; ORFS; Cosmid; Gene; Genetics; Open reading frame; Peptide sequence","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":[0.0003556193,0.0004781491,0.0003877078,0.0001103042,0.0001556694,0.000150671,0.0003962058,0.0006813175,0.0001203313],"category_scores_gemma":[0.0002453421,0.0004595639,0.0001689546,0.0001232282,0.0001224115,0.00002317807,0.0004279799,0.0003100733,0.00005795707],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000979989,"about_ca_system_score_gemma":0.000473218,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002245897,"about_ca_topic_score_gemma":0.000001401705,"domain_scores_codex":[0.9974775,0.00009955729,0.0005057682,0.001229266,0.0003037666,0.000384188],"domain_scores_gemma":[0.9977276,0.00002164331,0.000479726,0.001101559,0.0004716076,0.0001978768],"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":[0.00007786331,0.0000890537,0.003306579,0.00004321795,0.0002564671,0.000002466837,0.000002082917,0.00004287549,0.9946782,0.00009392862,0.001406358,9.306271e-7],"study_design_scores_gemma":[0.0004116124,0.00003857728,0.05962919,0.00006993142,0.0001033075,3.552576e-8,9.305604e-7,0.00002151824,0.9267765,0.000003778952,0.01241989,0.0005247336],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9578462,0.001322008,0.03459152,0.0004954375,0.002188792,0.0004198392,0.002986009,0.0001391904,0.00001105071],"genre_scores_gemma":[0.9912282,0.0007473927,0.003928851,0.0005587323,0.003127455,0.0001512833,0.00003878567,0.000108986,0.0001102879],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.06790169,"threshold_uncertainty_score":0.9997856,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01936653418905786,"score_gpt":0.2118760672276052,"score_spread":0.1925095330385473,"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."}}