{"id":"W4411529508","doi":"10.1111/tpj.70288","title":"From data to discovery: leveraging big data in plant natural products biosynthesis research","year":2025,"lang":"en","type":"review","venue":"The Plant Journal","topic":"Genetics, Bioinformatics, and Biomedical Research","field":"Biochemistry, Genetics and Molecular Biology","cited_by":8,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia, Okanagan Campus; University of British Columbia","funders":"Natural Sciences and Engineering Research Council of Canada; Deutsche Forschungsgemeinschaft; Michael Smith Health Research BC","keywords":"Big data; Data science; Natural (archaeology); Computer science; Data mining; Biology","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":["open_science"],"consensus_categories":[],"category_scores_codex":[0.005752807,0.0003750132,0.0008085162,0.0004808485,0.0002924278,0.0005100009,0.00736997,0.0003024929,0.000008396561],"category_scores_gemma":[0.004914053,0.0002136861,0.0001020679,0.0005657433,0.0002078843,0.00002177873,0.00714381,0.001787881,0.00004855168],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00008014881,"about_ca_system_score_gemma":0.002333635,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000230378,"about_ca_topic_score_gemma":0.0003953194,"domain_scores_codex":[0.9954917,0.0008378642,0.0008682748,0.0008451216,0.001081845,0.0008751485],"domain_scores_gemma":[0.9954768,0.0006625577,0.0002158398,0.003301918,0.0001285037,0.0002143837],"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":[0.000106668,0.00008878851,0.000007766056,0.002322384,0.0003442441,0.00008744768,0.0001165981,4.88494e-7,0.0005353351,0.000002306842,0.1409438,0.8554442],"study_design_scores_gemma":[0.0001636097,0.00006990426,0.00001563052,0.007220191,0.0001182883,0.0002048004,0.0001944079,0.00007237813,0.0002384779,0.00002933433,0.9913881,0.000284914],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"review","genre_gemma":"review","genre_scores_codex":[0.0003564563,0.9806229,0.0001127865,0.001658914,0.00152143,0.0007432349,0.01485282,0.000005348881,0.0001260791],"genre_scores_gemma":[0.0003734548,0.9774571,0.0004467757,0.000115019,0.003496567,0.00001116096,0.01719505,0.00002778892,0.000877062],"genre_candidate":"review","genre_consensus":"review","teacher_disagreement_score":0.8551593,"threshold_uncertainty_score":0.9980006,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2746612450864727,"score_gpt":0.4060715273915018,"score_spread":0.1314102823050291,"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."}}