{"id":"W4318617212","doi":"10.1038/s41597-023-01949-y","title":"Quality control and removal of technical variation of NMR metabolic biomarker data in ~120,000 UK Biobank participants","year":2023,"lang":"en","type":"article","venue":"Scientific Data","topic":"Metabolomics and Mass Spectrometry Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":177,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"NIHR Cambridge Biomedical Research Centre; Economic and Social Research Council; Engineering and Physical Sciences Research Council; Chief Scientist Office, Scottish Government Health and Social Care Directorate; Medical Research Council; Public Health Agency; University of Cambridge; Department of Health and Social Care; Canadian Institutes of Health Research; Health and Social Care Research and Development Division; National Institute for Health and Care Research; Science and Technology Facilities Council; British Heart Foundation; Scottish Government; Dell EMC; Wellcome Trust","keywords":"Biobank; Biomarker; Biomarker discovery; Computer science; Computational biology; Medicine; Bioinformatics; Chemistry; Biology; Proteomics; Biochemistry","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[{"model":"gemma","categories":[],"domain":null,"study_design":"not_applicable","genre":"methods","about_ca_system":false,"about_ca_topic":false,"confidence":"high","status":"direct model label, unvalidated"},{"model":"gpt","categories":[],"domain":null,"study_design":"bench_or_experimental","genre":"methods","about_ca_system":false,"about_ca_topic":false,"confidence":"low","status":"direct model label, unvalidated"}],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.06454731,0.001048966,0.001739717,0.003175742,0.001743557,0.002945558,0.002074475,0.001522144,0.008179365],"category_scores_gemma":[0.1708335,0.001038821,0.001492133,0.006036737,0.001591243,0.0009617543,0.00353755,0.001082671,0.003857527],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001187252,"about_ca_system_score_gemma":0.003292882,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01477034,"about_ca_topic_score_gemma":0.01583468,"domain_scores_codex":[0.9492206,0.02472652,0.0082099,0.008172981,0.008188397,0.00148159],"domain_scores_gemma":[0.889829,0.03888051,0.01272849,0.03320195,0.02418674,0.001173359],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.006559118,0.0004919937,0.4365939,0.004906255,0.002481076,0.001492885,0.01118886,0.008169628,0.059653,0.005620116,0.1042715,0.3585717],"study_design_scores_gemma":[0.000647501,0.0008106048,0.6343642,0.0009935396,0.001332632,0.002214053,0.001152597,0.01930656,0.05198591,0.004175604,0.2826559,0.0003608351],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"methods","genre_scores_codex":[0.4773415,0.003601259,0.4138023,0.002996986,0.001109562,0.004794122,0.07997186,0.008378145,0.008004301],"genre_scores_gemma":[0.5503451,0.001143477,0.3388328,0.00196631,0.0003931513,0.009949598,0.08353007,0.004491985,0.00934742],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.06454731,"threshold_uncertainty_score":0.3413629,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1024925104869529,"score_gpt":0.3681364229874934,"score_spread":0.2656439125005406,"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."}}