{"id":"W2335458838","doi":"10.1038/sdata.2014.12","title":"Direct infusion mass spectrometry metabolomics dataset: a benchmark for data processing and quality control","year":2014,"lang":"en","type":"article","venue":"Scientific Data","topic":"Metabolomics and Mass Spectrometry Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":139,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"Pfizer Canada; University of Birmingham; British Heart Foundation; Natural Environment Research Council; Advantage West Midlands; Pfizer","keywords":"Workflow; Benchmark (surveying); Computer science; Metabolomics; Data mining; Quality (philosophy); Set (abstract data type); Data quality; Quality assurance; Bioinformatics; Biology; Database; Medicine; Engineering","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":[],"consensus_categories":[],"category_scores_codex":[0.004735809,0.0002165125,0.0003701446,0.0001148987,0.0004764404,0.0003582623,0.001755885,0.00009159158,0.00001730157],"category_scores_gemma":[0.002119041,0.0001868118,0.00003221005,0.000262766,0.0003105944,0.00005135479,0.002164882,0.00008373908,0.000003981661],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00000733908,"about_ca_system_score_gemma":0.00008637316,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000292496,"about_ca_topic_score_gemma":0.0001376411,"domain_scores_codex":[0.9972419,0.0001208464,0.0003656631,0.001618125,0.0002464552,0.0004070198],"domain_scores_gemma":[0.9957342,0.00009114166,0.000214279,0.003742238,0.00009902522,0.0001191027],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0001271614,0.00007894249,0.001059971,0.0001161396,0.0001322457,3.009733e-7,0.00001398597,0.000001452824,0.8632033,0.00055218,0.1203284,0.01438591],"study_design_scores_gemma":[0.001200178,0.00008888663,0.001499025,0.00001186126,0.0001523499,0.000002768218,0.00004861394,0.005363956,0.01710105,0.0003346227,0.9738571,0.0003396077],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1830396,0.02339781,0.4085434,0.001422792,0.003816801,0.002227542,0.3745099,0.00009044031,0.002951638],"genre_scores_gemma":[0.6896641,0.0006714921,0.06826103,0.000439602,0.0006711188,0.00003177219,0.2393865,0.00004568031,0.0008286843],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8535287,"threshold_uncertainty_score":0.7617964,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04716827421050954,"score_gpt":0.3218757350716982,"score_spread":0.2747074608611887,"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."}}