{"id":"W2799515596","doi":"10.1016/j.mex.2018.04.008","title":"Extraction and cleansing of data for a non-targeted analysis of high-resolution mass spectrometry data of wastewater","year":2018,"lang":"en","type":"article","venue":"MethodsX","topic":"Metabolomics and Mass Spectrometry Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":15,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Generalitat de Catalunya; European Commission; Horizon 2020 Framework Programme; Canadian Institute for Advanced Research","keywords":"Wastewater; Mass spectrometry; Software; Workflow; Computer science; Pipeline (software); Data extraction; Chromatography; Extraction (chemistry); Data processing; Data mining; Process engineering; Chemistry; Environmental science; Database; Engineering","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001222604,0.0001033096,0.0004260417,0.0002439967,0.00003894138,0.000004964482,0.0003227697,0.00008305883,0.00001246769],"category_scores_gemma":[0.0003826582,0.00009102028,0.00006077618,0.0004071933,0.0001763015,0.00001396453,0.0003961846,0.00003597028,8.61554e-8],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000004570892,"about_ca_system_score_gemma":0.00002027935,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001233576,"about_ca_topic_score_gemma":0.00004969778,"domain_scores_codex":[0.9988968,0.00009470434,0.0003463824,0.000418458,0.0001013638,0.0001422826],"domain_scores_gemma":[0.9983801,0.00007182986,0.000231949,0.001142492,0.0001475062,0.00002608831],"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":[0.0001885823,0.00003950293,0.000609541,0.00005678491,0.001157135,8.534838e-8,0.00002659577,0.000005580559,0.9949047,0.00009880631,0.0001835002,0.002729217],"study_design_scores_gemma":[0.0004062671,0.0003345879,0.01253237,0.000008168164,0.001184761,8.818754e-7,0.00009806063,0.006697704,0.9767733,0.0002891906,0.00157349,0.0001012227],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5775353,0.0005451511,0.4209478,0.00002571315,0.00007723308,0.00009935845,0.0007228687,0.000001658771,0.00004484679],"genre_scores_gemma":[0.5706395,0.0002078889,0.4283939,0.000004885359,0.0000712699,0.00000121464,0.0006524179,0.000006852987,0.00002207472],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.01813137,"threshold_uncertainty_score":0.3711699,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05954794046672198,"score_gpt":0.3663454230117452,"score_spread":0.3067974825450233,"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."}}