{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003913219,0.002271552,0.001545012,0.002980032,0.001187015,0.002571089,0.001588415,0.001022419,0.0188073],"category_scores_gemma":[0.01466671,0.001185265,0.002060472,0.001942615,0.0007120188,0.001499099,0.002805053,0.002147205,0.02303783],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006775099,"about_ca_system_score_gemma":0.002186497,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0009847549,"about_ca_topic_score_gemma":0.001586247,"domain_scores_codex":[0.9963855,0.0005272112,0.0005702255,0.001069246,0.001193294,0.0002545322],"domain_scores_gemma":[0.9933987,0.002201899,0.0005523333,0.00214853,0.001464919,0.0002337217],"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":[0.00270589,0.0004323837,0.01782277,0.00451427,0.0007320308,0.001875052,0.001543113,0.003772482,0.6355184,0.004734203,0.09809081,0.2282585],"study_design_scores_gemma":[0.000182466,0.0003173127,0.01576067,0.0003079648,0.0001856508,0.001177918,0.0001974294,0.01419726,0.7808379,0.005188686,0.1813434,0.0003033848],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.04179034,0.0007133401,0.7283867,0.000884986,0.0004563657,0.001573101,0.07897747,0.1428179,0.004399947],"genre_scores_gemma":[0.04371414,0.0005503118,0.846252,0.0008954945,0.0001108808,0.003419599,0.07127989,0.02900651,0.004771161],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.0188073,"threshold_uncertainty_score":0.06291664,"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."}}