{"id":"W4309988277","doi":"10.1007/s00216-022-04434-4","title":"Exploring chemical space in non-targeted analysis: a proposed ChemSpace tool","year":2022,"lang":"en","type":"article","venue":"Analytical and Bioanalytical Chemistry","topic":"Metabolomics and Mass Spectrometry Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":68,"is_retracted":false,"has_abstract":false,"ca_institutions":"Health Canada","funders":"Pacific Northwest National Laboratory; Government of Canada; National Institute of Environmental Health Sciences; Battelle; U.S. Department of Energy","keywords":"Workflow; Chemical space; Analyte; Sample (material); Computer science; Identification (biology); Data mining; A priori and a posteriori; Chemistry; Chromatography; Database; Drug discovery","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":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0004040598,0.0003244032,0.0006002748,0.0001510253,0.0001520696,0.00004547653,0.0002854902,0.0001190985,0.0002749921],"category_scores_gemma":[0.0002383242,0.0003022428,0.0003169666,0.001379382,0.0002323112,0.000009851872,0.0007125347,0.0004369502,0.000003486205],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006745029,"about_ca_system_score_gemma":0.0000652698,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004189629,"about_ca_topic_score_gemma":0.000007288766,"domain_scores_codex":[0.9976523,0.0000391783,0.0004429879,0.0008836715,0.0003893583,0.0005925079],"domain_scores_gemma":[0.9991508,0.00004096382,0.00008299104,0.0004352504,0.00005942932,0.0002306422],"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":[0.0004132563,0.0005787992,0.0188691,0.00009936623,0.001799875,0.00008368149,0.00008443141,0.000148033,0.9759606,0.0008738982,0.00059129,0.0004976706],"study_design_scores_gemma":[0.003859319,0.0004990078,0.02502939,0.00002351181,0.002572724,0.00009133451,0.001867932,0.03722492,0.8940858,0.0004652989,0.03194884,0.002331952],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9952362,0.0005067725,0.0001790652,0.001631913,0.00003259987,0.000143481,0.00003564841,0.00001933824,0.002214936],"genre_scores_gemma":[0.9974403,0.0002479655,0.0003553582,0.0002141352,0.0001569829,0.00006705771,0.000123773,0.00002258123,0.001371891],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.08187483,"threshold_uncertainty_score":0.999943,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02132814043101137,"score_gpt":0.2359254582947765,"score_spread":0.2145973178637651,"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."}}