{"id":"W3194841450","doi":"10.1021/acs.analchem.1c01465","title":"CFM-ID 4.0: More Accurate ESI-MS/MS Spectral Prediction and Compound Identification","year":2021,"lang":"en","type":"article","venue":"Analytical Chemistry","topic":"Metabolomics and Mass Spectrometry Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":396,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"Natural Sciences and Engineering Research Council of Canada; Eesti Teadusagentuur; Genome British Columbia; Canada Foundation for Innovation; Alberta Machine Intelligence Institute; National Institute of Environmental Health Sciences; Canadian Institutes of Health Research; Genome Canada; Canadian Institute for Advanced Research","keywords":"Chemistry; Identification (biology); Mass spectrometry; Chromatography; Analytical Chemistry (journal)","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":[0.0001198934,0.000166141,0.0002002744,0.00001626551,0.0001096154,0.0000730949,0.0001018098,0.000149124,0.0001316701],"category_scores_gemma":[0.0001735884,0.0001663782,0.00008550473,0.0001355366,0.0001428399,0.000006480324,0.0001369068,0.0001343222,0.000006726481],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001992709,"about_ca_system_score_gemma":0.00005649881,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000008033314,"about_ca_topic_score_gemma":0.000005787608,"domain_scores_codex":[0.9988385,0.0000184635,0.0002635886,0.0004873693,0.0001504336,0.0002416557],"domain_scores_gemma":[0.9993414,0.00001586354,0.00007157257,0.0003372609,0.000112522,0.0001213434],"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":[0.00002675264,0.00007300432,0.003356194,0.00005416848,0.0001763439,0.00001687525,0.00001496514,0.0000112115,0.9930328,0.0002717806,0.002817489,0.0001484225],"study_design_scores_gemma":[0.0005585645,0.00003888183,0.02084593,0.00001098644,0.0001609286,0.0001126929,0.0002268756,0.001497287,0.9463563,0.0003596226,0.02954319,0.0002887598],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9901282,0.001325341,0.0005835283,0.0008241124,0.00008510342,0.00005648469,0.0000730811,0.00001941731,0.006904778],"genre_scores_gemma":[0.9944513,0.0009380257,0.0001951585,0.0001189893,0.0004204999,0.000008333445,0.0005292813,0.00001566544,0.003322697],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.04667651,"threshold_uncertainty_score":0.6784706,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01203279389417765,"score_gpt":0.2641669390528795,"score_spread":0.2521341451587019,"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."}}