{"id":"W4393981121","doi":"10.1038/s42256-024-00816-8","title":"Tandem mass spectrum prediction for small molecules using graph transformers","year":2024,"lang":"en","type":"article","venue":"Nature Machine Intelligence","topic":"Metabolomics and Mass Spectrometry Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":70,"is_retracted":false,"has_abstract":false,"ca_institutions":"University Health Network; Vector Institute; University of Toronto","funders":"Natural Sciences and Engineering Research Council of Canada; Canadian Institutes of Health Research; Canadian Institute for Advanced Research; Vector Institute; Canada Research Chairs; University Health Network","keywords":"Computer science; Leverage (statistics); Tandem; Tandem mass spectrometry; Mass spectrum; Transformer; Graph; Spectral line; Collision; Pattern recognition (psychology); Biological system; Artificial intelligence; Fragmentation (computing); Mass spectrometry; Data mining; Algorithm; Theoretical computer science; Chemistry; Materials science; Physics","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":[0.0002270208,0.0002254286,0.0001794181,0.0001416605,0.0001175432,0.00005644218,0.0001770432,0.0002874012,0.00001957393],"category_scores_gemma":[0.00007064647,0.0001915607,0.00022344,0.0002608138,0.00006432541,0.000005243974,0.00003365595,0.0003334603,0.000002206933],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002620242,"about_ca_system_score_gemma":0.00005096558,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001889002,"about_ca_topic_score_gemma":0.00007164985,"domain_scores_codex":[0.9988344,0.00002133856,0.0002325849,0.0004857098,0.0001224769,0.0003035186],"domain_scores_gemma":[0.9996502,0.00002692104,0.0000373383,0.0001687539,0.00005476724,0.00006196115],"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":[0.0001583,0.00005646649,0.0006862532,0.0002025344,0.0005479793,0.00001179837,0.00007865241,0.00115926,0.9581457,0.02067954,0.0008431104,0.01743044],"study_design_scores_gemma":[0.0001746991,0.0004811498,0.0001677014,0.00005860633,0.0001658897,0.00004766268,0.00009295611,0.02808366,0.8687059,0.01602286,0.08557398,0.0004249296],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.03423081,0.03738615,0.9245232,0.0005580998,0.001284386,0.0003974806,0.0002344136,0.00005684041,0.001328558],"genre_scores_gemma":[0.9854994,0.003172911,0.01013483,0.0001923643,0.0004926008,0.00002980373,0.0001472364,0.00004031722,0.0002904999],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9512686,"threshold_uncertainty_score":0.7811619,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01201127640054414,"score_gpt":0.2792427210405481,"score_spread":0.267231444640004,"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."}}