{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004650756,0.0007605583,0.00053865,0.002788148,0.0003748649,0.0008796553,0.0007620422,0.0005803865,0.003083277],"category_scores_gemma":[0.002855182,0.0002526613,0.0009758687,0.00171063,0.0004355772,0.002226797,0.0007583867,0.0006783602,0.0009673205],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004652836,"about_ca_system_score_gemma":0.0006165713,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001900318,"about_ca_topic_score_gemma":0.002570284,"domain_scores_codex":[0.9997498,0.00003794549,0.00001595831,0.00008722133,0.00007606768,0.00003297881],"domain_scores_gemma":[0.9985239,0.0009222311,0.0001274042,0.0001728979,0.0001983322,0.00005530129],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.001818409,0.0005114801,0.01211821,0.0004191633,0.0002148932,0.0008956745,0.0001253168,0.2941335,0.05749132,0.06161221,0.01073495,0.5599248],"study_design_scores_gemma":[0.00002668539,0.00006000481,0.0006161967,0.00001392285,0.00003287465,0.0001283754,0.00002033119,0.9272782,0.01005391,0.06058189,0.001173183,0.00001453552],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0980523,0.0003343838,0.887948,0.0002912152,0.00006431325,0.0001211038,0.002261947,0.007591805,0.003334981],"genre_scores_gemma":[0.8326049,0.0003395382,0.1621237,0.00008857227,0.00005154897,0.00007150242,0.002921318,0.0003364541,0.001462543],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.003083277,"threshold_uncertainty_score":0.01031464,"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."}}