{"id":"W4387773470","doi":"10.1038/s42256-023-00738-x","title":"Mitigating the missing-fragmentation problem in de novo peptide sequencing with a two-stage graph-based deep learning model","year":2023,"lang":"en","type":"article","venue":"Nature Machine Intelligence","topic":"Advanced Proteomics Techniques and Applications","field":"Chemistry","cited_by":37,"is_retracted":false,"has_abstract":false,"ca_institutions":"Bioinformatics Solutions (Canada); University of Waterloo","funders":"","keywords":"Fragmentation (computing); Tandem mass spectrometry; Deep learning; Peptide; Computer science; Computational biology; Graph; Recurrent neural network; Artificial neural network; Artificial intelligence; Biology; Chemistry; Mass spectrometry; Biochemistry; Theoretical computer science","routes":{"ca_aff":true,"ca_fund":false,"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":[0.000345948,0.0001896053,0.0001283878,0.00009731469,0.0002712205,0.00005921628,0.0003227656,0.0001419959,0.00002924329],"category_scores_gemma":[0.0001064633,0.0001462339,0.00005070899,0.0006901698,0.00007872967,0.00008898845,0.00005340716,0.001522351,0.000003949026],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000206725,"about_ca_system_score_gemma":0.0000987122,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001584822,"about_ca_topic_score_gemma":0.0002439334,"domain_scores_codex":[0.9988185,0.00002743259,0.0002683765,0.0003429419,0.0002124763,0.0003302554],"domain_scores_gemma":[0.9992474,0.000193268,0.0001700361,0.0002689741,0.00006643496,0.00005382855],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00002506546,0.00001314112,0.003002002,0.00008331746,0.000005936416,0.0000146266,0.0006223129,0.8527177,0.1314671,0.00291019,0.000002971246,0.0091356],"study_design_scores_gemma":[0.0001050889,0.00001094516,0.0000103981,0.0001749787,0.000006945254,0.000009734427,0.0003788002,0.7076183,0.2740036,0.01746249,0.00006725252,0.0001515351],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2339933,0.000132729,0.7623653,0.0007421615,0.000005098055,0.0002660754,0.00001314233,0.0003594096,0.002122793],"genre_scores_gemma":[0.7842521,0.00002552259,0.214866,0.000246063,0.00002284474,0.0002227024,0.00006790801,0.00003438771,0.0002624951],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.5502588,"threshold_uncertainty_score":0.6613943,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01281514757924118,"score_gpt":0.308552899223441,"score_spread":0.2957377516441998,"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."}}