{"id":"W4361279726","doi":"10.21203/rs.3.rs-2593528/v1","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":"preprint","venue":"Research Square","topic":"vaccines and immunoinformatics approaches","field":"Biochemistry, Genetics and Molecular Biology","cited_by":11,"is_retracted":false,"has_abstract":false,"ca_institutions":"Bioinformatics Solutions (Canada); University of Waterloo","funders":"","keywords":"Fragmentation (computing); Graph; Computer science; Computational biology; Artificial intelligence; Biology; 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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001457994,0.000856187,0.001070984,0.0006935291,0.0004444056,0.0007548922,0.002303706,0.002108223,0.002121242],"category_scores_gemma":[0.003655466,0.0008323237,0.0007823555,0.0007209895,0.0008143752,0.001997931,0.001708573,0.002610239,0.0004837218],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008683839,"about_ca_system_score_gemma":0.001906573,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.007845683,"about_ca_topic_score_gemma":0.01240908,"domain_scores_codex":[0.999616,0.0001090969,0.00001761639,0.0001130408,0.00007943453,0.00006464661],"domain_scores_gemma":[0.9976633,0.001538517,0.0001701256,0.0002151258,0.0002927374,0.0001203818],"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":[0.0002364862,0.0001480607,0.0009308423,0.0000978043,0.00007813971,0.00009633538,0.0000429547,0.8940516,0.003897351,0.008371843,0.001988323,0.09006034],"study_design_scores_gemma":[0.000004222446,0.00001024255,0.0000323584,0.000002077157,0.000004062318,0.000004861351,0.000001418287,0.9961219,0.0003449839,0.003405778,0.00006623488,0.000001833429],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.03906617,0.0003865143,0.9582447,0.0004808991,0.00004618626,0.00003409015,0.0001388636,0.0007995319,0.0008030295],"genre_scores_gemma":[0.7078713,0.0003824536,0.2836716,0.0005731518,0.00009085728,0.000135621,0.0007465783,0.0002611965,0.006267168],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.007845683,"threshold_uncertainty_score":0.01560003,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.07056530426285422,"score_gpt":0.3603553875013776,"score_spread":0.2897900832385234,"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."}}