{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00237665,0.0002442933,0.000201964,0.0002354346,0.0003910413,0.0002830657,0.00040585,0.0002032397,0.000004274349],"category_scores_gemma":[0.0002569009,0.0001862589,0.0001023549,0.0003428466,0.0000971924,0.00001086168,0.0005271651,0.001381266,0.000002980051],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002196996,"about_ca_system_score_gemma":0.0008997428,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000610659,"about_ca_topic_score_gemma":0.0005764487,"domain_scores_codex":[0.9976537,0.0003612827,0.0003786722,0.0004331727,0.0005112768,0.0006618435],"domain_scores_gemma":[0.9989061,0.00009722877,0.0001787238,0.0004805939,0.0002545933,0.00008272411],"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":[0.00008593722,0.00002196508,0.00710353,0.001032313,0.00004621736,0.00001128161,0.001916462,0.9407869,0.04765857,0.00004966801,0.00001909751,0.001268046],"study_design_scores_gemma":[0.001006273,0.0002180576,0.0007891973,0.001322835,0.00001361051,0.000006977298,0.009122846,0.970029,0.01600795,0.001096161,0.00006393935,0.0003231804],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9519746,0.00037051,0.04558014,0.000436027,0.00001456518,0.0009936165,0.0000210783,0.00003504227,0.0005744417],"genre_scores_gemma":[0.9715828,0.0001319431,0.02668635,0.00005117893,0.00007108576,0.0003860624,0.000658654,0.00007435388,0.0003575381],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.03165062,"threshold_uncertainty_score":0.7595419,"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."}}