{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001289968,0.0009614986,0.001117848,0.0007096018,0.000488126,0.0006923474,0.002541817,0.001795462,0.001646776],"category_scores_gemma":[0.002995561,0.0006970702,0.0008058405,0.000685316,0.000724773,0.001957537,0.001684445,0.002397105,0.0004368201],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007809786,"about_ca_system_score_gemma":0.002109425,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.009585579,"about_ca_topic_score_gemma":0.01678795,"domain_scores_codex":[0.9996549,0.00008875025,0.00001679139,0.0001036703,0.0000717135,0.00006419462],"domain_scores_gemma":[0.9983754,0.001019909,0.0001204983,0.0001430743,0.0002538835,0.00008733382],"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":[0.0002850387,0.0002210769,0.001469002,0.0001319186,0.0001072558,0.0001334125,0.00006223837,0.8446994,0.005627607,0.007985075,0.002611046,0.1366671],"study_design_scores_gemma":[0.000004209176,0.00001374768,0.00004239045,0.000002315852,0.000005653634,0.000006547213,0.000002046824,0.9970108,0.0003766648,0.002454078,0.00007907089,0.000002390151],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.05458549,0.0006227843,0.9419196,0.0005337604,0.00006047309,0.00004487803,0.0001524701,0.001051511,0.001029094],"genre_scores_gemma":[0.756807,0.0004711195,0.2362919,0.0006205126,0.00008423979,0.0001211618,0.0007534728,0.0001972639,0.004653347],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.009585579,"threshold_uncertainty_score":0.0190596,"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."}}