{"id":"W2947888846","doi":"10.1038/s41592-019-0428-5","title":"Deep learning adds an extra dimension to peptide fragmentation","year":2019,"lang":"en","type":"letter","venue":"Nature Methods","topic":"Advanced Proteomics Techniques and Applications","field":"Chemistry","cited_by":11,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Fragmentation (computing); Tandem mass spectrometry; Proteomics; Deep learning; Peptide; Computer science; Tandem; Computational biology; Artificial intelligence; Mass spectrometry; Chemistry; Biology; Materials science; Chromatography; Biochemistry","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":[0.001901324,0.0006368889,0.0007215153,0.0004067634,0.0008730607,0.002656048,0.0008509735,0.008349811,0.005649816],"category_scores_gemma":[0.009144353,0.0004254023,0.0004371289,0.0003614457,0.002258134,0.002805702,0.00125229,0.01306916,0.005116248],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001454193,"about_ca_system_score_gemma":0.0007213868,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0009467386,"about_ca_topic_score_gemma":0.001865572,"domain_scores_codex":[0.9990607,0.0002138298,0.00005339799,0.0001253057,0.0004430846,0.0001038417],"domain_scores_gemma":[0.9958836,0.00295778,0.0001396852,0.0002370307,0.000522704,0.0002590444],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0003142188,0.0000873429,0.0004433173,0.0003149736,0.00004999301,0.0007647399,0.00005125285,0.001944846,0.005134076,0.05113283,0.7456188,0.1941435],"study_design_scores_gemma":[0.0002053792,0.0001489831,0.0004565632,0.0001590258,0.00003341127,0.001066404,0.00003964933,0.03667764,0.01065351,0.2377914,0.7126849,0.00008318695],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"commentary","genre_gemma":"methods","genre_scores_codex":[0.003372426,0.01193644,0.05908389,0.8401755,0.0606215,0.00005636486,0.0004913402,0.0009830161,0.02327951],"genre_scores_gemma":[0.1097644,0.01800755,0.0503341,0.5787464,0.12551,0.0003837873,0.0005240075,0.0005389944,0.1161908],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.008349811,"threshold_uncertainty_score":0.01890045,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01803864559162903,"score_gpt":0.3876140123870884,"score_spread":0.3695753667954593,"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."}}