{"id":"W4406016843","doi":"10.1038/s41467-024-55021-3","title":"π-PrimeNovo: an accurate and efficient non-autoregressive deep learning model for de novo peptide sequencing","year":2025,"lang":"en","type":"article","venue":"Nature Communications","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":25,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia","funders":"National Key Research and Development Program of China; Natural Sciences and Engineering Research Council of Canada; Fudan University; National Natural Science Foundation of China; Canada Research Chairs","keywords":"Autoregressive model; Computational biology; Deep learning; Computer science; Artificial intelligence; Machine learning; Biology; Econometrics; Mathematics","routes":{"ca_aff":true,"ca_fund":true,"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":[0.0003117248,0.0001252403,0.0001074106,0.00006390658,0.0004458901,0.00005381331,0.0005802813,0.0002799511,8.006745e-7],"category_scores_gemma":[0.0005433867,0.0001235966,0.00004370071,0.00008267502,0.00009876354,0.0000067402,0.0004029948,0.0005997957,7.43198e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005288158,"about_ca_system_score_gemma":0.0001714671,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000006885351,"about_ca_topic_score_gemma":0.0001301669,"domain_scores_codex":[0.9993266,0.00007176017,0.0001819573,0.0001698538,0.00005953993,0.0001902984],"domain_scores_gemma":[0.9986975,0.00008665796,0.0001146961,0.0008719701,0.0001736957,0.00005548885],"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":[0.0001285216,0.0001782857,0.008112419,0.0002029123,0.00023015,7.552005e-7,0.005250323,0.6901769,0.266216,0.01843062,0.001411352,0.009661766],"study_design_scores_gemma":[0.0003400776,0.00005131718,0.0008077222,0.00003262314,0.00003095486,0.000006834039,0.0002950074,0.9870554,0.003773555,0.0001310951,0.007342141,0.0001333282],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5835537,0.004543308,0.4021489,0.001387519,0.00009450272,0.0006526624,0.00003072107,0.00007479849,0.00751393],"genre_scores_gemma":[0.8893076,0.0001832771,0.1090192,0.0005365694,0.00002277679,0.00005572667,0.0002698489,0.00001429119,0.0005907248],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3057539,"threshold_uncertainty_score":0.5040121,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01326433473405014,"score_gpt":0.3327947280421421,"score_spread":0.3195303933080919,"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."}}