{"id":"W4398160571","doi":"10.1101/2024.05.17.594647","title":"<i>π</i> -PrimeNovo: An Accurate and Efficient Non-Autoregressive Deep Learning Model for De Novo Peptide Sequencing","year":2024,"lang":"en","type":"preprint","venue":"bioRxiv (Cold Spring Harbor Laboratory)","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia","funders":"","keywords":"Autoregressive model; Computational biology; Deep learning; Artificial intelligence; Computer science; STAR model; Machine learning; Biology; Econometrics; Autoregressive integrated moving average; Mathematics; Time series","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":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0009377337,0.0006896806,0.0004890723,0.0001857657,0.0002901636,0.0003936002,0.0005412612,0.0007811175,0.000003398163],"category_scores_gemma":[0.000444992,0.0007229225,0.0001757518,0.0001333551,0.0001493732,0.00001274644,0.001218979,0.00114663,0.0000111146],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002453882,"about_ca_system_score_gemma":0.0009652413,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001968628,"about_ca_topic_score_gemma":0.000005740899,"domain_scores_codex":[0.997188,0.0001046371,0.0005787814,0.001099698,0.0002660777,0.0007628424],"domain_scores_gemma":[0.9977864,0.00004224884,0.0004665046,0.0009542038,0.0004007913,0.0003498224],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00006006162,0.00003767314,0.0005803366,0.001033155,0.0001655996,0.00001676744,0.0001662881,0.2387217,0.7589508,0.0001723461,0.00008624149,0.000009051199],"study_design_scores_gemma":[0.0004673454,0.000166092,0.00049229,0.0003385345,0.000159718,3.129346e-7,0.00002048201,0.8348566,0.1618495,0.000007816735,0.00083154,0.0008097235],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8859608,0.001224206,0.1111768,0.00006696147,0.000384404,0.0008039172,0.0001513083,0.0001985185,0.00003316982],"genre_scores_gemma":[0.9434289,0.0001625841,0.05515036,0.0002444796,0.0004911037,0.0002528093,0.000007188783,0.000217135,0.00004547344],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.5971013,"threshold_uncertainty_score":0.9995222,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01098850987186952,"score_gpt":0.2501141174601321,"score_spread":0.2391256075882625,"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."}}