{"id":"W4394988401","doi":"10.1101/2024.04.16.589668","title":"NovoBoard: a comprehensive framework for evaluating the false discovery rate and accuracy of de novo peptide sequencing","year":2024,"lang":"en","type":"preprint","venue":"bioRxiv (Cold Spring Harbor Laboratory)","topic":"Advanced Proteomics Techniques and Applications","field":"Chemistry","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo; Bioinformatics Solutions (Canada)","funders":"","keywords":"False discovery rate; Computational biology; Benchmark (surveying); Computer science; Set (abstract data type); Proteomics; Peptide; DNA sequencing; Biology; Data mining; Genetics; DNA; Biochemistry; Gene","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":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.04456626,0.003730515,0.002801874,0.009544268,0.001000579,0.00381695,0.00471481,0.002607846,0.001223692],"category_scores_gemma":[0.07947768,0.001107496,0.002252953,0.003207637,0.001676232,0.003248001,0.002996241,0.002451368,0.000555183],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002588066,"about_ca_system_score_gemma":0.003785233,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005333561,"about_ca_topic_score_gemma":0.00548328,"domain_scores_codex":[0.9767883,0.01090125,0.002101422,0.002841816,0.006713786,0.0006533923],"domain_scores_gemma":[0.9371474,0.04221154,0.007200298,0.004652152,0.00771005,0.001078592],"domain_codex":null,"domain_gemma":"methods","domain_candidate":"methods","domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.001902645,0.0005586884,0.02801021,0.001577181,0.002432954,0.0005473996,0.0002494433,0.5922415,0.02143774,0.03162879,0.01337365,0.3060398],"study_design_scores_gemma":[0.00007707422,0.0002753485,0.002670922,0.0001025686,0.0001718561,0.0002287935,0.00002741473,0.9650565,0.01033819,0.01733608,0.003593037,0.0001221807],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.009223279,0.001244975,0.9812813,0.0001537193,0.00005806064,0.0001684022,0.001128678,0.006266167,0.0004753674],"genre_scores_gemma":[0.1334423,0.0005497782,0.8615281,0.0002099957,0.00009825755,0.0004623367,0.002456294,0.0008089729,0.0004439482],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9554337,"threshold_uncertainty_score":0.2356917,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03850165146694528,"score_gpt":0.3202244891070318,"score_spread":0.2817228376400865,"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."}}