{"id":"W4414777573","doi":"10.1038/s43588-025-00880-z","title":"Proteoform search from protein database with top-down mass spectra","year":2025,"lang":"en","type":"article","venue":"Nature Computational Science","topic":"Advanced Proteomics Techniques and Applications","field":"Chemistry","cited_by":0,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Waterloo; Bioinformatics Solutions (Canada)","funders":"Canadian Network for Research and Innovation in Machining Technology, Natural Sciences and Engineering Research Council of Canada; Natural Sciences and Engineering Research Council of Canada; National Natural Science Foundation of China","keywords":"Deconvolution; Pipeline (software); Identification (biology); Graph; Basis (linear algebra); Search algorithm","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":[0.0001715236,0.0001158578,0.00009065864,0.00008259397,0.0003584806,0.00009455022,0.0005654888,0.00009066236,0.0001330744],"category_scores_gemma":[0.00005981289,0.00009508074,0.00002133837,0.0008141014,0.0002215394,0.0002352259,0.0001256189,0.0005859591,0.000009196852],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002664874,"about_ca_system_score_gemma":0.0004974719,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005578245,"about_ca_topic_score_gemma":0.000007825148,"domain_scores_codex":[0.9986226,0.000004657185,0.0001351602,0.0004833368,0.000506593,0.0002476398],"domain_scores_gemma":[0.9992392,0.00007453133,0.00005377324,0.0003166539,0.0002414732,0.00007434063],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.00006554802,0.00009098178,0.001602264,0.00004976849,0.00001251963,0.000007224503,0.00004296922,0.004195482,0.8026556,0.1851722,0.0001520023,0.005953408],"study_design_scores_gemma":[0.0002702405,0.00001413144,0.0006123536,0.0001371891,0.000004852862,0.000002894887,0.00002446772,0.01357355,0.8681682,0.1148912,0.002123502,0.0001774702],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2625386,0.00008354418,0.7218292,0.003133367,0.00001946777,0.000616262,0.000168912,0.0001843651,0.01142623],"genre_scores_gemma":[0.5673742,0.000001214917,0.4318853,0.0001314943,0.00003637717,0.0001292892,0.00007782203,0.000004769042,0.0003594763],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.3048356,"threshold_uncertainty_score":0.387728,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.006857039943264111,"score_gpt":0.3020115019358871,"score_spread":0.295154461992623,"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."}}