{"id":"W4408291802","doi":"10.1021/acs.jproteome.4c00943","title":"<scp>Proteoform-predictor</scp>: Increasing the Phylogenetic Reach of Top-Down Proteomics","year":2025,"lang":"en","type":"article","venue":"Journal of Proteome Research","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Manitoba; Children's Hospital Research Institute of Manitoba","funders":"National Cancer Institute; Division of Cancer Prevention, National Cancer Institute; National Institute of General Medical Sciences; Northwestern University","keywords":"Proteomics; Computational biology; Biology; Bioinformatics; Genetics; 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":[],"consensus_categories":[],"category_scores_codex":[0.004772809,0.002930684,0.00162017,0.003473958,0.001020711,0.003414336,0.00313982,0.001967636,0.01628123],"category_scores_gemma":[0.01002693,0.001236455,0.001622009,0.00302558,0.001093946,0.00442323,0.004387378,0.003845613,0.01756715],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009864499,"about_ca_system_score_gemma":0.001902431,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001647454,"about_ca_topic_score_gemma":0.002351586,"domain_scores_codex":[0.9968419,0.000454366,0.0002816497,0.000673868,0.001491876,0.0002563559],"domain_scores_gemma":[0.9939994,0.002017709,0.0007353066,0.001124408,0.00132911,0.0007941538],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.001109418,0.0002331123,0.006651375,0.002369907,0.0003884131,0.00114656,0.0003394464,0.002016539,0.07456048,0.009223641,0.6937171,0.208244],"study_design_scores_gemma":[0.0005202161,0.000383922,0.01456455,0.0006450824,0.0002131986,0.002183804,0.0001235289,0.06680389,0.1473149,0.02884831,0.7379643,0.0004343204],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"software","genre_gemma":"methods","genre_scores_codex":[0.02184791,0.003722419,0.3091103,0.0081847,0.002341631,0.0005349793,0.04186512,0.5909877,0.02140524],"genre_scores_gemma":[0.07975747,0.003902923,0.6439247,0.007841693,0.001565974,0.0009724607,0.1657828,0.08127167,0.01498028],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.01628123,"threshold_uncertainty_score":0.05446607,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02747077814542674,"score_gpt":0.3248899132684941,"score_spread":0.2974191351230674,"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."}}