{"id":"W4406644944","doi":"10.21203/rs.3.rs-5429797/v1","title":"Proteoform Search from Protein Database with Top-Down Mass Spectra: Algorithms and Evaluation","year":2025,"lang":"en","type":"preprint","venue":"Research Square","topic":"Advanced Proteomics Techniques and Applications","field":"Chemistry","cited_by":0,"is_retracted":false,"has_abstract":false,"ca_institutions":"Bioinformatics Solutions (Canada); University of Waterloo","funders":"National Natural Science Foundation of China; City University of Hong Kong; National Science Foundation","keywords":"Computer science; Database; Spectral line; Algorithm; Information retrieval; Chemistry; Physics","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":[0.001987667,0.001807972,0.001326345,0.003359978,0.001054518,0.001402867,0.001545864,0.001209667,0.002717171],"category_scores_gemma":[0.003950394,0.0003177923,0.001356275,0.002866737,0.0003091166,0.001217094,0.001270493,0.0006298862,0.00201065],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007120835,"about_ca_system_score_gemma":0.001647953,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004424337,"about_ca_topic_score_gemma":0.004817053,"domain_scores_codex":[0.9991786,0.0001371272,0.0000854416,0.0002032964,0.0002959488,0.00009956588],"domain_scores_gemma":[0.9987323,0.0005339049,0.00007911961,0.0002344773,0.0003405559,0.00007967379],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.007841226,0.001901052,0.02749755,0.002173536,0.001350612,0.0007292836,0.000219956,0.04686893,0.0713755,0.003379261,0.05171666,0.7849464],"study_design_scores_gemma":[0.0005701334,0.0005510784,0.01434347,0.0000624789,0.0004795142,0.001311149,0.0002212894,0.9270154,0.04259029,0.00521755,0.007578069,0.00005962568],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"methods","genre_scores_codex":[0.5669562,0.006856333,0.3566049,0.000642466,0.0002600604,0.0009535844,0.01978435,0.04280411,0.005138017],"genre_scores_gemma":[0.3268183,0.001694295,0.6129398,0.0002870305,0.00007429816,0.0004984051,0.05378675,0.00101388,0.002887205],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.004424337,"threshold_uncertainty_score":0.01051193,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06226527210188592,"score_gpt":0.4171100315547648,"score_spread":0.3548447594528789,"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."}}