{"id":"W4411710436","doi":"10.1101/2025.06.20.660691","title":"MassNet: billion-scale AI-friendly mass spectral corpus enables robust <i>de novo</i> peptide sequencing","year":2025,"lang":"en","type":"preprint","venue":"bioRxiv (Cold Spring Harbor Laboratory)","topic":"Advanced Proteomics Techniques and Applications","field":"Chemistry","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia","funders":"Westlake University","keywords":"Scale (ratio); Environmentally friendly; Computer science; Computational biology; Biology; Geography; Cartography; Ecology","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":[0.001077498,0.001525527,0.0005660998,0.00185922,0.0007605532,0.001282735,0.002969502,0.00104412,0.006997129],"category_scores_gemma":[0.004553537,0.0007064534,0.0007760278,0.002014308,0.0007974238,0.003167722,0.002310548,0.001416576,0.005243374],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001320597,"about_ca_system_score_gemma":0.002013276,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.009519896,"about_ca_topic_score_gemma":0.01487447,"domain_scores_codex":[0.9994252,0.00006687309,0.00005426006,0.0002332796,0.0001620104,0.00005849799],"domain_scores_gemma":[0.9988652,0.0002584309,0.000104394,0.0003394698,0.0003216017,0.0001108138],"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":[0.001808135,0.0006066427,0.01011306,0.001570645,0.0002737694,0.001083724,0.0005655934,0.1053461,0.05294488,0.03803128,0.5091932,0.2784629],"study_design_scores_gemma":[0.0002254821,0.0002183185,0.003304373,0.00009825395,0.00007223563,0.0003263885,0.0001494784,0.772499,0.05125164,0.03406875,0.1376889,0.0000972541],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.1784511,0.00173027,0.3665899,0.002723437,0.001315057,0.0008047079,0.1856672,0.2395608,0.02315754],"genre_scores_gemma":[0.2647028,0.00078678,0.3228831,0.0007762482,0.0002316507,0.001224486,0.395814,0.005452245,0.008128711],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.009519896,"threshold_uncertainty_score":0.02340776,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01181141503754162,"score_gpt":0.2276951254003469,"score_spread":0.2158837103628052,"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."}}