{"id":"W7101397496","doi":"10.5281/zenodo.17458967","title":"Zero-Shot Protein Segmentation (ZPS) Data and Embeddings","year":2025,"lang":"","type":"dataset","venue":"Zenodo (CERN European Organization for Nuclear Research)","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"SickKids Foundation; Hospital for Sick Children; University of Toronto","funders":"","keywords":"UniProt; Parsing; Segmentation; Human proteome project; Search engine indexing; Proteome; Human proteins; File format","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":[0.001294286,0.002463416,0.0009936781,0.003567693,0.0009831865,0.00223189,0.002402755,0.001705822,0.04860561],"category_scores_gemma":[0.006458913,0.0008012689,0.001701446,0.00473633,0.0006706013,0.002532973,0.003123763,0.002680488,0.07083176],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001669419,"about_ca_system_score_gemma":0.001492832,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005586263,"about_ca_topic_score_gemma":0.006278269,"domain_scores_codex":[0.997817,0.0001857994,0.0002453119,0.0006784734,0.0007930372,0.0002804043],"domain_scores_gemma":[0.9974463,0.0004126496,0.0001292294,0.00113693,0.0007368154,0.000138066],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","study_design_scores_codex":[0.000561181,0.0001398679,0.001586132,0.001222709,0.00006358016,0.000129555,0.0001072381,0.001331507,0.005192324,0.002699706,0.9599139,0.02705231],"study_design_scores_gemma":[0.0005266569,0.0003889507,0.01250882,0.0003562546,0.00008668207,0.0006322667,0.000527403,0.0173423,0.03843301,0.01127785,0.9177762,0.0001435369],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"dataset","genre_gemma":"dataset","genre_scores_codex":[0.005157483,0.0001966359,0.004508328,0.0001446717,0.0001979945,0.0001290372,0.9563128,0.02918691,0.004166155],"genre_scores_gemma":[0.003263327,0.00005243943,0.004654504,0.0000383726,0.000009431345,0.0001428512,0.9895705,0.001212117,0.001056511],"genre_candidate":"dataset","genre_consensus":"dataset","teacher_disagreement_score":0.04860561,"threshold_uncertainty_score":0.1626019,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02744503348056311,"score_gpt":0.2919406257354329,"score_spread":0.2644955922548698,"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."}}