{"id":"W4416113856","doi":"10.1371/journal.pcbi.1012929","title":"Zero-shot segmentation using embeddings from a protein language model identifies functional regions in the human proteome","year":2025,"lang":"en","type":"article","venue":"PLoS Computational Biology","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"Hospital for Sick Children; University of Toronto","funders":"Canadian Institutes of Health Research; Canada Foundation for Innovation; Natural Sciences and Engineering Research Council of Canada; Canada Research Chairs","keywords":"UniProt; Human proteome project; Proteome; Categorization; Protein function prediction; Protein domain; Proteomics; Protein family; Annotation; Function (biology)","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":[0.0001736365,0.0001231113,0.0001116449,0.0001077502,0.0001658756,0.00003755566,0.000187442,0.0001179374,0.00001552166],"category_scores_gemma":[0.0001028179,0.0001021778,0.00004871469,0.0001333836,0.00009574603,0.000009284433,0.00009432871,0.0001577858,0.000005507135],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002999182,"about_ca_system_score_gemma":0.00008932,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000730254,"about_ca_topic_score_gemma":0.00002985606,"domain_scores_codex":[0.9991034,0.0001325551,0.000277484,0.0002255724,0.0001148984,0.0001460562],"domain_scores_gemma":[0.9995873,0.00004938361,0.0001177477,0.0001565641,0.00007298302,0.00001603976],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00003421585,0.00008324216,0.003361884,0.00002667462,0.00006776572,8.960108e-7,0.0006346228,0.1120353,0.8762726,0.007038772,0.0003747952,0.00006931523],"study_design_scores_gemma":[0.001673511,0.0001723941,0.01199699,0.0001262832,0.00006328914,0.00001339146,0.0009595542,0.8576242,0.04177424,0.08486998,0.0002785476,0.000447637],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8355407,0.00005306994,0.1631247,0.0003482792,0.00003627436,0.0004144157,0.00004566853,0.00001506613,0.0004218621],"genre_scores_gemma":[0.9790887,0.000001076362,0.01749459,0.0006694857,0.00006395522,0.0001056367,0.002334567,0.000008077036,0.0002339631],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8344983,"threshold_uncertainty_score":0.4166689,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03058763592084477,"score_gpt":0.3211175182554487,"score_spread":0.2905298823346039,"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."}}