{"id":"W4408339030","doi":"10.1101/2025.03.05.641584","title":"Zero-shot segmentation using embeddings from a protein language model identifies functional regions in the human proteome","year":2025,"lang":"en","type":"preprint","venue":"bioRxiv (Cold Spring Harbor Laboratory)","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"Hospital for Sick Children; University of Toronto","funders":"","keywords":"Proteome; Computational biology; Human proteome project; Segmentation; Zero (linguistics); Computer science; Shot (pellet); Artificial intelligence; Natural language processing; Biology; Chemistry; Proteomics; Bioinformatics; Linguistics; 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":[0.0005483017,0.0005040954,0.0003992266,0.0008883477,0.0002935749,0.0005882145,0.0004937549,0.0007385968,0.001082753],"category_scores_gemma":[0.001852358,0.0002055322,0.0007593271,0.0005241043,0.0005464819,0.001148712,0.0008766932,0.0006975842,0.0005055021],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005318951,"about_ca_system_score_gemma":0.0005289241,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002390918,"about_ca_topic_score_gemma":0.002240145,"domain_scores_codex":[0.9996377,0.00008796114,0.00001956205,0.0001325658,0.00006500747,0.00005717635],"domain_scores_gemma":[0.9991601,0.0004208173,0.0001186223,0.00009368594,0.0001464785,0.00006026104],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.002907364,0.0005513023,0.04127283,0.0007529867,0.0002732056,0.001568779,0.001086053,0.3868311,0.2542235,0.01931926,0.009201137,0.2820125],"study_design_scores_gemma":[0.0000135712,0.00009119674,0.002399978,0.00001075003,0.00001252461,0.0001221245,0.0001050528,0.9800167,0.01193947,0.004489877,0.000783549,0.00001521389],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.720517,0.0003780587,0.2730821,0.0003364345,0.00006344643,0.00005747273,0.001272678,0.002909737,0.001383048],"genre_scores_gemma":[0.9138134,0.0001136886,0.08091637,0.00009103478,0.00001726967,0.0000477078,0.0039169,0.0002195806,0.0008639912],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.002390918,"threshold_uncertainty_score":0.004754007,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02175423891401078,"score_gpt":0.2732539982848037,"score_spread":0.2514997593707929,"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."}}