{"id":"W4414090146","doi":"10.1101/2025.09.08.674958","title":"A novel Vector-Symbolic Architecture for graph encoding and its application to viral pangenome-based species classification","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":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"ENCODE; Representation (politics); Encoding (memory); Graph; Genome; Pattern recognition (psychology); Sequence (biology); Architecture","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":[0.0004575952,0.0008728477,0.0005962455,0.001541042,0.0006373291,0.001485203,0.001153538,0.0007879031,0.003172236],"category_scores_gemma":[0.003223166,0.0002881764,0.001065714,0.002017797,0.0007392213,0.00242895,0.0009979527,0.001205615,0.0009710717],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00129272,"about_ca_system_score_gemma":0.001269409,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.008185308,"about_ca_topic_score_gemma":0.007170002,"domain_scores_codex":[0.9994986,0.0001046686,0.00005352787,0.0001524405,0.0001442554,0.00004649935],"domain_scores_gemma":[0.9989592,0.0003718958,0.00009599054,0.0002081358,0.0003041203,0.00006066405],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0003468685,0.0001542485,0.002987872,0.0003877629,0.00008413196,0.0002782037,0.0004596125,0.2738762,0.03201436,0.08215867,0.008250848,0.5990012],"study_design_scores_gemma":[0.00001099403,0.00005104828,0.0002081063,0.00002635234,0.00001487175,0.00006547252,0.00004703447,0.9587068,0.004607498,0.0320002,0.004244104,0.00001736681],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.02309157,0.0002813726,0.969398,0.0003315562,0.00008431098,0.00008569586,0.0006663314,0.004479019,0.001582145],"genre_scores_gemma":[0.2171544,0.0004140257,0.7763914,0.000198287,0.00005424634,0.0002206011,0.002521934,0.000394031,0.002650941],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.008185308,"threshold_uncertainty_score":0.01627529,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01340911375852166,"score_gpt":0.2393449661134086,"score_spread":0.225935852354887,"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."}}