{"id":"W4382937982","doi":"10.21203/rs.3.rs-3083229/v1","title":"Anchor Clustering for million-scale immune repertoire sequencing data","year":2023,"lang":"en","type":"preprint","venue":"Research Square","topic":"vaccines and immunoinformatics approaches","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Guelph","funders":"University of Guelph","keywords":"Cluster analysis; Repertoire; Pairwise comparison; Single-linkage clustering; Computer science; Correlation clustering; CURE data clustering algorithm; Consensus clustering; Data mining; Computational biology; Artificial intelligence; 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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002598605,0.0008405641,0.0009540775,0.004889761,0.0009502098,0.001211886,0.001341697,0.001244341,0.002386142],"category_scores_gemma":[0.01076868,0.0003987973,0.001190433,0.005429185,0.0005725512,0.0009629971,0.001380502,0.001176414,0.0014584],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009239863,"about_ca_system_score_gemma":0.0009601405,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003713267,"about_ca_topic_score_gemma":0.004056561,"domain_scores_codex":[0.9979194,0.0006275041,0.0001613372,0.0005676076,0.000582774,0.0001414142],"domain_scores_gemma":[0.9946709,0.002344256,0.000513739,0.001334678,0.0009366599,0.0001997549],"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":[0.001749283,0.000624155,0.04761228,0.001184499,0.001015173,0.000868527,0.0009620413,0.4860014,0.08295169,0.01131739,0.01622765,0.3494858],"study_design_scores_gemma":[0.00005874628,0.0001284531,0.01484329,0.0000375978,0.00006097495,0.0002901452,0.0002882664,0.9284112,0.02349463,0.02421913,0.008095185,0.00007234521],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.3269399,0.0009876513,0.6523446,0.0003285509,0.0001570953,0.0002928491,0.009603959,0.007802451,0.001542888],"genre_scores_gemma":[0.4404505,0.0002935893,0.5366558,0.0000794277,0.00006323494,0.0004254604,0.02028261,0.0006589754,0.001090395],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.004889761,"threshold_uncertainty_score":0.01374286,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1866787123305273,"score_gpt":0.4017514002363556,"score_spread":0.2150726879058283,"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."}}