{"id":"W4409586142","doi":"10.21203/rs.3.rs-6255613/v1","title":"A machine learning framework to identify complex physicochemical features of B cell epitopes","year":2025,"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":false,"ca_institutions":"University of Alberta","funders":"Natural Sciences and Engineering Research Council of Canada; National Institute of Allergy and Infectious Diseases; Canadian Institutes of Health Research; National Institutes of Health","keywords":"Epitope; Computational biology; Computer science; Chemistry; Artificial intelligence; Biology; Immunology; Antigen","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":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0006400935,0.0002810482,0.0004235029,0.0002199002,0.0001469474,0.0001139908,0.000868206,0.0005167047,0.00004368005],"category_scores_gemma":[0.0006489017,0.0002614872,0.0002746176,0.000293577,0.00008183542,0.000003208094,0.003551057,0.001559195,0.00001533835],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003563286,"about_ca_system_score_gemma":0.0002245374,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000179065,"about_ca_topic_score_gemma":0.000008941,"domain_scores_codex":[0.9978606,0.0002257524,0.0003978277,0.0004991548,0.0005282529,0.0004884397],"domain_scores_gemma":[0.9982491,0.0001045454,0.0001329567,0.0008808997,0.0005039638,0.0001285348],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0004116358,0.0004269338,0.001977833,0.006105658,0.0002967663,0.000003312436,0.001105986,0.002312082,0.9596208,0.000846818,0.02043803,0.006454134],"study_design_scores_gemma":[0.0007077642,0.0008137725,0.01458777,0.001907588,0.00005507654,0.000004198241,0.001308362,0.001392298,0.9231421,0.002802471,0.0524713,0.0008073056],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9604711,0.01086391,0.005670817,0.001055585,0.0003159243,0.002206717,0.0007524868,0.0000538813,0.0186096],"genre_scores_gemma":[0.9880543,0.001081866,0.006647554,0.00006736362,0.000287907,0.0001156518,0.001396952,0.00003139548,0.002316982],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.03647871,"threshold_uncertainty_score":0.9999837,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04415705445527994,"score_gpt":0.3880488878787035,"score_spread":0.3438918334234235,"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."}}