{"id":"W4414563674","doi":"10.1109/tcbbio.2025.3614457","title":"SeqDA-HLA: Language Model and Dual Attention-Based Network to Predict Peptide-HLA Class I Binding","year":2025,"lang":"en","type":"article","venue":"IEEE Transactions on Computational Biology and Bioinformatics","topic":"vaccines and immunoinformatics approaches","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"National Research Foundation of Korea","keywords":"Interpretability; Pairwise comparison; Benchmark (surveying); Class (philosophy); Dual (grammatical number); Language model; Flexibility (engineering); Key (lock)","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":[0.0006792293,0.001202451,0.0007724076,0.000888581,0.0003318742,0.0006032449,0.001294626,0.0008308807,0.002505039],"category_scores_gemma":[0.001942543,0.0003213713,0.0008278248,0.0005660596,0.0002918171,0.001377256,0.001252957,0.001432794,0.0009659762],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006989254,"about_ca_system_score_gemma":0.0008291249,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.008134197,"about_ca_topic_score_gemma":0.01442671,"domain_scores_codex":[0.9996862,0.00008527647,0.00001587427,0.0001240606,0.00004724119,0.0000413709],"domain_scores_gemma":[0.9994709,0.000297548,0.00004931702,0.00004447416,0.00009741147,0.00004027012],"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":[0.0006772298,0.0005769828,0.01399962,0.0004042408,0.0005059747,0.0003697831,0.0001690972,0.4711019,0.02301283,0.005974404,0.02152402,0.461684],"study_design_scores_gemma":[0.00001139206,0.0000484741,0.0004007681,0.000006940546,0.00001980253,0.00003500901,0.00001082629,0.9946033,0.001172629,0.002721234,0.0009606591,0.000008972675],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.162058,0.004981776,0.8091942,0.001495284,0.0005234616,0.0001898659,0.005110234,0.01061549,0.005831684],"genre_scores_gemma":[0.8353033,0.0009646273,0.1457273,0.001075022,0.0002381739,0.0003229754,0.007597167,0.0003242354,0.008447103],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.008134197,"threshold_uncertainty_score":0.01617366,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.009316485310543009,"score_gpt":0.2513189397927815,"score_spread":0.2420024544822385,"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."}}