{"id":"W4410288329","doi":"10.34133/research.0721","title":"S <sup>2</sup> ALM: Sequence-Structure Pre-trained Large Language Model for Comprehensive Antibody Representation Learning","year":2025,"lang":"en","type":"article","venue":"Research","topic":"Monoclonal and Polyclonal Antibodies Research","field":"Medicine","cited_by":7,"is_retracted":false,"has_abstract":true,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"","keywords":"Sequence (biology); Computer science; Representation (politics); Artificial intelligence; Natural language processing; Sequence learning; Chemistry; Political science; Biochemistry","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008085232,0.0002094084,0.0004226915,0.000540196,0.0005975226,0.00008533365,0.0002978072,0.0002051388,0.000233606],"category_scores_gemma":[0.000959406,0.0001723011,0.0001849838,0.0008583529,0.0002585665,0.0001250857,0.0002900125,0.00117656,0.00003937912],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001451195,"about_ca_system_score_gemma":0.0005364392,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0003740875,"about_ca_topic_score_gemma":0.00002993201,"domain_scores_codex":[0.9966346,0.0003392468,0.0003385441,0.0006078215,0.001071748,0.001008057],"domain_scores_gemma":[0.9974073,0.000873888,0.00004345808,0.0004368283,0.001003301,0.000235199],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.006614306,0.0005178663,0.03830897,0.003406417,0.0007317505,0.0003787234,0.01285062,0.01616112,0.8467972,0.01471238,0.03918708,0.02033357],"study_design_scores_gemma":[0.002454388,0.0003712798,0.006321829,0.0002843761,0.00003814529,0.00003476778,0.00296938,0.9567157,0.01132699,0.001691789,0.01760092,0.0001904366],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9832878,0.000965144,0.004168019,0.004629948,0.00004330221,0.001780363,0.0002474563,0.0001304666,0.004747574],"genre_scores_gemma":[0.9307535,0.0002753692,0.001994527,0.0003074572,0.0002589397,0.00009633796,0.001089045,0.0000340611,0.06519074],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9405546,"threshold_uncertainty_score":0.7026236,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1171747083553692,"score_gpt":0.4948905315855291,"score_spread":0.37771582323016,"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."}}