{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000792853,0.001397258,0.0006032323,0.0004233404,0.0002636158,0.0007807349,0.002103293,0.001647495,0.00981091],"category_scores_gemma":[0.002545811,0.0004396528,0.001301752,0.0003535941,0.0004535264,0.00134378,0.001183929,0.002532883,0.005117449],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006613929,"about_ca_system_score_gemma":0.001065512,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00508684,"about_ca_topic_score_gemma":0.009424446,"domain_scores_codex":[0.9996624,0.00009724197,0.00002021627,0.0001058604,0.00006918596,0.00004497493],"domain_scores_gemma":[0.9992645,0.0004236342,0.0000460304,0.00009990184,0.0001140664,0.00005187666],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0006350988,0.0002948138,0.001659123,0.0003312908,0.0001752714,0.0004997335,0.0001232755,0.4292213,0.022192,0.00946802,0.05832187,0.4770781],"study_design_scores_gemma":[0.00001298905,0.00006302897,0.00008932537,0.000007676494,0.00001321899,0.00002620044,0.000007481588,0.9919464,0.002823229,0.002801592,0.002201609,0.0000071902],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.03659341,0.001546819,0.9299416,0.001391161,0.0005834164,0.0002030729,0.002766952,0.02011481,0.006858675],"genre_scores_gemma":[0.4620412,0.001094328,0.4907137,0.002773671,0.000409571,0.0008131462,0.018084,0.001338522,0.02273193],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.00981091,"threshold_uncertainty_score":0.0328207,"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."}}