{"id":"W4413105633","doi":"10.1101/2025.08.10.669533","title":"Multi-Modal Protein Representation Learning with CLASP","year":2025,"lang":"en","type":"preprint","venue":"bioRxiv (Cold Spring Harbor Laboratory)","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"Institute for Research in Immunology and Cancer; McGill University; Genome Canada; Mila - Quebec Artificial Intelligence Institute","funders":"Natural Sciences and Engineering Research Council of Canada; Alliance de recherche numérique du Canada","keywords":"Representation (politics); Modal; Computer science; Artificial intelligence; Political science; Materials science","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":[0.001790113,0.001443377,0.0009814117,0.001477144,0.0004924008,0.00110984,0.002425564,0.002198384,0.002434671],"category_scores_gemma":[0.003801488,0.0005796007,0.001323593,0.001580935,0.001253831,0.003135646,0.002924437,0.002942096,0.001088735],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001033114,"about_ca_system_score_gemma":0.001113586,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00413823,"about_ca_topic_score_gemma":0.004934406,"domain_scores_codex":[0.9992633,0.0002141276,0.00003104463,0.0002431849,0.0001670945,0.00008114196],"domain_scores_gemma":[0.998504,0.0005364816,0.0001595201,0.0003389848,0.0003472451,0.0001137501],"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":[0.0003423976,0.0004256546,0.002112249,0.0003030109,0.0002524933,0.000181526,0.0002105954,0.6557507,0.02247394,0.02314327,0.01338877,0.2814154],"study_design_scores_gemma":[0.000004125043,0.00002683501,0.00007019956,0.000004164337,0.000004864351,0.00001448238,0.00000774044,0.9913181,0.0008774829,0.007380006,0.0002869899,0.000004998528],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.04277455,0.0005390276,0.9506677,0.0006721329,0.0000547732,0.00005554626,0.0004885743,0.00326292,0.001484763],"genre_scores_gemma":[0.7038345,0.0005766239,0.2842292,0.001112559,0.0001634189,0.000250607,0.00463758,0.0004541067,0.004741472],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.00413823,"threshold_uncertainty_score":0.009467125,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.009713097066967363,"score_gpt":0.2443413976580875,"score_spread":0.2346283005911201,"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."}}