{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0004366236,0.0005496855,0.000413109,0.0001894949,0.0002065993,0.0001833196,0.0005581636,0.0007107312,0.00001707559],"category_scores_gemma":[0.0005470674,0.0005502962,0.000139504,0.0002963473,0.0001302841,0.00001285028,0.0007751443,0.001158988,0.00002661986],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00008711053,"about_ca_system_score_gemma":0.0006508558,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005391199,"about_ca_topic_score_gemma":0.000006907352,"domain_scores_codex":[0.9975337,0.0002249475,0.0005057566,0.0009164223,0.0003428268,0.0004763412],"domain_scores_gemma":[0.9975587,0.00001908435,0.0005396529,0.001259016,0.0004639366,0.0001596798],"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":[0.0001415621,0.0001189924,0.02599626,0.000683844,0.0002894982,0.00001564395,0.00001879331,0.006952452,0.9654019,0.0001061743,0.0002672431,0.000007589058],"study_design_scores_gemma":[0.001829388,0.0003807614,0.0573631,0.0009175513,0.0001794758,7.893969e-8,0.00001649788,0.01708864,0.8952782,7.196513e-7,0.02534578,0.001599784],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9567329,0.0003749335,0.04047028,0.0001646497,0.0003772151,0.00135803,0.00008906484,0.000292322,0.0001406409],"genre_scores_gemma":[0.9272939,0.00007224316,0.07143921,0.0001434883,0.0003211931,0.0003087102,0.000007417305,0.00009308659,0.0003207418],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.07012372,"threshold_uncertainty_score":0.9996949,"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."}}