{"id":"W4394930608","doi":"10.1101/2024.04.15.589672","title":"ProSST: Protein Language Modeling with Quantized Structure and Disentangled Attention","year":2024,"lang":"en","type":"preprint","venue":"bioRxiv (Cold Spring Harbor Laboratory)","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":35,"is_retracted":false,"has_abstract":true,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"Shanghai Jiao Tong University; Science and Technology Commission of Shanghai Municipality; National Natural Science Foundation of China; National Science Foundation","keywords":"Computer science; Linguistics; Natural language processing; Philosophy","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":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0002338061,0.0004860266,0.0003417911,0.0001207372,0.0001069321,0.0002807885,0.0002637844,0.0004974758,0.000008515438],"category_scores_gemma":[0.00009146493,0.0004203514,0.00008728209,0.0001561636,0.0000890162,0.000008394884,0.0007193645,0.0007393782,0.000008556524],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004588994,"about_ca_system_score_gemma":0.0002315359,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002530387,"about_ca_topic_score_gemma":0.000007630857,"domain_scores_codex":[0.9981963,0.00007387003,0.0003637459,0.0007424377,0.0002709742,0.0003526554],"domain_scores_gemma":[0.998642,0.000004625804,0.0002291502,0.0008094747,0.000171569,0.0001432176],"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":[0.00009257745,0.00002577641,0.001946425,0.001345386,0.0001880912,0.00002285784,0.00002237493,0.0006184507,0.9953846,0.000320105,0.00003086227,0.000002514323],"study_design_scores_gemma":[0.002742633,0.0005415477,0.008390356,0.002970503,0.0006482844,7.424844e-7,0.00005121178,0.1804397,0.8002388,0.00003181491,0.0008835239,0.003060828],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9925385,0.001539574,0.004205679,0.0001098455,0.0002165278,0.000998395,0.0002141033,0.0001673492,0.00001002312],"genre_scores_gemma":[0.9864587,0.00004533333,0.01283657,0.00005524039,0.0003299475,0.0001127344,0.000007487984,0.0001317842,0.00002215079],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.1951457,"threshold_uncertainty_score":0.9998248,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.005088720207963003,"score_gpt":0.2178787602609839,"score_spread":0.2127900400530209,"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."}}