{"id":"W4405778657","doi":"10.1101/2024.12.12.628267","title":"ppLM-CO:Pre-trained Protein Language Model for Codon Optimization","year":2024,"lang":"en","type":"preprint","venue":"bioRxiv (Cold Spring Harbor Laboratory)","topic":"RNA and protein synthesis mechanisms","field":"Biochemistry, Genetics and Molecular Biology","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"","keywords":"ORFS; Open reading frame; Benchmark (surveying); Messenger RNA; Translation (biology); ENCODE; Computer science; Codon usage bias; Computational biology; Biology; Genetics; Gene; Peptide sequence; Genome","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":[0.0005536978,0.001546922,0.0008749823,0.0003876664,0.0003274878,0.0008248409,0.001679842,0.001592885,0.003842113],"category_scores_gemma":[0.001867982,0.000544555,0.0009580664,0.000409179,0.0005176426,0.00135862,0.001037273,0.002809052,0.0030152],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009295293,"about_ca_system_score_gemma":0.001461063,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004827811,"about_ca_topic_score_gemma":0.007070913,"domain_scores_codex":[0.9996276,0.0000785103,0.00001854967,0.0001325196,0.00008810028,0.00005470161],"domain_scores_gemma":[0.9995002,0.0001994804,0.00005144249,0.00007421309,0.0001280494,0.00004663265],"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":[0.0002811117,0.0002427884,0.001067331,0.0001951535,0.000120449,0.000210704,0.0000498125,0.8104036,0.0295582,0.005470307,0.01447252,0.1379281],"study_design_scores_gemma":[0.000005165685,0.00001857244,0.00002864839,0.000002695851,0.0000033844,0.00001106748,0.000002317108,0.9957676,0.002806785,0.000813437,0.0005362383,0.000004217774],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.04510702,0.001072226,0.9292972,0.0007335171,0.0003160253,0.0001000404,0.0007187954,0.01855771,0.004097572],"genre_scores_gemma":[0.5692883,0.0006848192,0.4084091,0.001364374,0.0001951691,0.0005097587,0.003971214,0.002084801,0.01349257],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.004827811,"threshold_uncertainty_score":0.01285315,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.011520487154335,"score_gpt":0.2405904218897433,"score_spread":0.2290699347354083,"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."}}