{"id":"W4399075790","doi":"10.1101/2024.05.23.594910","title":"AptaGPT: Advancing aptamer design with a generative pre-trained language model","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":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"Discovery Centre","funders":"","keywords":"Aptamer; Systematic evolution of ligands by exponential enrichment; Computer science; Generative grammar; SELEX Aptamer Technique; Computational biology; Artificial intelligence; Machine learning; Oligonucleotide; Biology; RNA; Molecular biology; Genetics; DNA","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":[0.0006623646,0.0006985302,0.000605393,0.0003531298,0.0002085496,0.0007020888,0.001043681,0.001092773,0.002158434],"category_scores_gemma":[0.001920913,0.000567696,0.001012396,0.0003049748,0.0007115894,0.0005869748,0.0008718017,0.001589578,0.0007456786],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007130214,"about_ca_system_score_gemma":0.0009807089,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002486796,"about_ca_topic_score_gemma":0.003808217,"domain_scores_codex":[0.9997097,0.00009511823,0.0000124872,0.00006925882,0.00008089318,0.00003255697],"domain_scores_gemma":[0.9992858,0.0005176262,0.00003917732,0.00005553916,0.00006665227,0.0000351647],"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":[0.00007332184,0.0000535444,0.0004847163,0.00006868173,0.00004554168,0.0001086899,0.00005302405,0.9335222,0.01224798,0.008955793,0.001079693,0.04330685],"study_design_scores_gemma":[0.000005159814,0.00001314483,0.00001319157,0.000001702297,0.000003708434,0.00001143002,0.000002067863,0.9962431,0.001421063,0.001997994,0.000285302,0.000002099191],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02332091,0.0001911797,0.9717576,0.0002676683,0.00004467874,0.00005153297,0.0001156107,0.001617743,0.002633026],"genre_scores_gemma":[0.5969084,0.0003776275,0.393398,0.0008800184,0.00006426522,0.0003417176,0.0006442559,0.0005867723,0.006798955],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.002486796,"threshold_uncertainty_score":0.007220685,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01063085603139744,"score_gpt":0.2249765696873308,"score_spread":0.2143457136559333,"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."}}