{"id":"W3159573239","doi":"10.1101/2021.04.27.441365","title":"Prediction of RNA-protein interactions using a nucleotide language model","year":2021,"lang":"en","type":"preprint","venue":"bioRxiv (Cold Spring Harbor Laboratory)","topic":"RNA and protein synthesis mechanisms","field":"Biochemistry, Genetics and Molecular Biology","cited_by":6,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Core Research for Evolutional Science and Technology; Institute of Genetics; Japan Society for the Promotion of Science","keywords":"Computer science; Python (programming language); Artificial intelligence; Encoder; RNA; RNA-binding protein; Language model; Computational biology; Architecture; Deep learning; Machine learning; Theoretical computer science; Biology; Programming language; Gene; Genetics","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004046321,0.0006075192,0.0005206848,0.000583739,0.0002190879,0.0005566401,0.0006578931,0.0007255853,0.001842222],"category_scores_gemma":[0.0009435068,0.0003332645,0.0006961125,0.0005138049,0.0002684731,0.000726822,0.0004340929,0.0009520131,0.0009045299],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007482254,"about_ca_system_score_gemma":0.0008157479,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.007546166,"about_ca_topic_score_gemma":0.01029284,"domain_scores_codex":[0.9998391,0.00004373792,0.000006505265,0.00005428937,0.00002927215,0.00002702794],"domain_scores_gemma":[0.9996299,0.0002265234,0.00003234501,0.00002419967,0.00005872329,0.00002830917],"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":[0.000190004,0.00009772875,0.003740198,0.00008319013,0.00006372322,0.0001831261,0.00002776581,0.9366522,0.01312598,0.006203566,0.002643173,0.03698928],"study_design_scores_gemma":[0.000001987544,0.000004943892,0.00009539044,0.000001173731,0.000002156632,0.000006342358,0.000001298691,0.9978375,0.0007605367,0.001165875,0.0001211042,0.000001838574],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2782461,0.001134365,0.7061653,0.0007084208,0.0001084696,0.00006106608,0.00330602,0.005417143,0.004853037],"genre_scores_gemma":[0.920336,0.0003641697,0.06907754,0.0001757857,0.00004092926,0.00008248846,0.003754626,0.0002417095,0.005926667],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.007546166,"threshold_uncertainty_score":0.01500446,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02156951671998887,"score_gpt":0.2351190909926607,"score_spread":0.2135495742726718,"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."}}