{"id":"W4378195393","doi":"10.1101/2023.05.25.542237","title":"DeepRaccess: High-speed RNA accessibility prediction using deep learning","year":2023,"lang":"en","type":"preprint","venue":"bioRxiv (Cold Spring Harbor Laboratory)","topic":"RNA and protein synthesis mechanisms","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Japan Society for the Promotion of Science; Institute of Genetics; Japan Agency for Medical Research and Development","keywords":"RNA; Computer science; Translation (biology); Software; Feature (linguistics); Artificial intelligence; Transcriptome; Source code; Deep learning; Computational biology; Messenger RNA; Data mining; Biology; Gene; Genetics; Gene expression","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":[0.0007779403,0.001587619,0.001055086,0.0007377326,0.0004534821,0.001164208,0.00213741,0.001576467,0.006853595],"category_scores_gemma":[0.002426845,0.0008831868,0.001285353,0.0006908476,0.0006010612,0.001480052,0.00123441,0.003373278,0.002944814],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001042209,"about_ca_system_score_gemma":0.001483664,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.007386064,"about_ca_topic_score_gemma":0.008054189,"domain_scores_codex":[0.9996338,0.00005923344,0.00001906156,0.0001259736,0.0001091599,0.00005282378],"domain_scores_gemma":[0.9991437,0.0004121831,0.0000670765,0.0001410636,0.0001636894,0.00007230627],"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":[0.0005239963,0.0003588964,0.004560269,0.0005295444,0.0004244694,0.0003266128,0.0001343499,0.7498715,0.04171626,0.01176893,0.05122379,0.1385613],"study_design_scores_gemma":[0.00001407473,0.00001625276,0.0001634324,0.000005211405,0.000005141322,0.00001397199,0.000003423346,0.9927417,0.003805368,0.002070919,0.001151191,0.000009194601],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.08729415,0.001407226,0.8035877,0.0006827147,0.0002734678,0.0001662167,0.006201891,0.09561619,0.004770444],"genre_scores_gemma":[0.5149818,0.0007384944,0.4516775,0.000753988,0.0001390628,0.0005101145,0.01901734,0.00478028,0.007401482],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.007386064,"threshold_uncertainty_score":0.02292758,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02388487394085373,"score_gpt":0.251166640754877,"score_spread":0.2272817668140233,"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."}}