{"id":"W3048927351","doi":"10.1101/2020.08.10.244442","title":"RNA secondary structure prediction using deep learning with thermodynamic integration","year":2020,"lang":"en","type":"preprint","venue":"bioRxiv (Cold Spring Harbor Laboratory)","topic":"RNA and protein synthesis mechanisms","field":"Biochemistry, Genetics and Molecular Biology","cited_by":15,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Institute of Genetics; Japan Society for the Promotion of Science; Research Organization of Information and Systems","keywords":"Overfitting; Artificial intelligence; Nucleic acid secondary structure; Computer science; Deep learning; Machine learning; Regularization (linguistics); Artificial neural network; Coding (social sciences); RNA; Algorithm; Mathematics; Chemistry","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":[0.0009950114,0.001090584,0.0008645048,0.0007584709,0.0003601749,0.0007706779,0.0009830573,0.001002642,0.001164629],"category_scores_gemma":[0.001713465,0.0005770139,0.0008014109,0.0005954496,0.0005582657,0.001109376,0.001115232,0.001627382,0.0004593536],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009421002,"about_ca_system_score_gemma":0.001268323,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00266982,"about_ca_topic_score_gemma":0.003406868,"domain_scores_codex":[0.9996538,0.00008244032,0.00001942939,0.0001151371,0.00009545687,0.00003378476],"domain_scores_gemma":[0.9994398,0.0002393761,0.00006613734,0.00008587251,0.0001175922,0.00005125702],"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":[0.0001046101,0.0001373817,0.001379207,0.00005679884,0.00006101977,0.00004832524,0.00002554532,0.8925341,0.01732731,0.003835835,0.001317196,0.08317267],"study_design_scores_gemma":[0.000002613483,0.000005044191,0.00003058067,7.649473e-7,0.000001053682,0.000002382468,6.738197e-7,0.9975113,0.001521882,0.0008521044,0.00007007158,0.000001602601],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.07830068,0.0002961127,0.9152349,0.0002215456,0.00005531562,0.00005426574,0.0002023126,0.004280861,0.001354092],"genre_scores_gemma":[0.6098146,0.0001474996,0.3860618,0.0002189226,0.00004868142,0.0001411628,0.001062991,0.0003014472,0.002202862],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.00266982,"threshold_uncertainty_score":0.006835401,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.008502738184107541,"score_gpt":0.1994316590909165,"score_spread":0.1909289209068089,"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."}}