{"id":"W4366686673","doi":"10.1101/2023.04.20.537615","title":"Automatic recognition of complementary strands: Lessons regarding machine learning abilities in RNA folding","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":"Université de Montréal; Institute for Research in Immunology and Cancer","funders":"","keywords":"Overfitting; Artificial intelligence; Machine learning; Computer science; Complementarity (molecular biology); USable; Extrapolation; Folding (DSP implementation); Limiting; Task (project management); Artificial neural network; Engineering; Mathematics","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":[0.002419716,0.0003943566,0.000452698,0.0008748657,0.0004216151,0.001823271,0.0008693765,0.001107761,0.002685699],"category_scores_gemma":[0.01462468,0.0003997594,0.000472812,0.0005745871,0.002264574,0.005296054,0.001422965,0.001394871,0.0006326079],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005008889,"about_ca_system_score_gemma":0.0004077535,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0008231916,"about_ca_topic_score_gemma":0.0005719553,"domain_scores_codex":[0.9994684,0.0002034772,0.00003329326,0.0001482088,0.00009925986,0.00004749926],"domain_scores_gemma":[0.9904247,0.006791137,0.0005808116,0.001377885,0.0005320308,0.0002935342],"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":[0.0006706727,0.0003412966,0.0316764,0.0006272958,0.0001374465,0.0005721565,0.0008564604,0.3877829,0.08182678,0.2806943,0.003440228,0.211374],"study_design_scores_gemma":[0.00001674065,0.00007131948,0.003925805,0.00004869697,0.0000130552,0.0001935435,0.0001076999,0.595138,0.01918909,0.3797445,0.001514572,0.00003708576],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7334762,0.002961258,0.2402685,0.004833434,0.0001435017,0.00003249951,0.00034476,0.0008760649,0.01706385],"genre_scores_gemma":[0.9826834,0.000377432,0.01582982,0.0001249576,0.00005203475,0.00001307612,0.0001001377,0.00004105166,0.0007780658],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.002685699,"threshold_uncertainty_score":0.01279682,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03418215281967774,"score_gpt":0.2533498438153,"score_spread":0.2191676909956222,"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."}}