{"id":"W4386417746","doi":"10.3389/fgene.2023.1254226","title":"Automatic recognition of complementary strands: lessons regarding machine learning abilities in RNA folding","year":2023,"lang":"en","type":"article","venue":"Frontiers in Genetics","topic":"RNA and protein synthesis mechanisms","field":"Biochemistry, Genetics and Molecular Biology","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université de Montréal; Institute for Research in Immunology and Cancer","funders":"","keywords":"Overfitting; Computer science; Machine learning; Artificial intelligence; Complementarity (molecular biology); Task (project management); Generalization; Limiting; Folding (DSP implementation); Extrapolation; Context (archaeology); 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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005251607,0.0001237481,0.0002133326,0.0002067209,0.00004557021,0.0000112663,0.0001445318,0.0001020695,0.00002641578],"category_scores_gemma":[0.0000965935,0.0001377279,0.00006252762,0.0002136917,0.0000422736,0.000004152356,0.00007507862,0.00009807901,0.000002017672],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002656543,"about_ca_system_score_gemma":0.0000285759,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003738392,"about_ca_topic_score_gemma":0.00007918781,"domain_scores_codex":[0.9988858,0.0001559375,0.0003415404,0.0002371408,0.0001284253,0.0002512287],"domain_scores_gemma":[0.9996527,0.00002680476,0.00009452849,0.000170788,0.00002366367,0.0000314608],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.00009792976,0.00006460454,0.0975899,0.000293028,0.00008514197,0.00001185404,0.0009095912,0.00296621,0.5774972,0.00002854721,0.0009051999,0.3195508],"study_design_scores_gemma":[0.001957725,0.0004504415,0.0127952,0.0003883809,0.00004096407,0.000004784648,0.005525894,0.02918351,0.9383598,0.008177649,0.002602913,0.0005127424],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9923036,0.001427551,0.00535434,0.00009959042,0.0002817111,0.0002398363,0.00003646367,0.0000197247,0.0002371774],"genre_scores_gemma":[0.9742281,0.001530087,0.02384261,0.00002076437,0.00004538421,0.00003126935,0.0001994515,0.00002417203,0.00007815984],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3608626,"threshold_uncertainty_score":0.5616379,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02768553855659107,"score_gpt":0.265634237727259,"score_spread":0.2379486991706679,"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."}}