{"id":"W4387362445","doi":"10.1073/pnas.2221165120","title":"Deciphering RNA splicing logic with interpretable machine learning","year":2023,"lang":"en","type":"article","venue":"Proceedings of the National Academy of Sciences","topic":"RNA and protein synthesis mechanisms","field":"Biochemistry, Genetics and Molecular Biology","cited_by":26,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"York University; Additional Ventures; Lalor Foundation; Life Sciences Research Foundation; Pharmaceutical Research and Manufacturers of America Foundation; Simons Foundation; National Science Foundation","keywords":"Interpretability; RNA splicing; Artificial intelligence; Machine learning; Computer science; TRACE (psycholinguistics); Artificial neural network; Process (computing); Deep learning; Biology; RNA; Gene","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":[0.001871179,0.0007311793,0.0005563359,0.0005271931,0.000335905,0.001950236,0.00097603,0.0009156779,0.001699152],"category_scores_gemma":[0.00695698,0.0004958294,0.0009730406,0.0003267774,0.001825375,0.002111459,0.0009537013,0.00224682,0.0003315387],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001202227,"about_ca_system_score_gemma":0.001122768,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001361073,"about_ca_topic_score_gemma":0.002209686,"domain_scores_codex":[0.9994001,0.0002966458,0.00003027221,0.0001211934,0.0001148265,0.00003685968],"domain_scores_gemma":[0.9971727,0.001931678,0.0002562863,0.0004284405,0.0001627247,0.00004812533],"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":[0.00009542417,0.00007627282,0.001758894,0.0001174344,0.00005578993,0.0001318748,0.0001252817,0.864296,0.009740796,0.0951683,0.0005092935,0.0279247],"study_design_scores_gemma":[0.000004094279,0.00001304524,0.00005924697,0.000005934732,0.00000496418,0.000008398784,0.000006675755,0.9489381,0.001718706,0.04895097,0.0002847665,0.000005038327],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.04522485,0.0001768308,0.9508969,0.0008792223,0.00004650389,0.00003276457,0.0001621113,0.0006867467,0.001894038],"genre_scores_gemma":[0.734063,0.0004280397,0.263117,0.000280616,0.00004783782,0.0001487797,0.0003209838,0.0001520432,0.001441628],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.001950236,"threshold_uncertainty_score":0.009895861,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0283287603412796,"score_gpt":0.2810729463950307,"score_spread":0.252744186053751,"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."}}