{"id":"W4386693514","doi":"10.1101/2023.09.08.556883","title":"Deciphering 3’ UTR mediated gene regulation using interpretable deep representation learning","year":2023,"lang":"en","type":"preprint","venue":"bioRxiv (Cold Spring Harbor Laboratory)","topic":"RNA modifications and cancer","field":"Biochemistry, Genetics and Molecular Biology","cited_by":8,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"People's Government of Jilin Province; Natural Sciences and Engineering Research Council of Canada; National Natural Science Foundation of China","keywords":"Computer science; Encoder; Artificial intelligence; Untranslated region; Transformer; Natural language processing; Representation (politics); Computational biology; Messenger RNA; Gene; Machine learning; Biology; Genetics; Engineering","routes":{"ca_aff":true,"ca_fund":true,"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":[0.0003735918,0.0005601395,0.0003741211,0.0003715314,0.0001515464,0.0005515561,0.0006512062,0.0006589863,0.001004868],"category_scores_gemma":[0.0008116841,0.0002346673,0.0005678431,0.0003195227,0.0003765151,0.0005714973,0.0004731002,0.001060481,0.000295919],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006745652,"about_ca_system_score_gemma":0.0005576996,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005231394,"about_ca_topic_score_gemma":0.005178268,"domain_scores_codex":[0.999886,0.00002568426,0.000003911719,0.00004406243,0.00001918948,0.00002103456],"domain_scores_gemma":[0.9997799,0.0001175373,0.00002822028,0.00003016418,0.00002947001,0.00001469744],"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":[0.0002145909,0.0001120561,0.003102652,0.0001237395,0.00009611993,0.0001620769,0.00007191098,0.8117256,0.0653059,0.009289365,0.002476857,0.1073191],"study_design_scores_gemma":[0.000002390745,0.000008138853,0.0001929699,0.000002048621,0.000003910091,0.000005832529,0.000003785084,0.9922267,0.004526987,0.002830465,0.0001944433,0.000002358711],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2558203,0.001205382,0.7338341,0.0005839634,0.00008987109,0.00002931625,0.0009062569,0.00482767,0.002702956],"genre_scores_gemma":[0.9322226,0.0003096143,0.06413838,0.0001598701,0.00002609464,0.00003420309,0.001078917,0.0001243374,0.001906018],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.005231394,"threshold_uncertainty_score":0.01040184,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02493933564462733,"score_gpt":0.2603483260045794,"score_spread":0.2354089903599521,"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."}}