{"id":"W2962655813","doi":"10.1093/bioinformatics/btz337","title":"Prediction of mRNA subcellular localization using deep recurrent neural networks","year":2019,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":86,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université de Montréal; Montreal Clinical Research Institute; McGill University","funders":"Institut de Valorisation des Données","keywords":"Computational biology; Sequence (biology); Computer science; Identification (biology); RNA; Subcellular localization; Variety (cybernetics); Messenger RNA; Biology; Set (abstract data type); Deep learning; RNA-binding protein; Artificial neural network; Artificial intelligence; Gene; Genetics","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002319338,0.0001632247,0.0001711886,0.00007228552,0.0000559363,0.0000257577,0.0001808594,0.0001895959,0.00003170953],"category_scores_gemma":[0.00006412285,0.0001541256,0.00008806523,0.0001540683,0.0000490366,0.00002181441,0.0001165017,0.0001273762,0.00001360244],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002418262,"about_ca_system_score_gemma":0.00003163056,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000005642093,"about_ca_topic_score_gemma":0.000001775203,"domain_scores_codex":[0.9988273,0.00003370631,0.0005916753,0.0001068548,0.000217274,0.0002232111],"domain_scores_gemma":[0.9990464,0.00001016048,0.000372779,0.0003841603,0.000123985,0.00006249459],"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":[0.00007988734,0.00006635729,0.08589184,0.0005727056,0.00007807434,3.634134e-7,0.0005480394,0.895071,0.006911257,0.000182685,0.0006111136,0.009986633],"study_design_scores_gemma":[0.0003961125,0.0002598029,0.0008184561,0.00003465286,0.00002459827,0.00001551847,0.0001277927,0.9923142,0.002878559,0.000005055027,0.002983814,0.0001414743],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5164503,0.0002149016,0.4809129,0.000007328431,0.00063824,0.0003494949,0.00001808411,0.00002834695,0.001380397],"genre_scores_gemma":[0.9863076,0.00008420002,0.01268665,0.0001117879,0.0001271832,0.000002676683,0.0005983424,0.00002139937,0.00006021604],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.4698572,"threshold_uncertainty_score":0.6285062,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01212322715081878,"score_gpt":0.2315241812715117,"score_spread":0.2194009541206929,"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."}}