{"id":"W1019830208","doi":"10.1038/nbt.3300","title":"Predicting the sequence specificities of DNA- and RNA-binding proteins by deep learning","year":2015,"lang":"en","type":"article","venue":"Nature Biotechnology","topic":"RNA and protein synthesis mechanisms","field":"Biochemistry, Genetics and Molecular Biology","cited_by":3163,"is_retracted":false,"has_abstract":false,"ca_institutions":"Canadian Institute for Advanced Research; University of Toronto","funders":"Canadian Institutes of Health Research","keywords":"Computational biology; Sequence (biology); Deep learning; Computer science; Artificial intelligence; DNA sequencing; Scalability; RNA; Software; Machine learning; Biology; DNA; Data mining; Bioinformatics; Genetics; Gene","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":[0.0005162019,0.0007813988,0.0007167288,0.0007652077,0.0003353837,0.0009266634,0.000842982,0.0009673744,0.00143673],"category_scores_gemma":[0.001356359,0.0005687108,0.0006575735,0.0006006042,0.0004691909,0.001073262,0.0004768935,0.001781762,0.0007373126],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009353529,"about_ca_system_score_gemma":0.0006338874,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002951983,"about_ca_topic_score_gemma":0.004639918,"domain_scores_codex":[0.9998361,0.00003762107,0.000007397939,0.00005009352,0.00003372662,0.00003500535],"domain_scores_gemma":[0.9992765,0.0004291696,0.00009086314,0.00004519374,0.00008228277,0.0000759902],"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":[0.001038116,0.0005251343,0.02407724,0.0004390344,0.0002385721,0.0002408768,0.00009493111,0.5560287,0.2127867,0.01983463,0.005963902,0.1787321],"study_design_scores_gemma":[0.00001298152,0.00002279586,0.0007984682,0.000004716429,0.00001178077,0.00002194127,0.00001369531,0.9769068,0.01112174,0.01072771,0.0003495766,0.000007800676],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"methods","genre_scores_codex":[0.7046845,0.001222341,0.2875229,0.0006589358,0.00007461329,0.00003981326,0.0007089779,0.001721252,0.003366556],"genre_scores_gemma":[0.9610209,0.0003664987,0.03605104,0.0001833949,0.00003062078,0.00002904278,0.0008683692,0.00008904278,0.001361167],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.002951983,"threshold_uncertainty_score":0.006786466,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01211662501401373,"score_gpt":0.2361391247602344,"score_spread":0.2240224997462207,"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."}}