{"id":"W4391250913","doi":"10.1016/j.isci.2024.109002","title":"Graphylo: A deep learning approach for predicting regulatory DNA and RNA sites from whole-genome multiple alignments","year":2024,"lang":"en","type":"article","venue":"iScience","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University","funders":"Natural Sciences and Engineering Research Council of Canada; Compute Canada","keywords":"Interpretability; Deep learning; Genome; Convolutional neural network; Genomics; Computational biology; Computer science; Artificial intelligence; Phylogenetic tree; Machine learning; Biology; 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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004835895,0.001370823,0.0006902283,0.001662883,0.0005612663,0.0007855641,0.001378216,0.00120626,0.00283502],"category_scores_gemma":[0.001259481,0.0005590298,0.0009989304,0.001158411,0.0005017127,0.001359463,0.001035354,0.001791804,0.001144567],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001023709,"about_ca_system_score_gemma":0.001253682,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.009650627,"about_ca_topic_score_gemma":0.01836229,"domain_scores_codex":[0.9997398,0.00004565471,0.00001097595,0.0001132429,0.0000541148,0.00003622551],"domain_scores_gemma":[0.9996914,0.0001321063,0.0000519584,0.00004354169,0.00004041283,0.00004066943],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.001039976,0.0004739679,0.01373174,0.0008847837,0.0006834397,0.0007205413,0.00028569,0.3290694,0.0850205,0.02678999,0.04932736,0.4919727],"study_design_scores_gemma":[0.00003981993,0.00006492257,0.001188121,0.00002871631,0.00003838283,0.00008829215,0.00003937159,0.9626594,0.008622443,0.01847513,0.008728892,0.00002654986],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.09488767,0.002705041,0.8563558,0.0008855254,0.000250756,0.000154259,0.008462501,0.0311019,0.005196611],"genre_scores_gemma":[0.4279152,0.001637245,0.5302896,0.0009191076,0.0001111051,0.0002920592,0.02710951,0.00290633,0.008819883],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.009650627,"threshold_uncertainty_score":0.01918888,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01306975114720741,"score_gpt":0.2261694880036522,"score_spread":0.2130997368564448,"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."}}