{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000183412,0.0001151002,0.00009448648,0.00003300482,0.0002166402,0.00007467599,0.0001385209,0.00005595493,0.000001012525],"category_scores_gemma":[0.00005679663,0.000104557,0.00005375174,0.00007733994,0.0001361474,0.000002269,0.000154383,0.00004882194,0.000001018411],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000006917408,"about_ca_system_score_gemma":0.00001824626,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001491254,"about_ca_topic_score_gemma":0.000009883714,"domain_scores_codex":[0.9990804,0.00001415135,0.0001179453,0.0004785468,0.00009489897,0.0002140523],"domain_scores_gemma":[0.9997085,0.00003281171,0.0000329672,0.000141648,0.00002550992,0.00005850815],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.000007680332,0.00001003165,0.01453228,0.00002014935,0.00003777494,4.939861e-7,0.0004517606,0.0004279857,0.9808546,0.00001784186,0.000031495,0.003607868],"study_design_scores_gemma":[0.001609536,0.001060406,0.2420992,0.00008438861,0.0001707169,0.00002326275,0.003064693,0.1162251,0.5382839,0.001778973,0.09424589,0.001353978],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9755685,0.01685825,0.006920919,0.00002735246,0.0001163792,0.0001717707,0.00007307543,0.000009863941,0.0002538833],"genre_scores_gemma":[0.9953215,0.0001814293,0.003963979,0.00004397838,0.0001849522,0.00004072154,0.00007045219,0.0000140492,0.0001789037],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.4425707,"threshold_uncertainty_score":0.4263711,"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."}}