{"id":"W4394582173","doi":"10.1093/bioinformatics/btae190","title":"Improving the performance of supervised deep learning for regulatory genomics using phylogenetic augmentation","year":2024,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Genomics and Chromatin Dynamics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":12,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"Natural Sciences and Engineering Research Council of Canada; Canada Research Chairs","keywords":"Genomics; Phylogenetic tree; Computer science; Deep learning; Source code; Set (abstract data type); Artificial intelligence; Sequence (biology); Function (biology); Machine learning; Code (set theory); Computational genomics; Functional genomics; Biological data; Computational biology; Genome; Biology; 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":[0.002952739,0.001659441,0.0008388522,0.0005907014,0.0004610459,0.0008713458,0.002009815,0.001470554,0.002630667],"category_scores_gemma":[0.01094933,0.000554782,0.0008976229,0.000617919,0.0008609536,0.002030855,0.001498541,0.00280722,0.001349171],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001175707,"about_ca_system_score_gemma":0.001643356,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004754961,"about_ca_topic_score_gemma":0.005436358,"domain_scores_codex":[0.9991049,0.0003512627,0.00005516328,0.0002267359,0.0001826493,0.00007924294],"domain_scores_gemma":[0.994908,0.003170537,0.0002544412,0.0007803787,0.0007184675,0.000168193],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0006014403,0.0005402468,0.007177648,0.000285151,0.0001526934,0.0001329413,0.000137199,0.7515048,0.01724982,0.004515399,0.008062038,0.2096406],"study_design_scores_gemma":[0.0000100344,0.00002818454,0.0002265779,0.000009211889,0.000006344354,0.000008683736,0.000006371767,0.9936923,0.003173374,0.0025027,0.0003315255,0.000004667797],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2867326,0.001848221,0.6811692,0.002328951,0.0002629854,0.0001661156,0.001811116,0.01976997,0.005910767],"genre_scores_gemma":[0.7623149,0.0003679992,0.2275207,0.0007719986,0.00009670873,0.0002309403,0.005567558,0.000512671,0.002616584],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.004754961,"threshold_uncertainty_score":0.01561576,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.008751119482387123,"score_gpt":0.2201087679822682,"score_spread":0.2113576484998811,"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."}}