{"id":"W4364381330","doi":"10.1101/2023.04.09.536185","title":"Functional similarity of non-coding regions is revealed in phylogenetic average motif score representations","year":2023,"lang":"en","type":"preprint","venue":"bioRxiv (Cold Spring Harbor Laboratory)","topic":"Genomics and Chromatin Dynamics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":5,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"Common Fund; National Human Genome Research Institute; National Institute of Neurological Disorders and Stroke; National Institute of Mental Health; NIH Office of the Director; National Heart, Lung, and Blood Institute; National Institute on Drug Abuse; Natural Sciences and Engineering Research Council of Canada; National Cancer Institute; National Institutes of Health","keywords":"Phylogenetic tree; Motif (music); Coding (social sciences); Noncoding DNA; Regulatory sequence; Artificial intelligence; Computational biology; Biology; Pattern recognition (psychology); Theoretical computer science; Genetics; Computer science; Gene; Mathematics; Genome; Transcription factor; Statistics","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":[0.0004994208,0.0002432071,0.0003899338,0.001164012,0.0002244525,0.0007012826,0.0004688513,0.0004323101,0.001932487],"category_scores_gemma":[0.00317288,0.0001274587,0.000349555,0.001204465,0.0004609201,0.001103557,0.0005239315,0.0004786076,0.0003051382],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002850113,"about_ca_system_score_gemma":0.0002543862,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0008930018,"about_ca_topic_score_gemma":0.0008898582,"domain_scores_codex":[0.9996762,0.00007799121,0.0000219106,0.00009902113,0.00007506667,0.00004974458],"domain_scores_gemma":[0.9985305,0.0005139133,0.0003812851,0.0002472737,0.0002119017,0.0001150842],"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":[0.00163317,0.000352887,0.09521054,0.0004670732,0.0002529274,0.0006222683,0.0006396396,0.1167514,0.4320029,0.05793617,0.002106137,0.2920249],"study_design_scores_gemma":[0.0000369747,0.00059493,0.09246093,0.00006252601,0.0001165364,0.0006449628,0.0003184264,0.7529135,0.06099347,0.08815948,0.003606931,0.0000912406],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8310156,0.0003301681,0.1655681,0.0001791438,0.00002917726,0.00001644966,0.0006098025,0.0004718469,0.001779717],"genre_scores_gemma":[0.9821725,0.00006799573,0.01687481,0.00002819859,0.00001060109,0.00001098523,0.0004747039,0.00004729524,0.0003128343],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.001932487,"threshold_uncertainty_score":0.006464839,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02301704554085113,"score_gpt":0.2372564026236737,"score_spread":0.2142393570828226,"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."}}