{"id":"W4406221449","doi":"10.1038/s41467-024-55185-y","title":"Systematically developing a registry of splice-site creating variants utilizing massive publicly available transcriptome sequence data","year":2025,"lang":"en","type":"article","venue":"Nature Communications","topic":"RNA Research and Splicing","field":"Biochemistry, Genetics and Molecular Biology","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Japan Society for the Promotion of Science; Institute of Genetics; Japan Agency for Medical Research and Development","keywords":"splice; Transcriptome; Computational biology; RNA splicing; Biology; Genetics; Alu element; Alternative splicing; Gene; Sequence (biology); Bioinformatics; Genome; Human genome; RNA; Exon; Gene expression","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.005007772,0.001115739,0.001682533,0.008761724,0.001118037,0.002691003,0.001345601,0.0008901054,0.001965185],"category_scores_gemma":[0.01101793,0.0006662695,0.00170043,0.007813785,0.0004726363,0.00183869,0.002504763,0.001356365,0.003172031],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006961938,"about_ca_system_score_gemma":0.003759028,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00363012,"about_ca_topic_score_gemma":0.007958034,"domain_scores_codex":[0.9964265,0.0004961331,0.000572524,0.001451239,0.0008104965,0.0002430696],"domain_scores_gemma":[0.9934306,0.002086139,0.001117866,0.001401811,0.001475143,0.0004885384],"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":[0.001536489,0.0006288444,0.2865947,0.005484324,0.001644968,0.003737182,0.001587585,0.02339385,0.191635,0.01045392,0.1136493,0.3596538],"study_design_scores_gemma":[0.0005752236,0.001001068,0.2743625,0.001464381,0.001961086,0.004620084,0.003399104,0.217602,0.1389965,0.03030573,0.3250865,0.0006259691],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"dataset","genre_gemma":"methods","genre_scores_codex":[0.3150271,0.004262525,0.1904926,0.000751473,0.0003997955,0.000912148,0.4508166,0.03101778,0.006320022],"genre_scores_gemma":[0.1135695,0.001294818,0.2186673,0.0002023968,0.00008714047,0.000706195,0.6635384,0.001197061,0.0007371639],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.008761724,"threshold_uncertainty_score":0.02648395,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.07055552631111407,"score_gpt":0.3655698656500227,"score_spread":0.2950143393389086,"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."}}