{"id":"W4384339915","doi":"10.1080/14737159.2023.2237411","title":"Lost in translation: the pitfalls of Ensembl gene annotations between human genome assemblies and their impact on diagnostics","year":2023,"lang":"en","type":"article","venue":"Expert Review of Molecular Diagnostics","topic":"Genomics and Rare Diseases","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia","funders":"","keywords":"RefSeq; Ensembl; Gene; Computational biology; Gene nomenclature; Genome; Human genome; Biology; Genomics; Bioinformatics; Genetics","routes":{"ca_aff":true,"ca_fund":false,"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":[0.0002683833,0.0002242631,0.000375747,0.00009126292,0.0000591857,0.00001278723,0.0002314445,0.00008972993,0.000008395148],"category_scores_gemma":[0.0005632465,0.000150028,0.00020616,0.0002778113,0.0001231164,0.0000041625,0.00008201451,0.00008182504,0.00000368917],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001004451,"about_ca_system_score_gemma":0.00006998749,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001661449,"about_ca_topic_score_gemma":0.000008389022,"domain_scores_codex":[0.9987921,0.000140285,0.0004567448,0.0002526432,0.0001550522,0.0002031798],"domain_scores_gemma":[0.9988056,0.0003899694,0.0001666289,0.0004394927,0.0001229052,0.00007536961],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","study_design_scores_codex":[0.00004041612,0.0004923438,0.01569787,0.001935327,0.0006012258,0.00007449397,0.00134736,0.0009562922,0.9627767,0.0006746634,0.00506181,0.0103415],"study_design_scores_gemma":[0.001804396,0.002157775,0.5069504,0.004800647,0.000379086,0.00003039695,0.0005683766,0.00006841158,0.4488835,0.001034998,0.03201859,0.001303497],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.794041,0.2042015,0.000264059,0.0004542999,0.0000375417,0.0004825966,0.0003809707,0.000005585978,0.0001325043],"genre_scores_gemma":[0.7144779,0.2842404,0.0001099906,0.0003214707,0.00006867858,0.00003040334,0.0007243538,0.00002261498,0.000004160878],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.5138932,"threshold_uncertainty_score":0.6117965,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02008550928769607,"score_gpt":0.3222297867852412,"score_spread":0.3021442774975451,"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."}}