{"id":"W4385628976","doi":"10.1038/s41588-023-01469-w","title":"PhenoScore quantifies phenotypic variation for rare genetic diseases by combining facial analysis with other clinical features using a machine-learning framework","year":2023,"lang":"en","type":"article","venue":"Nature Genetics","topic":"Genomics and Rare Diseases","field":"Biochemistry, Genetics and Molecular Biology","cited_by":74,"is_retracted":false,"has_abstract":false,"ca_institutions":"Université de Montréal","funders":"National Institute of General Medical Sciences; Medical Research Council; National Institutes of Health; National Health and Medical Research Council; European Commission; National Institute for Health and Care Research; Universiteit Antwerpen; Office for People With Developmental Disabilities","keywords":"Phenotype; Phenomics; Biology; Computational biology; Genetics; Phenotypic trait; Variation (astronomy); Genotype-phenotype distinction; Gene; Genomics; Genome","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":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0001403116,0.0002869438,0.0003422529,0.0001322043,0.0003065469,0.0001058016,0.0002605614,0.0005862212,0.00001502678],"category_scores_gemma":[0.0002757278,0.0002489202,0.0002995859,0.0005152017,0.00008966358,0.000003843907,0.0001085648,0.0003605341,0.000002654811],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001350416,"about_ca_system_score_gemma":0.0001129133,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001760272,"about_ca_topic_score_gemma":0.00004994992,"domain_scores_codex":[0.9983142,0.0001174769,0.0003224155,0.0006406299,0.0002276782,0.0003776098],"domain_scores_gemma":[0.998981,0.00009558968,0.0002102769,0.0003863509,0.0001766288,0.0001501392],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.001310033,0.0003191748,0.9000331,0.0001535329,0.003528932,0.00001865459,0.0004390272,0.05471621,0.0311287,0.000135042,0.003530679,0.004686986],"study_design_scores_gemma":[0.004065394,0.001875423,0.8477011,0.0001295144,0.006990652,0.00001955966,0.000810149,0.06503056,0.00771154,0.001959177,0.06136261,0.002344325],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9676018,0.0105957,0.02010377,0.00005954481,0.0003456342,0.0003587023,0.0008676294,0.00005473285,0.00001246905],"genre_scores_gemma":[0.9843206,0.000493241,0.01203197,0.0003765553,0.0005821108,0.00002895087,0.001891287,0.00007635556,0.0001989261],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.05783193,"threshold_uncertainty_score":0.9999963,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01451055269996052,"score_gpt":0.3104937217926899,"score_spread":0.2959831690927293,"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."}}