학술논문
PhenoScore quantifies phenotypic variation for rare genetic diseases by combining facial analysis with other clinical features using a machine-learning framework
Document Type
Original Paper
Author
Dingemans, Alexander J. M.; Hinne, Max; Truijen, Kim M. G.; Goltstein, Lia; van Reeuwijk, Jeroen; de Leeuw, Nicole; Schuurs-Hoeijmakers, Janneke; Pfundt, Rolph; Diets, Illja J.; den Hoed, Joery; de Boer, Elke; Coenen-van der Spek, Jet; Jansen, Sandra; van Bon, Bregje W.; Jonis, Noraly; Ockeloen, Charlotte W.; Vulto-van Silfhout, Anneke T.; Kleefstra, Tjitske; Koolen, David A.; Campeau, Philippe M.; Palmer, Elizabeth E.; Van Esch, Hilde; Lyon, Gholson J.; Alkuraya, Fowzan S.; Rauch, Anita; Marom, Ronit; Baralle, Diana; van der Sluijs, Pleuntje J.; Santen, Gijs W. E.; Kooy, R. Frank; van Gerven, Marcel A. J.; Vissers, Lisenka E. L. M.; de Vries, Bert B. A.
Source
Nature Genetics. 55(9):1598-1607
Subject
Language
English
ISSN
1061-4036
1546-1718
1546-1718
Abstract
Several molecular and phenotypic algorithms exist that establish genotype–phenotype correlations, including facial recognition tools. However, no unified framework that investigates both facial data and other phenotypic data directly from individuals exists. We developed PhenoScore: an open-source, artificial intelligence-based phenomics framework, combining facial recognition technology with Human Phenotype Ontology data analysis to quantify phenotypic similarity. Here we show PhenoScore’s ability to recognize distinct phenotypic entities by establishing recognizable phenotypes for 37 of 40 investigated syndromes against clinical features observed in individuals with other neurodevelopmental disorders and show it is an improvement on existing approaches. PhenoScore provides predictions for individuals with variants of unknown significance and enables sophisticated genotype–phenotype studies by testing hypotheses on possible phenotypic (sub)groups. PhenoScore confirmed previously known phenotypic subgroups caused by variants in the same gene for SATB1, SETBP1 and DEAF1 and provides objective clinical evidence for two distinct ADNP-related phenotypes, already established functionally.
PhenoScore is an open-source machine-learning tool that combines facial image recognition with Human Phenotype Ontology for genetic syndrome identification without genomic data, with applications to subgroup analysis and variants of unknown significance classification.
PhenoScore is an open-source machine-learning tool that combines facial image recognition with Human Phenotype Ontology for genetic syndrome identification without genomic data, with applications to subgroup analysis and variants of unknown significance classification.