Purpose Phenotype information is crucial for the interpretation of genomic variants. So far it has only been accessible for bioinformatics workflows after encoding into clinical terms by expert dysmorphologists. Methods Here, we introduce an approach driven by artificial intelligence that uses portrait photographs for the interpretation of clinical exome data. We measured the value added by computer-assisted image analysis to the diagnostic yield on a cohort consisting of 679 individuals with 105 different monogenic disorders. For each case in the cohort we compiled frontal photos, clinical features, and the disease-causing variants, and simulated multiple exomes of different ethnic backgrounds. Results The additional use of similarity scores from computer-assisted analysis of frontal photos improved the top 1 accuracy rate by more than 20–89% and the top 10 accuracy rate by more than 5–99% for the disease-causing gene. Conclusion Image analysis by deep-learning algorithms can be used to quantify the phenotypic similarity (PP4 criterion of the American College of Medical Genetics and Genomics guidelines) and to advance the performance of bioinformatics pipelines for exome analysis.

Faciogenital dysplasia or Aarskog–Scott syndrome (AAS) is a genetically heterogeneous developmental disorder. The X-linked form of AAS has been ascribed to mutations in the FGD1 gene. However, although AAS may be considered as a relatively frequent clinical diagnosis, mutations have been established in few patients. Genetic heterogeneity and the clinical overlap with a number of other syndromes might explain this discrepancy. In this study, we have conducted a single-strand conformation polymorphism (SSCP) analysis of the entire coding region of FGD1 in 46 AAS patients and identified eight novel mutations, including one insertion, four deletions and three missense mutations (19.56% detection rate). One mutation (528insC) was found in two independent families. The mutations are scattered all along the coding sequence. Phenotypically, all affected males present with the characteristic AAS phenotype. FGD1 mutations were not associated with severe mental retardation. However, neuropsychiatric disorders, mainly behavioural and learning problems in childhood, were observed in five out of 12 mutated individuals. The current study provides further evidence that mutations of FGD1 may cause AAS and expands the spectrum of disease-causing mutations. The importance of considering the neuropsychological phenotype of AAS patients is discussed.

New technologies such as non-invasive prenatal testing (NIPT), capable of analyzing cell-free fetal DNA in the maternal bloodstream, have become increasingly widespread and available, which has in turn led to ethical and policy challenges that need addressing. NIPT is not yet a diagnostic tool, but can still provide information about fetal genetic characteristics (including sex) very early in pregnancy, and there is no denying that it offers valuable opportunities for pregnant women, particularly those at high risk of having a child with severe genetic disorders or seeking an alternative to invasive prenatal testing. Nonetheless, the ethical, legal and social implications (ELSI) include multiple aspects of informed decision-making, which can entail risks for the individual right to procreative autonomy, in addition to the potential threats posed by sex-selective termination of pregnancy (in light of the information about fetal sex within the first trimester), and the stigmatization and discrimination of disabled individuals. After taking such daunting challenges into account and addressing NIPT-related medicolegal complexities, the review’s authors highlight the need for an ethically and legally sustainable framework for the implementation of NIPT, which seems poised to become a diagnostic tool, as its scope is likely to broaden in the near future.