Search

Over a relatively short period of time, the clinical geneticist’s “toolbox” has been expanded by machine-learning algorithms for image analysis, which can be applied to the task of syndrome identification on the basis of facial photographs, but these technologies harbor potential beyond the recognition of established phenotypes. Here, we comprehensively characterized two individuals with a hitherto unknown genetic disorder caused by the same de novo mutation in LEMD2 (c.1436C>T;p.Ser479Phe), the gene which encodes the nuclear envelope protein LEM domain-containing protein 2 (LEMD2). Despite different ages and ethnic backgrounds, both individuals share a progeria-like facial phenotype and a distinct combination of physical and neurologic anomalies, such as growth retardation; hypoplastic jaws crowded with multiple supernumerary, yet unerupted, teeth; and cerebellar intention tremor. Immunofluorescence analyses of patient fibroblasts revealed mutation-induced disturbance of nuclear architecture, recapitulating previously published data in LEMD2-deficient cell lines, and additional experiments suggested mislocalization of mutant LEMD2 protein within the nuclear lamina. Computational analysis of facial features with two different deep neural networks showed phenotypic proximity to other nuclear envelopathies. One of the algorithms, when trained to recognize syndromic similarity (rather than specific syndromes) in an unsupervised approach, clustered both individuals closely together, providing hypothesis-free hints for a common genetic etiology. We show that a recurrent de novo mutation in LEMD2 causes a nuclear envelopathy whose prognosis in adolescence is relatively good in comparison to that of classical Hutchinson-Gilford progeria syndrome, and we suggest that the application of artificial intelligence to the analysis of patient images can facilitate the discovery of new genetic disorders.

As a result of a whole-exome sequencing study, we report three mutant alleles in SEC24D, a gene encoding a component of the COPII complex involved in protein export from the ER: the truncating mutation c.613C>T (p.Gln205∗) and the missense mutations c.3044C>T (p.Ser1015Phe, located in a cargo-binding pocket) and c.2933A>C (p.Gln978Pro, located in the gelsolin-like domain). Three individuals from two families affected by a similar skeletal phenotype were each compound heterozygous for two of these mutant alleles, with c.3044C>T being embedded in a 14 Mb founder haplotype shared by all three. The affected individuals were a 7-year-old boy with a phenotype most closely resembling Cole-Carpenter syndrome and two fetuses initially suspected to have a severe type of osteogenesis imperfecta. All three displayed a severely disturbed ossification of the skull and multiple fractures with prenatal onset. The 7-year-old boy had short stature and craniofacial malformations including macrocephaly, midface hypoplasia, micrognathia, frontal bossing, and down-slanting palpebral fissures. Electron and immunofluorescence microscopy of skin fibroblasts of this individual revealed that ER export of procollagen was inefficient and that ER tubules were dilated, faithfully reproducing the cellular phenotype of individuals with cranio-lentico-sutural dysplasia (CLSD). CLSD is caused by SEC23A mutations and displays a largely overlapping craniofacial phenotype, but it is not characterized by generalized bone fragility and presented with cataracts in the original family described. The cellular and morphological phenotypes we report are in concordance with the phenotypes described for the Sec24d-deficient fish mutants vbi (medaka) and bulldog (zebrafish).