The Discovery of a LEMD2-Associated Nuclear Envelopathy with Early Progeroid Appearance Suggests Advanced Applications for AI-Driven Facial Phenotyping

Abstract

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.

Two novel cases further expand the phenotype of TOR1AIP1-associated nuclear envelopathies

“…4g), which according to the previous data likely resemble cytoplasmic channels traversing the nucleus (Fichtman et al 2019). Such nuclear channels were not observed in control cell lines, and we have not observed them before either in primary cell lines of unaffected or in individuals affected by various progeroid features (Hisama et al 2011;Lessel et al 2014bLessel et al , 2017bMarbach et al 2019).…”

“…Segmental progeroid syndromes, defined as syndromes with signs of premature aging affecting more than one tissue or organ (Martin 1978), are highly heterogenous genetic disorders. Studies utilizing next-generation sequencing (NGS) approaches have revealed several novel progeroid genes in recent years (Ehmke et al 2017;Jay et al 2016;Lessel et al 2014bLessel et al , 2017bLessel et al , 2018Marbach et al 2019;Paolacci et al 2018;Puente et al 2011;Schrauwen et al 2015;Wambach et al 2018), and broadened the spectrum of phenotypes of many known progeroid conditions and the number of associated genetic causes (Lessel et al 2014a(Lessel et al , 2015Rodriguez-Garcia et al 2018;Soria-Valles et al 2016).…”

“…Several such genes have been connected with human diseases displaying a wide variety of clinical symptoms, including muscular dystrophies, cardiomyopathies, lipodystrophies, skeletal anomalies, anomalies of the skin, cataracts, neuropathies, leukodystrophies, Pelger-Huet anomaly, and progeroid features. Examples include LMNA (MIM: 150330) (Alastalo et al 2015;Bonne et al 1999; Cao and Hegele 1 3 2000; Chen et al 2003;De Sandre-Giovannoli et al 2002Eriksson et al 2003;Fatkin et al 1999;Hisama et al 2011;Moulson et al 2007;Muchir et al 2000;Novelli et al 2002;Quijano-Roy et al 2008;Saha et al 2010), EMD (MIM: 3003849) (Bione et al 1994), LBR (MIM: 600024) (Hoffmann et al 2002), LMNB1 (MIM: 150340) (Padiath et al 2006), SYNE1 (MIM: 608441) (Gros-Louis et al 2007;Zhang et al 2007), SYNE2 (MIM: 608442) (Zhang et al 2007), ZMPSTE24 (MIM: 606480) (Agarwal et al 2003;Navarro et al 2004), LEMD2 (MIM: 616312) (Boone et al 2016;Marbach et al 2019), LEMD3 (MIM: 607844) (Hellemans et al 2004), and BANF1 (MIM: 603811) (Puente et al 2011).…”

Hereditary Syndromes With Signs of Premature Aging

“…In the further course of the disease, patients often develop bilateral cataract, type 2 diabetes, skin ulcers (typically around the ankle), osteoporosis (especially of the long bones), calcification in the Achilles tendon, hypogonadism, atherosclerosis of the coronary arteries with increased risk of myocardial infarction, as well as cancers, such as soft-tissue sarcoma, osteosarcoma, melanoma, and thyroid cancer, which are rather rare in the general population (Table). The most common causes of death are cardiovascular disease and cancer; the average life expectancy is 54 years (17,18 (4,25,(36)(37)(38). Likewise, besides the two infantile SPS discussed here, there are numerous other syndromes with childhood onset, which could not be described in detail, again for lack of space.…”

Artificial Intelligence (AI) in Rare Diseases: Is the Future Brighter?

“…Several studies have employed DeepGestalt to diagnose rare syndromes with a moderate [46] to high degree of success, namely, Cornelia de Lange syndrome (ORPHA: 199) [47], Emanuel syndrome (ORPHA:96170), and Pallister-Killian syndrome (ORPHA: 884) [48]. Besides diagnosis, DeepGestalt can also be applied to discover new RDs [49].…”