Dataset Information

Evaluating Face2Gene as a Tool to Identify Cornelia de Lange Syndrome by Facial Phenotypes.

ABSTRACT: Characteristic or classic phenotype of Cornelia de Lange syndrome (CdLS) is associated with a recognisable facial pattern. However, the heterogeneity in causal genes and the presence of overlapping syndromes have made it increasingly difficult to diagnose only by clinical features. DeepGestalt technology, and its app Face2Gene, is having a growing impact on the diagnosis and management of genetic diseases by analysing the features of affected individuals. Here, we performed a phenotypic study on a cohort of 49 individuals harbouring causative variants in known CdLS genes in order to evaluate Face2Gene utility and sensitivity in the clinical diagnosis of CdLS. Based on the profile images of patients, a diagnosis of CdLS was within the top five predicted syndromes for 97.9% of our cases and even listed as first prediction for 83.7%. The age of patients did not seem to affect the prediction accuracy, whereas our results indicate a correlation between the clinical score and affected genes. Furthermore, each gene presents a different pattern recognition that may be used to develop new neural networks with the goal of separating different genetic subtypes in CdLS. Overall, we conclude that computer-assisted image analysis based on deep learning could support the clinical diagnosis of CdLS.

SUBMITTER: Latorre-Pellicer A

PROVIDER: S-EPMC7038094 | biostudies-literature | 2020 Feb

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Evaluating Face2Gene as a Tool to Identify Cornelia de Lange Syndrome by Facial Phenotypes.

Latorre-Pellicer Ana A Ascaso Ángela Á Trujillano Laura L Gil-Salvador Marta M Arnedo Maria M Lucia-Campos Cristina C Antoñanzas-Pérez Rebeca R Marcos-Alcalde Iñigo I Parenti Ilaria I Bueno-Lozano Gloria G Musio Antonio A Puisac Beatriz B Kaiser Frank J FJ Ramos Feliciano J FJ Gómez-Puertas Paulino P Pié Juan J

International journal of molecular sciences 20200204 3

Characteristic or classic phenotype of Cornelia de Lange syndrome (CdLS) is associated with a recognisable facial pattern. However, the heterogeneity in causal genes and the presence of overlapping syndromes have made it increasingly difficult to diagnose only by clinical features. DeepGestalt technology, and its app Face2Gene, is having a growing impact on the diagnosis and management of genetic diseases by analysing the features of affected individuals. Here, we performed a phenotypic study on ...[more]

PMID: 32033219

Similar Datasets

Project description:BackgroundCornelia de Lange syndrome (CdLS) is a genetic disorder caused by variants in cohesion genes including NIPBL, SMC1A, SMC3, RAD21, and HDAC8. According to the 2018 consensus statement, a patient with clinical scored ≥ 11 points could be diagnosed as CdLS. However, some variants in non-cohesion genes rather than cohesion genes can manifest as phenotypes of CdLS.ObjectivesThis study describes six variants of non-cohesion genes (KDM6A, KMT2D, KMT2A ANKRD11, and UBE2A), and assesses the reliability of 11-points scale criteria in the clinical diagnosis of CdLS.MethodsWhole-exome sequencing (WES) was performed on six patients with features of CdLS. Phenotypic and genotypic spectra of 40 previously reported patients with features of CdLS caused by non-cohesion genes variants and 34 previously reported patients with NIPBL variants were summarized. Clinical score comparison among patients with NIPBL variants versus those with variants in non-cohesin genes was performed.ResultsVariants in non-cohesion genes were found in six patients [KMT2A (n = 2), KMT2D, ANKRD11, KDM6A, and UBE2A]. Of them, four variants (KMT2A c.7789C > T, ANKRD11 c.1757_1776del, KDM6A c.655-1G > A, and UBE2A c.439C > T) were novel. Combining with previously reported cases, 46 patients with phenotypes of CdLS caused by variants in 20 non-cohesion genes are now reported. From this total cohort, the average clinical score of patients in ANKRD11 cohort, SETD5 cohort, and AFF4 cohort was statistically lower than those in NIPBL cohort (8.92 ± 1.77 vs. 12.23 ± 2.58, 7.33 ± 2.52 vs. 12.23 ± 2.58, 5.33 ± 1.53 vs. 12.23 ± 2.58; p < 0.05). The average clinical score of KMT2A cohort, EP300 cohort, and NIPBL cohort had not significantly different from (11 ± 2.19 vs. 12.23 ± 2.58, 10 ± 4.58 vs. 12.23 ± 2.58; p > 0.05).ConclusionWe described 4 novel variants of non-cohesion genes in six Chinese patients with phenotypes of CdLS. Of note, three genes (KMT2D, KDM6A, and UBE2A) causing features of CdLS have never been reported. The proposed clinical criteria for CdLS needed to be updated and refined, insofar as WES was necessary to confirm the diagnosis of CdLS. Our study expanded the spectra of non-cohesion genetic variations in patients with features of CdLS.

Dataset Information

Evaluating Face2Gene as a Tool to Identify Cornelia de Lange Syndrome by Facial Phenotypes.

Publications

Evaluating Face2Gene as a Tool to Identify Cornelia de Lange Syndrome by Facial Phenotypes.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets