PEDIA: prioritization of exome data by image analysis.

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.

A second cohort of CHD3 patients expands the molecular mechanisms known to cause Snijders Blok-Campeau syndrome.

There has been one previous report of a cohort of patients with variants in Chromodomain Helicase DNA-binding 3 (CHD3), now recognized as Snijders Blok-Campeau syndrome. However, with only three previously-reported patients with variants outside the ATPase/helicase domain, it was unclear if variants outside of this domain caused a clinically similar phenotype. We have analyzed 24 new patients with CHD3 variants, including nine outside the ATPase/helicase domain. All patients were detected with unbiased molecular genetic methods. There is not a significant difference in the clinical or facial features of patients with variants in or outside this domain. These additional patients further expand the clinical and molecular data associated with CHD3 variants. Importantly we conclude that there is not a significant difference in the phenotypic features of patients with various molecular disruptions, including whole gene deletions and duplications, and missense variants outside the ATPase/helicase domain. This data will aid both clinical geneticists and molecular geneticists in the diagnosis of this emerging syndrome.

Transmission of a TP53 germline mutation from unaffected male carrier associated with pediatric glioblastoma in his child and gestational choriocarcinoma in his female partner.

Li-Fraumeni syndrome (LFS) is an autosomal dominant cancer predisposition syndrome caused by germline alterations in the tumor suppressor gene TP53 LFS is associated with numerous malignancies including astrocytoma. Sanger sequencing and chromosomal microarray studies of blood and tumor tissue from a 4-yr-old boy with glioblastoma demonstrated a germline TP53 mutation with loss of heterozygosity for the short arm of Chromosome 17 as the second inactivating event in the tumor. There was no family history of LFS, but the child's mother had recently died from metastatic choriocarcinoma after antecedent normal term delivery of a then 6-mo-old daughter. The choriocarcinoma contained the same TP53 mutation detected in the proband and the 6-mo-old daughter was confirmed to be a carrier. Unexpectedly, the germline TP53 mutation was found to be inherited from the unaffected father. We report here the second genetically confirmed case of TP53-mutated choriocarcinoma in the partner of an LFS patient. Based on this case and recent literature, female partners of LFS patients may have increased risk of choriocarcinoma due to transmission of germline TP53 mutation from male carriers. Although the Toronto protocol has established an effective approach to detect tumors and improve survival in children and adults with LFS, there is a need to expand the current criteria to include surveillance of female partners of LFS patients for choriocarcinoma and other gestational trophoblastic disease. Recognition of this unique mode of transmission of TP53 mutations should be considered in genetic counseling for cancer risk assessment and family planning.