No abstract

Background: New genome sequencing technologies with enhanced diagnostic efficiency have emerged. Rapid and timely diagnosis of treatable rare genetic diseases can alter their medical management and clinical course. However, multiple factors, including ethical issues, must be considered. We designed a targeted sequencing platform to avoid ethical issues and reduce the turnaround time.Methods: We designed an automated sequencing platform using dried blood spot samples and a NEOseq_ACTION panel comprising 254 genes associated with Mendelian diseases having curable or manageable treatment options. Retrospective validation was performed using data from 24 genetically and biochemically confirmed patients. Prospective validation was performed using data from 111 patients with suspected actionable genetic diseases.Results: In prospective clinical validation, 13.5% patients presented with medically actionable diseases, including short-or medium-chain acyl-CoA dehydrogenase deficiencies (N = 6), hyperphenylalaninemia (N = 2), mucopolysaccharidosis type IVA (N = 1), alpha thalassemia (N = 1), 3-methylcrotonyl-CoA carboxylase 2 deficiency (N = 1), propionic acidemia (N = 1), glycogen storage disease, type IX(a) (N = 1), congenital myasthenic syndrome (N = 1), and citrullinemia, type II (N = 1). Using the automated analytic pipeline, the turnaround time from blood collection to result reporting was < 4 days.Conclusions: This pilot study evaluated the possibility of rapid and timely diagnosis of treatable rare genetic diseases using a panel designed by a multidisciplinary team. The automated analytic pipeline maximized the clinical utility of rapid targeted sequencing for medically actionable genes, providing a strategy for appropriate and timely treatment of rare genetic diseases.

No abstract

No abstract

This paper proposes a new spatial regularization of Fisher linear discriminant analysis (LDA) to reduce the overfitting due to small size sample (SSS) problem in face recognition. Many regularized LDAs have been proposed to alleviate the overfitting by regularizing an estimate of the within-class scatter matrix. Spatial regularization methods have been suggested that make the discriminant vectors spatially smooth, leading to mitigation of the overfitting. As a generalized version of the spatially regularized LDA, the proposed regularized LDA utilizes the non-uniformity of spatial correlation structures in face images in adding a spatial smoothness constraint into an LDA framework. The region-dependent spatial regularization is advantageous for capturing the non-flat spatial correlation structure within face image as well as obtaining a spatially smooth projection of LDA. Experimental results on public face databases such as ORL and CMU PIE show that the proposed regularized LDA performs well especially when the number of training images per individual is quite small, compared with other regularized LDAs.