Systematically Analyzing the Pathogenic Variations for Acute Intermittent Porphyria.

The rare autosomal dominant disorder acute intermittent porphyria (AIP) is caused by the deficient activity of hydroxymethylbilane synthase (HMBS). The symptoms of AIP are acute neurovisceral attacks which are induced by the dysfunction of heme biosynthesis. To better interpret the underlying mechanism of clinical phenotypes, we collected 117 HMBS gene mutations from reported individuals with AIP and evaluated the mutations' impacts on the corresponding protein structure and function. We found that several mutations with most severe clinical symptoms are located at dipyromethane cofactor (DPM) binding domain of HMBS. Mutations on these residues likely significantly influence the catalytic reaction. To infer new pathogenic mutations, we evaluated the pathogenicity for all the possible missense mutations of HMBS gene with different bioinformatic prediction algorithms, and identified 34 mutations with serious pathogenicity and low allele frequency. In addition, we found that gene PPARA may also play an important role in the mechanisms of AIP attacks. Our analysis about the distribution frequencies of the 23 variations revealed different distribution patterns among eight ethnic populations, which could help to explain the genetic basis that may contribute to population disparities in AIP prevalence. Our systematic analysis provides a better understanding for this disease and helps for the diagnosis and treatment of AIP.

Deep Learning-Based Multi-Omics Data Integration Reveals Two Prognostic Subtypes in High-Risk Neuroblastoma.

High-risk neuroblastoma is a very aggressive disease, with excessive tumor growth and poor outcomes. A proper stratification of the high-risk patients by prognostic outcome is important for treatment. However, there is still a lack of survival stratification for the high-risk neuroblastoma. To fill the gap, we adopt a deep learning algorithm, Autoencoder, to integrate multi-omics data, and combine it with K-means clustering to identify two subtypes with significant survival differences. By comparing the Autoencoder with PCA, iCluster, and DGscore about the classification based on multi-omics data integration, Autoencoder-based classification outperforms the alternative approaches. Furthermore, we also validated the classification in two independent datasets by training machine-learning classification models, and confirmed its robustness. Functional analysis revealed that MYCN amplification was more frequently occurred in the ultra-high-risk subtype, in accordance with the overexpression of MYC/MYCN targets in this subtype. In summary, prognostic subtypes identified by deep learning-based multi-omics integration could not only improve our understanding of molecular mechanism, but also help the clinicians make decisions.