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.

Neuroblastoma (NB) is the most common malignant tumor originating from the extracranial sympathetic nervous system in children. The molecular mechanisms underlying this disease are complex, and not completely understood. Quantitative real-time PCR (qRT-PCR) was applied to quantify the expression of miR-20a-5p and its target gene ATG7 in clinical NB tissues. The biological function of miR-20a-5p and ATG7 in SH-SY5Y cells was investigated through in vitro studies (Real-Time cell kinetic analyzer, colony formation assay, caspase-Glo 3/7 assay and western blotting). The luciferase reporter assay was conducted to verify the biological relationship between miR-20a-5p and ATG7. Here we found that miR-20a-5p expression was significantly downregulated whereas its target autophagy-related gene 7 (ATG7) was increased along with clinical staging of NB progression. Correlation analysis showed that miR-20a-5p had a negative correlation trend with ATG7. In SH-SY5Y cells, forced expression of miR-20a-5p suppressed ATG7 expression, autophagy initiation and cellular proliferation while promoted apoptosis, suggesting a potential association between miR-20a-5p and ATG7. Further bioinformatic target prediction combined with protein expression and luciferase reporter assay verified that miR-20a-5p inhibited ATG7 by directly binding to its 3′-UTR, confirming the involvement of miR-20a-5p in the regulation of ATG7 in NB. These results clarified that miR-20a-5p inhibited cell proliferation and promoted apoptosis through negative regulation of ATG7 and thus autophagy suppression in SH-SY5Y cells. Therefore, defining the context-specific roles of autophagy in NB and regulatory mechanisms involved will be critical for developing autophagy-targeted therapeutics against NB. Both miR-20a-5p and ATG7 would be potential therapeutic targets for future NB treatment.

Rare diseases affect over a hundred million people worldwide, most of these patients are not accurately diagnosed and effectively treated. The limited knowledge of rare diseases forms the biggest obstacle for improving their treatment. Detailed clinical phenotyping is considered as a keystone of deciphering genes and realizing the precision medicine for rare diseases. Here, we preset a standardized system for various types of rare diseases, called encyclopedia of Rare disease Annotations for Precision Medicine (eRAM). eRAM was built by text-mining nearly 10 million scientific publications and electronic medical records, and integrating various data in existing recognized databases (such as Unified Medical Language System (UMLS), Human Phenotype Ontology, Orphanet, OMIM, GWAS). eRAM systematically incorporates currently available data on clinical manifestations and molecular mechanisms of rare diseases and uncovers many novel associations among diseases. eRAM provides enriched annotations for 15 942 rare diseases, yielding 6147 human disease related phenotype terms, 31 661 mammalians phenotype terms, 10,202 symptoms from UMLS, 18 815 genes and 92 580 genotypes. eRAM can not only provide information about rare disease mechanism but also facilitate clinicians to make accurate diagnostic and therapeutic decisions towards rare diseases. eRAM can be freely accessed at http://www.unimd.org/eram/.