Characterization of signature trends across the spectrum of non-alcoholic fatty liver disease using deep learning method.

AIMS: The timely diagnosis of different stages in NAFLD is crucial for disease treatment and reversal. We used hepatocellular ballooning to determine different NAFLD stages. MAIN METHODS: We analyzed differentially expressed genes (DEGs) in 78 patients with NAFLD and in healthy controls from previously published RNA-seq data. We identified two expression types in NAFLD progression, calculated the predictive power of candidate genes, and validated them in an independent cohort. We also performed cancer studies with these candidates retrieved from the Cancer Genome Atlas. KEY FINDINGS: We identified 103 DEGs in NAFLD patients compared to healthy controls: 75 genes gradually increased or decreased in the NAFLD stage, whereas 28 genes showed differences only in NASH. The former were enriched in negative regulation and binding-related genes; the latter were involved in positive regulation and cell proliferation. Feature selection showed the gradual up- or down-regulation of 21 genes in NASH compared to controls; 18 were highly expressed only in NASH. Using deep-learning method with subset of features from lasso regression, we obtained reliable determination performance in NAFL and NASH (accuracy: 0.857) and validated these genes using an independent cohort (accuracy: 0.805). From cancer studies, we identified significant differential expression of several candidate genes in LIHC; 5 genes were gradually up-regulated and 6 showing high expression only in NASH were influential to patient survival. SIGNIFICANCE: The identified biomolecular signatures may determine the spectrum of NAFLD and its relationship with HCC, improving clinical diagnosis and prognosis and enabling a therapeutic intervention for NAFLD.

Development of a quantitative prediction algorithm for target organ-specific similarity of human pluripotent stem cell-derived organoids and cells.

Human pluripotent stem cell (hPSC)-derived organoids and cells have similar characteristics to human organs and tissues. Thus, in vitro human organoids and cells serve as a superior alternative to conventional cell lines and animal models in drug development and regenerative medicine. For a simple and reproducible analysis of the quality of organoids and cells to compensate for the shortcomings of existing experimental validation studies, a quantitative evaluation method should be developed. Here, using the GTEx database, we construct a quantitative calculation system to assess similarity to the human organs. To evaluate our system, we generate hPSC-derived organoids and cells, and detected organ similarity. To facilitate the access of our system by researchers, we develop a web-based user interface presenting similarity to the appropriate organs as percentages. Thus, this program could provide valuable information for the generation of high-quality organoids and cells and a strategy to guide proper lineage-oriented differentiation.

Characterization of terminal-ileal and colonic Crohn's disease in treatment-naïve paediatric patients based on transcriptomic profile using logistic regression.

BACKGROUND: Inflammatory bowel disease (IBD) is a chronic and idiopathic inflammatory disorder of the gastrointestinal tract and comprises ulcerative colitis (UC) and Crohn's disease (CD). Crohn's disease can affect any part of the gastrointestinal tract, but mainly the terminal ileum and colon. In the present study, we aimed to characterize terminal-ileal CD (ICD) and colonic CD (CCD) at the molecular level, which might enable a more optimized approach for the clinical care and scientific research of CD. METHODS: We analyzed differentially expressed genes in samples from 23 treatment-naïve paediatric patients with CD and 25 non-IBD controls, and compared the data with previously published RNA-Seq data using multi-statistical tests and confidence intervals. We implemented functional profiling and proposed statistical methods for feature selection using a logistic regression model to identify genes that are highly associated in ICD or CCD. We also validated our final candidate genes in independent paediatric and adult cohorts. RESULTS: We identified 550 genes specifically expressed in patients with CD compared with those in healthy controls (p < 0.05). Among these DEGs, 240 from patients with CCD were mainly involved in mitochondrial dysfunction, whereas 310 from patients with ICD were enriched in the ileum functions such as digestion, absorption, and metabolism. To choose the most effective gene set, we selected the most powerful genes (p-value ≤ 0.05, accuracy ≥ 0.8, and AUC ≥ 0.8) using logistic regression. Consequently, 33 genes were identified as useful for discriminating CD location; the accuracy and AUC were 0.86 and 0.83, respectively. We then validated the 33 genes with data from another independent paediatric cohort (accuracy = 0.93, AUC = 0.92) and adult cohort (accuracy = 0.88, AUC = 0.72). CONCLUSIONS: In summary, we identified DEGs that are specifically expressed in CCD and ICD compared with those in healthy controls and patients with UC. Based on the feature selection analysis, 33 genes were identified as useful for discriminating CCD and ICD with high accuracy and AUC, for not only paediatric patients but also independent cohorts. We propose that our approach and the final gene set are useful for the molecular classification of patients with CD, and it could be beneficial in treatments based on disease location.

A deep learning and similarity-based hierarchical clustering approach for pathological stage prediction of papillary renal cell carcinoma.

Papillary renal cell carcinoma (pRCC), which accounts for 10-15% of renal cell carcinomas, is the second most frequent renal cell carcinoma. pRCC patient classification is difficult because of disease heterogeneity, histologic subtypes, and variations in both disease progression and patient outcomes. Nevertheless, symptom-based patient classification is indispensable in deciding treatment options. Here we introduce a prediction method for distinguishing pRCC pathological tumour stages using deep learning and similarity-based hierarchical clustering approaches. Differentially expressed genes (DEGs) were identified from gene expression data of pRCC patients retrieved from TCGA. Thirty-three of these genes were distinguished based on expression in early or late stage pRCC using the Wilcoxon rank sum test, confidence interval, and LASSO regression. Then, a deep learning model was constructed to predict tumour progression with an accuracy of 0.942 and area under curve of 0.933. Furthermore, pathological sub-stage information with an accuracy of 0.857 was obtained via similarity-based hierarchical clustering using 18 DEGs between stages I and II, and 11 DEGs between stages III and IV, identified through Wilcoxon rank sum test and quantile approach. Additionally, we offer this classification process as an R function. This is the first report of a model distinguishing the pathological tumour stages of pRCC using deep learning and similarity-based hierarchical clustering methods. Our findings are potentially applicable for improving early detection and treatment of pRCC and establishing a clearer classification of the pathological stages in other tumours.

Characterization of sexual size dimorphism and sex-biased genes expression profile in the olive flounder.

Sexual size dimorphism (SSD) is a widespread phenomenon in fish species, including in the olive flounder. Although it is well established that female olive flounders acquire more bone mass than males, the underlying mechanism and timing of this SSD remains controversial. Here, the gene expression profiles of adult male and female olive flounder fish were explored to better understand the SSD mechanisms. Using RNA sequencing, a total of 4784 sex-biased differentially expressed genes (DEGs) in the fin with asymptotic growth after maturity were identified, among which growth-related factors were found. Gene ontology and pathway enrichment studies were performed to predict potential SSD-related genes and their functions. According to functional analysis, negative regulation of cell proliferation was significantly enriched in males, and anabolism related genes were highly expressed in females. In addition, pathway analysis using the Kyoto Encyclopedia of Genes and Genomes database revealed that five sexual dimorphism-related candidate genes (bambia, smurf1, dvl2, cul1a, and dvl3) were enriched in osteogenesis-contributing pathways. These results suggest that these five candidate genes may be relevant for skeletal development in olive flounders. Altogether, this study adds new knowledge for a better understanding of SSD-related growth traits in olive flounder, which can be used for enhancing aquaculture productivity with reduced production costs.

Bioinformatic analysis of regulation of natural antisense transcripts by transposable elements in human mRNA.

Non-coding RNA is no longer considered to be "junk" DNA, based on evidence uncovered in recent decades. In particular, the important role played by natural antisense transcripts (NATs) in regulating the expression of genes is receiving increasing attention. However, the regulatory mechanisms of NATs remain incompletely understood. It is well-known that the insertion of transposable elements (TEs) can affect gene transcription. Using a bioinformatics approach, we identified NATs using human mRNA sequences from the UCSC Genome Browser Database. Our in silico analysis identified 1079 NATs and 700 sense-antisense gene pairs. We identified 179 NATs that showed evidence of having been affected by TEs during cellular gene expression. These findings may provide an understanding of the complex regulation mechanisms of NATs. If our understanding of NATs as modulators of gene expression is further enhanced, we can develop ways to control gene expression.

Gene selection tool (GST): A R-based tool for genetic disorders based on the sliding-window proportion test using whole-exome sequencing data.

Whole-exome sequencing (WES) can identify causative mutations in hereditary diseases. However, WES data might have a large candidate variant list, including false positives. Moreover, in families, it is more difficult to select disease-associated variants because many variants are shared among members. To reduce false positives and extract accurate candidates, we used a multilocus variant instead of a single-locus variant (SNV). We set up a specific window to analyze the multilocus variant and devised a sliding-window approach to observe all variants. We developed the gene selection tool (GST) based on proportion tests for linkage analysis using WES data. This tool is R program coded and has high sensitivity. We tested our code to find the gene for hereditary spastic paraplegia using SNVs from a specific family and identified the gene known to cause the disease in a significant gene list. The list identified other genes that might be associated with the disease.

A liver-specific gene expression panel predicts the differentiation status of in vitro hepatocyte models.

Alternative cell sources, such as three-dimensional organoids and induced pluripotent stem cell-derived cells, might provide a potentially effective approach for both drug development applications and clinical transplantation. For example, the development of cell sources for liver cell-based therapy has been increasingly needed, and liver transplantation is performed for the treatment for patients with severe end-stage liver disease. Differentiated liver cells and three-dimensional organoids are expected to provide new cell sources for tissue models and revolutionary clinical therapies. However, conventional experimental methods confirming the expression levels of liver-specific lineage markers cannot provide complete information regarding the differentiation status or degree of similarity between liver and differentiated cell sources. Therefore, in this study, to overcome several issues associated with the assessment of differentiated liver cells and organoids, we developed a liver-specific gene expression panel (LiGEP) algorithm that presents the degree of liver similarity as a "percentage." We demonstrated that the percentage calculated using the LiGEP algorithm was correlated with the developmental stages of in vivo liver tissues in mice, suggesting that LiGEP can correctly predict developmental stages. Moreover, three-dimensional cultured HepaRG cells and human pluripotent stem cell-derived hepatocyte-like cells showed liver similarity scores of 59.14% and 32%, respectively, although general liver-specific markers were detected. CONCLUSION: Our study describes a quantitative and predictive model for differentiated samples, particularly liver-specific cells or organoids; and this model can be further expanded to various tissue-specific organoids; our LiGEP can provide useful information and insights regarding the differentiation status of in vitro liver models. (Hepatology 2017;66:1662-1674).

HEpD: a database describing epigenetic differences between Thoroughbred and Jeju horses.

With the advent of next-generation sequencing technology, genome-wide maps of DNA methylation are now available. The Thoroughbred horse is bred for racing, while the Jeju horse is a traditional Korean horse bred for racing or food. The methylation profiles of equine organs may provide genomic clues underlying their athletic traits. We have developed a database to elucidate genome-wide DNA methylation patterns of the cerebrum, lung, heart, and skeletal muscle from Thoroughbred and Jeju horses. Using MeDIP-Seq, our database provides information regarding significantly enriched methylated regions beyond a threshold, methylation density of a specific region, and differentially methylated regions (DMRs) for tissues from two equine breeds. It provided methylation patterns at 784 gene regions in the equine genome. This database can potentially help researchers identify DMRs in the tissues of these horse species and investigate the differences between the Thoroughbred and Jeju horse breeds.