Evaluation of deep learning-based feature selection for single-cell RNA sequencing data analysis.

BACKGROUND: Feature selection is an essential task in single-cell RNA-seq (scRNA-seq) data analysis and can be critical for gene dimension reduction and downstream analyses, such as gene marker identification and cell type classification. Most popular methods for feature selection from scRNA-seq data are based on the concept of differential distribution wherein a statistical model is used to detect changes in gene expression among cell types. Recent development of deep learning-based feature selection methods provides an alternative approach compared to traditional differential distribution-based methods in that the importance of a gene is determined by neural networks. RESULTS: In this work, we explore the utility of various deep learning-based feature selection methods for scRNA-seq data analysis. We sample from Tabula Muris and Tabula Sapiens atlases to create scRNA-seq datasets with a range of data properties and evaluate the performance of traditional and deep learning-based feature selection methods for cell type classification, feature selection reproducibility and diversity, and computational time. CONCLUSIONS: Our study provides a reference for future development and application of deep learning-based feature selection methods for single-cell omics data analyses.

Moonlighting functions of the ubiquitin-like protein, Hub1/UBL-5.

The faithful splicing of pre-mRNA is critical for accurate gene expression. Dysregulation of pre-mRNA splicing has been associated with several human diseases including cancer. The ubiquitin-like protein Hub1/UBL5 binds to the substrates non-covalently and promotes pre-mRNA splicing. Additionally, UBL5 promotes the common fragile sites stability and the Fanconi anemia pathway of DNA damage repair. These functions strongly suggests that UBL5 could potentially be implicated in cancer. Therefore, we analyzed the UBL5 expression in TCGA tumor sample datasets and observed the differences between tumor and normal tissues among different tumor subtypes. We have noticed the alteration frequency of UBL5 in TCGA tumor samples. Altogether, this review summarizes the UBL5 functions and discusses its putative role in tumorigenesis.

3DVizSNP: a tool for rapidly visualizing missense mutations identified in high throughput experiments in iCn3D.

BACKGROUND: High throughput experiments in cancer and other areas of genomic research identify large numbers of sequence variants that need to be evaluated for phenotypic impact. While many tools exist to score the likely impact of single nucleotide polymorphisms (SNPs) based on sequence alone, the three-dimensional structural environment is essential for understanding the biological impact of a nonsynonymous mutation. RESULTS: We present a program, 3DVizSNP, that enables the rapid visualization of nonsynonymous missense mutations extracted from a variant caller format file using the web-based iCn3D visualization platform. The program, written in Python, leverages REST APIs and can be run locally without installing any other software or databases, or from a webserver hosted by the National Cancer Institute. It automatically selects the appropriate experimental structure from the Protein Data Bank, if available, or the predicted structure from the AlphaFold database, enabling users to rapidly screen SNPs based on their local structural environment. 3DVizSNP leverages iCn3D annotations and its structural analysis functions to assess changes in structural contacts associated with mutations. CONCLUSIONS: This tool enables researchers to efficiently make use of 3D structural information to prioritize mutations for further computational and experimental impact assessment. The program is available as a webserver at https://analysistools.cancer.gov/3dvizsnp or as a standalone python program at https://github.com/CBIIT-CGBB/3DVizSNP .

Integrated Bioinformatics Analysis Identifies Crucial Biochemical Processes Shared between Pancreatitis and Pancreatic Ductal Adenocarcinoma.

BACKGROUND: Pancreatic ductal adenocarcinoma (PDAC) is a highly aggressive malignancy associated with rapid progression and an abysmal prognosis. Previous research has shown that chronic pancreatitis can significantly increase the risk of developing PDAC. The overarching hypothesis is that some of the biological processes disrupted during the inflammatory stage tend to show significant dysregulation, even in cancer. This might explain why chronic inflammation increases the risk of carcinogenesis and uncontrolled proliferation. Here, we try to pinpoint such complex processes by comparing the expression profiles of pancreatitis and PDAC tissues. METHODS: We analyzed a total of six gene expression datasets retrieved from the EMBL-EBI ArrayExpress and NCBI GEO databases, which included 306 PDAC, 68 pancreatitis and 172 normal pancreatic samples. The disrupted genes identified were used to perform downstream analysis for ontology, interaction, enriched pathways, potential druggability, promoter methylation, and the associated prognostic value. Further, we performed expression analysis based on gender, patient's drinking habit, race, and pancreatitis status. RESULTS: Our study identified 45 genes with altered expression levels shared between PDAC and pancreatitis. Over-representation analysis revealed that protein digestion and absorption, ECM-receptor interaction, PI3k-Akt signaling, and proteoglycans in cancer pathways as significantly enriched. Module analysis identified 15 hub genes, of which 14 were found to be in the druggable genome category. CONCLUSION: In summary, we have identified critical genes and various biochemical processes disrupted at a molecular level. These results can provide valuable insights into certain events leading to carcinogenesis, and therefore help identify novel therapeutic targets to improve PDAC treatment in the future.