fThe epithelial-to-mesenchymal transition (EMT) is an essential biological process during embryonic development that is also implicated in cancer metastasis. While the transcriptional regulation of EMT has been well studied, the role of alternative splicing (AS) regulation in EMT remains relatively uncharacterized. We previously showed that the epithelial cell-type-specific proteins epithelial splicing regulatory proteins 1 (ESRP1) and ESRP2 are important for the regulation of many AS events that are altered during EMT. However, the contributions of the ESRPs and other splicing regulators to the AS regulatory network in EMT require further investigation. Here, we used a robust in vitro EMT model to comprehensively characterize splicing switches during EMT in a temporal manner. These investigations revealed that the ESRPs are the major regulators of some but not all AS events during EMT. We determined that the splicing factor RBM47 is downregulated during EMT and also regulates numerous transcripts that switch splicing during EMT. We also determined that Quaking (QKI) broadly promotes mesenchymal splicing patterns. Our study highlights the broad role of posttranscriptional regulation during the EMT and the important role of combinatorial regulation by different splicing factors to fine tune gene expression programs during these physiological and developmental transitions.A lternative splicing (AS) is a process by which a single gene transcript can be differentially spliced to yield numerous splice variants that can encode different protein isoforms and thereby greatly expand the protein coding capacity of the genome. Nearly all human genes are alternatively spliced, and cell-typespecific protein isoforms have been shown to be functionally essential for cell fate and viability (1-3). This process is under complex regulation by various cis elements in pre-mRNAs and their cognate binding partners, mainly RNA-binding proteins (RBPs). Splicing-regulatory RBPs recruited to their respective binding sites can have positive or negative effects on the splicing of different exons or splice sites. Many RBPs with largely ubiquitous expression in different tissues and cells have been shown to have broad impacts on splicing and important cell functions, such as SR and hnRNP protein families (4). However, several tissue-specific RBPs, such as NOVA, PTBP2 (nPTB), MBNL, and RBFOX proteins, have recently been described as having important roles as essential regulators of tissue-or cell-type-specific splicing (5-9). In order to further define a "splicing code" that controls broad patterns of tissue-specific splicing, as well as those that occur during developmental transitions, it is essential to characterize in greater detail how these tissue-specific regulators fine-tune AS programs combinatorially with more ubiquitously expressed splicing regulators (10).The epithelial-to-mesenchymal transition (EMT) is a process by which epithelial cells transdifferentiate into mesenchymal cells, which involves extensive changes at the cellular ...

SUMMARY Alternative splicing (AS) plays a critical role in cell fate transitions, development, and disease. Recent studies have shown that AS also influences pluripotency and somatic cell reprogramming. We profiled transcriptome-wide AS changes that occur during reprogramming of fibroblasts to pluripotency. This analysis revealed distinct phases of AS, including a splicing program that is unique to transgene-independent induced pluripotent stem cells (iPSCs). Changes in the expression of AS factors Zcchc24, Esrp1, Mbnl1/2, and Rbm47 were demonstrated to contribute to phase-specific AS. RNA-binding motif enrichment analysis near alternatively spliced exons provided further insight into the combinatorial regulation of AS during reprogramming by different RNA-binding proteins. Ectopic expression of Esrp1 enhanced reprogramming, in part by modulating the AS of the epithelial specific transcription factor Grhl1. These data represent a comprehensive temporal analysis of the dynamic regulation of AS during the acquisition of pluripotency.

Identifying genes associated with Parkinson's disease plays an extremely important role in the diagnosis and treatment of Parkinson's disease. In recent years, based on the guilt-by-association hypothesis, many methods have been proposed to predict disease-related genes, but few of these methods are designed or used for Parkinson's disease gene prediction. In this paper, we propose a novel prediction method for Parkinson's disease gene prediction, named N2A-SVM. N2A-SVM includes three parts: extracting features of genes based on network, reducing the dimension using deep neural network, and predicting Parkinson's disease genes using a machine learning method. The evaluation test shows that N2A-SVM performs better than existing methods. Furthermore, we evaluate the significance of each step in the N2A-SVM algorithm and the influence of the hyper-parameters on the result. In addition, we train N2A-SVM on the recent dataset and used it to predict Parkinson's disease genes. The predicted top-rank genes can be verified based on literature study.

Differential expression (DE) analysis and gene set enrichment (GSE) analysis are commonly applied in single cell RNA sequencing (scRNA-seq) studies. Here, we develop an integrative and scalable computational method, iDEA, to perform joint DE and GSE analysis through a hierarchical Bayesian framework. By integrating DE and GSE analyses, iDEA can improve the power and consistency of DE analysis and the accuracy of GSE analysis. Importantly, iDEA uses only DE summary statistics as input, enabling effective data modeling through complementing and pairing with various existing DE methods. We illustrate the benefits of iDEA with extensive simulations. We also apply iDEA to analyze three scRNA-seq data sets, where iDEA achieves up to five-fold power gain over existing GSE methods and up to 64% power gain over existing DE methods. The power gain brought by iDEA allows us to identify many pathways that would not be identified by existing approaches in these data.

Benchmarked approaches for reconstruction of in vitro cell lineages and in silico models of C. elegans and M. musculus developmental trees Graphical abstract Highlights d We organized a DREAM challenge to benchmark methods of cell lineage reconstruction d Using experimental, in silico datasets as ground-truth trees of 10 2 , 10 3 , and 10 4 cells d Smaller trees allowed the training of a machine-learning decision tree approach d These results delineate a potential way forward for solving larger cell lineage trees

Motivation A microRNA (miRNA) is a type of non-coding RNA, which plays important roles in many biological processes. Lots of studies have shown that miRNAs are implicated in human diseases, indicating that miRNAs might be potential biomarkers for various types of diseases. Therefore, it is important to reveal the relationships between miRNAs and diseases/phenotypes. Results We propose a novel learning-based framework, MDA-CNN, for miRNA-disease association identification. The model first captures interaction features between diseases and miRNAs based on a three-layer network including disease similarity network, miRNA similarity network and protein-protein interaction network. Then, it employs an auto-encoder to identify the essential feature combination for each pair of miRNA and disease automatically. Finally, taking the reduced feature representation as input, it uses a convolutional neural network to predict the final label. The evaluation results show that the proposed framework outperforms some state-of-the-art approaches in a large margin on both tasks of miRNA-disease association prediction and miRNA-phenotype association prediction. Availability and implementation The source code and data are available at https://github.com/Issingjessica/MDA-CNN. Supplementary information Supplementary data are available at Bioinformatics online.

Accurately identifying potential drug–target interactions (DTIs) is a key step in drug discovery. Although many related experimental studies have been carried out for identifying DTIs in the past few decades, the biological experiment-based DTI identification is still timeconsuming and expensive. Therefore, it is of great significance to develop effective computational methods for identifying DTIs. In this paper, we develop a novel ‘end-to-end’ learning-based framework based on heterogeneous ‘graph’ convolutional networks for ‘DTI’ prediction called end-to-end graph (EEG)-DTI. Given a heterogeneous network containing multiple types of biological entities (i.e. drug, protein, disease, side-effect), EEG-DTI learns the low-dimensional feature representation of drugs and targets using a graph convolutional networks-based model and predicts DTIs based on the learned features. During the training process, EEG-DTI learns the feature representation of nodes in an end-to-end mode. The evaluation test shows that EEG-DTI performs better than existing state-of-art methods. The data and source code are available at: https://github.com/MedicineBiology-AI/EEG-DTI.

BackgroundIdentifying the genes associated to human diseases is crucial for disease diagnosis and drug design. Computational approaches, esp. the network-based approaches, have been recently developed to identify disease-related genes effectively from the existing biomedical networks. Meanwhile, the advance in biotechnology enables researchers to produce multi-omics data, enriching our understanding on human diseases, and revealing the complex relationships between genes and diseases. However, none of the existing computational approaches is able to integrate the huge amount of omics data into a weighted integrated network and utilize it to enhance disease related gene discovery.ResultsWe propose a new network-based disease gene prediction method called SLN-SRW (Simplified Laplacian Normalization-Supervised Random Walk) to generate and model the edge weights of a new biomedical network that integrates biomedical data from heterogeneous sources, thus far enhancing the disease related gene discovery.ConclusionsThe experiment results show that SLN-SRW significantly improves the performance of disease gene prediction on both the real and the synthetic data sets.Electronic supplementary materialThe online version of this article (doi:10.1186/s12864-016-3263-4) contains supplementary material, which is available to authorized users.