Xiangtao Chen

Collective Prediction of Disease-Associated miRNAs Based on Transduction Learning

The discovery of human disease-related miRNA is a challenging problem for complex disease biology research. For existing computational methods, it is difficult to achieve excellent performance with sparse known miRNA-disease association verified by biological experiment. Here, we develop CPTL, a Collective Prediction based on Transduction Learning, to systematically prioritize miRNAs related to disease. By combining disease similarity, miRNA similarity with known miRNA-disease association, we construct a miRNA-disease network for predicting miRNA-disease association. Then, CPTL calculates relevance score and updates the network structure iteratively, until a convergence criterion is reached. The relevance score of node including miRNA and disease is calculated by the use of transduction learning based on its neighbors. The network structure is updated using relevance score, which increases the weight of important links. To show the effectiveness of our method, we compared CPTL with existing methods based on HMDD datasets. Experimental results indicate that CPTL outperforms existing approaches in terms of AUC, precision, recall, and F1-score. Moreover, experiments performed with different number of iterations verify that CPTL has good convergence. Besides, it is analyzed that the varying of weighted parameters affect predicted results. Case study on breast cancer has further confirmed the identification ability of CPTL.

Seeksv: an accurate tool for somatic structural variation and virus integration detection

Motivation: Many forms of variations exist in the human genome including single nucleotide polymorphism, small insert/deletion (DEL) (indel) and structural variation (SV). Somatically acquired SV may regulate the expression of tumor-related genes and result in cell proliferation and uncontrolled growth, eventually inducing tumor formation. Virus integration with host genome sequence is a type of SV that causes the related gene instability and normal cells to transform into tumor cells. Cancer SVs and viral integration sites must be discovered in a genome-wide scale for clarifying the mechanism of tumor occurrence and development. Results: In this paper, we propose a new tool called seeksv to detect somatic SVs and viral integration events. Seeksv simultaneously uses split read signal, discordant paired-end read signal, read depth signal and the fragment with two ends unmapped. Seeksv can detect DEL, insertion, inversion and inter-chromosome transfer at single-nucleotide resolution. Different types of sequencing data, such as single-end sequencing data or paired-end sequencing data can accommodate to detect SV. Seeksv develops a rescue model for SV with breakpoints located in sequence homology regions. Results on simulated and real data from the 1000 Genomes Project and esophageal squamous cell carcinoma samples show that seeksv has higher efficiency and precision compared with other similar software in detecting SVs. For the discovery of hepatitis B virus integration sites from probe capture data, the verified experiments show that more than 90% viral integration sequences detected by seeksv are true. Availability and Implementation: seeksv is implemented in C ++ and can be downloaded from https://github.com/qkl871118/seeksv. Contact: dragonbw@163.com Supplementary information: Supplementary data are available at Bioinformatics online.

A path-based measurement for human miRNA functional similarities using miRNA-disease associations.

Compared with the sequence and expression similarity, miRNA functional similarity is so important for biology researches and many applications such as miRNA clustering, miRNA function prediction, miRNA synergism identification and disease miRNA prioritization. However, the existing methods always utilized the predicted miRNA target which has high false positive and false negative to calculate the miRNA functional similarity. Meanwhile, it is difficult to achieve high reliability of miRNA functional similarity with miRNA-disease associations. Therefore, it is increasingly needed to improve the measurement of miRNA functional similarity. In this study, we develop a novel path-based calculation method of miRNA functional similarity based on miRNA-disease associations, called MFSP. Compared with other methods, our method obtains higher average functional similarity of intra-family and intra-cluster selected groups. Meanwhile, the lower average functional similarity of inter-family and inter-cluster miRNA pair is obtained. In addition, the smaller p-value is achieved, while applying Wilcoxon rank-sum test and Kruskal-Wallis test to different miRNA groups. The relationship between miRNA functional similarity and other information sources is exhibited. Furthermore, the constructed miRNA functional network based on MFSP is a scale-free and small-world network. Moreover, the higher AUC for miRNA-disease prediction indicates the ability of MFSP uncovering miRNA functional similarity.

Gene Regulatory Network Inferences Using a Maximum-Relevance and Maximum-Significance Strategy.

Recovering gene regulatory networks from expression data is a challenging problem in systems biology that provides valuable information on the regulatory mechanisms of cells. A number of algorithms based on computational models are currently used to recover network topology. However, most of these algorithms have limitations. For example, many models tend to be complicated because of the “large p, small n” problem. In this paper, we propose a novel regulatory network inference method called the maximum-relevance and maximum-significance network (MRMSn) method, which converts the problem of recovering networks into a problem of how to select the regulator genes for each gene. To solve the latter problem, we present an algorithm that is based on information theory and selects the regulator genes for a specific gene by maximizing the relevance and significance. A first-order incremental search algorithm is used to search for regulator genes. Eventually, a strict constraint is adopted to adjust all of the regulatory relationships according to the obtained regulator genes and thus obtain the complete network structure. We performed our method on five different datasets and compared our method to five state-of-the-art methods for network inference based on information theory. The results confirm the effectiveness of our method.

A modified PBI approach for multi-objective optimization with complex Pareto fronts

Abstract The penalty-based boundary intersection (PBI) approach is widely used in the decomposition-based multi-objective evolutionary algorithm (MOEA/D). Generally, a uniform distribution of weight vectors in PBI approach will lead to a set of evenly distributed solutions on the Pareto-optimal front (POF), but this approach cannot work well in practice when the target multi-objective optimization problem (MOP) has a complex POF. For example, the POF may have disconnected regions and a long tail and a sharp peak and a degenerate geometry, which significantly degrades the performance of the original MOEA/D. This paper proposes a modified PBI (MPBI) approach and a strategy of adjusting reference points (ARP) to handle these MOPs with complex fronts. A two-stage strategy is adopted in the proposed algorithm. The first stage is to determine a hyperplane based on the modified PBI approach, so that the projection points derived from the solutions obtained in second stage to this hyperplane are all in the first quadrant. Exploring those regions where the solution exists is also a key task in this stage. The second stage is to adjust the reference points periodically so that the reference points can be redistributed adaptively to improve the distribution of solutions. The framework of the proposed algorithm is based on θ -DEA and named NSGA-MPBI. Some widely used test instances and three many-objective MOPs with complex POFs are employed in the experiments. The experimental results indicate that NSGA-MPBI outperforms the state-of-the-art algorithms.

A Novel Group Wise-Based Method for Calculating Human miRNA Functional Similarity

The measurement of human miRNA functional similarity is an important research for studying miRNA-related therapeutic strategy. Pair wise-based approaches using disease-miRNA associations have recently become a popular tool for inferring miRNA functional similarity. However, the miRNA functional similarity is vitally influenced by calculation of the disease semantic similarity in those methods. Moreover, integrating information content with hierarchical structure can improve calculation of the miRNA functional similarity. Therefore, we propose a group-wise method for inferring the miRNA functional similarity, named GMFS. First, the information content is computed by using disease MeSH descriptors to describe the specific of disease. Second, the acquirement of disease feature is based on the hierarchical structure as well as the information content of disease. Finally, the miRNA functional similarity is measured by using both miRNA-disease associations and the disease feature. To validate the effectiveness of the GMFS, we compare our method with several existing methods in terms of the average similarity of intra-family, inter-family, intra-cluster, and inter-cluster groups. The

Similarity Measure by Aggregating Shared Emerging Patterns

p

Semi-supervised prediction of human miRNA-disease association based on graph regularization framework in heterogeneous networks

-values achieved by non-parametric test further indicate that the GMFS could have reliable miRNA similarity. Besides, the correlation between other biological information of the miRNA and the miRNA functional similarity is analyzed. The influence of the varying parameter is shown. We also demonstrate that the constructed network based on the miRNA functional similarity is a scale-free and small-world network. The superior performance on uncovering lymphoma-related miRNAs explains the ability of the GMFS inferring the miRNA functional similarity.

Mining strong jumping emerging patterns with a novel list data structure

The shared emerging patterns (SEPs) is a special form of emerging patterns(EPs). In the field of data mining, EPs represents the knowledge of strong characters in one dataset and it is very important for building classifier. However, SEPs represents the shared knowledge of strong characters in two or more datasets and it has great potential for applying in analogy and transfer learning. When the training data is lacking, in order to save cost, we need to find the existing similar data and not to mark new data. In this case, similarity measure of dataset has great significance. In this paper, a novel application of SEPs is proposed that it used to measure similarity of two datasets, the quality and quantity of SEPs are two parameters for the contribution that used to measure the similarity. For lack of samples in a certain field, according to the similarity measure we obtain known similar samples.

Finding Contrast Patterns in Imbalanced Classification based on Sliding Window

Abstract MicroRNAs (miRNAs) play important roles in the various pathogenesis of diseases. However, experimental prediction of associations between microRNAs and diseases remains challenging. Furthermore, there are several critical limitations of previous computational methods in miRNA-disease network for uncovering the potential miRNA-disease associations. Some existing methods are not applicable for diseases without any known miRNA. Meanwhile, several other methods have failed to prioritize associations for all diseases simultaneously. Therefore, it is essential to develop an algorithm to solve these problems effectively, which can identify reliable disease miRNA candidates using existing miRNA-disease associations verified by biological experiment. In this study, we propose a novel semi-supervised prediction method of MiRNA-Disease Association based on Graph Regularization Framework (MDAGRF) in miRNA-disease network. Our method achieves higher average AUC and AUPR of 19 human diseases associating with at least 80 miRNAs based on five-fold cross validation. In addition, the performance of our method is not sensitive to the selections of parameters. Compared with other existing global methods, MDAGRF could obtain better prediction result for all diseases simultaneously as well. Moreover, diseases without any known miRNA could be effectively dealt by the proposed method.