Zhu-Hong You

Prediction of protein-protein interactions from amino acid sequences with ensemble extreme learning machines and principal component analysis

BackgroundProtein-protein interactions (PPIs) play crucial roles in the execution of various cellular processes and form the basis of biological mechanisms. Although large amount of PPIs data for different species has been generated by high-throughput experimental techniques, current PPI pairs obtained with experimental methods cover only a fraction of the complete PPI networks, and further, the experimental methods for identifying PPIs are both time-consuming and expensive. Hence, it is urgent and challenging to develop automated computational methods to efficiently and accurately predict PPIs.ResultsWe present here a novel hierarchical PCA-EELM (principal component analysis-ensemble extreme learning machine) model to predict protein-protein interactions only using the information of protein sequences. In the proposed method, 11188 protein pairs retrieved from the DIP database were encoded into feature vectors by using four kinds of protein sequences information. Focusing on dimension reduction, an effective feature extraction method PCA was then employed to construct the most discriminative new feature set. Finally, multiple extreme learning machines were trained and then aggregated into a consensus classifier by majority voting. The ensembling of extreme learning machine removes the dependence of results on initial random weights and improves the prediction performance.ConclusionsWhen performed on the PPI data of Saccharomyces cerevisiae, the proposed method achieved 87.00% prediction accuracy with 86.15% sensitivity at the precision of 87.59%. Extensive experiments are performed to compare our method with state-of-the-art techniques Support Vector Machine (SVM). Experimental results demonstrate that proposed PCA-EELM outperforms the SVM method by 5-fold cross-validation. Besides, PCA-EELM performs faster than PCA-SVM based method. Consequently, the proposed approach can be considered as a new promising and powerful tools for predicting PPI with excellent performance and less time.

WBSMDA: Within and Between Score for MiRNA-Disease Association prediction.

Increasing evidences have indicated that microRNAs (miRNAs) are functionally associated with the development and progression of various complex human diseases. However, the roles of miRNAs in multiple biological processes or various diseases and their underlying molecular mechanisms still have not been fully understood yet. Predicting potential miRNA-disease associations by integrating various heterogeneous biological datasets is of great significance to the biomedical research. Computational methods could obtain potential miRNA-disease associations in a short time, which significantly reduce the experimental time and cost. Considering the limitations in previous computational methods, we developed the model of Within and Between Score for MiRNA-Disease Association prediction (WBSMDA) to predict potential miRNAs associated with various complex diseases. WBSMDA could be applied to the diseases without any known related miRNAs. The AUC of 0.8031 based on Leave-one-out cross validation has demonstrated its reliable performance. WBSMDA was further applied to Colon Neoplasms, Prostate Neoplasms, and Lymphoma for the identification of their potential related miRNAs. As a result, 90%, 84%, and 80% of predicted miRNA-disease pairs in the top 50 prediction list for these three diseases have been confirmed by recent experimental literatures, respectively. It is anticipated that WBSMDA would be a useful resource for potential miRNA-disease association identification.

Long non-coding RNAs and complex diseases: from experimental results to computational models

Abstract LncRNAs have attracted lots of attentions from researchers worldwide in recent decades. With the rapid advances in both experimental technology and computational prediction algorithm, thousands of lncRNA have been identified in eukaryotic organisms ranging from nematodes to humans in the past few years. More and more research evidences have indicated that lncRNAs are involved in almost the whole life cycle of cells through different mechanisms and play important roles in many critical biological processes. Therefore, it is not surprising that the mutations and dysregulations of lncRNAs would contribute to the development of various human complex diseases. In this review, we first made a brief introduction about the functions of lncRNAs, five important lncRNA-related diseases, five critical disease-related lncRNAs and some important publicly available lncRNA-related databases about sequence, expression, function, etc. Nowadays, only a limited number of lncRNAs have been experimentally reported to be related to human diseases. Therefore, analyzing available lncRNA–disease associations and predicting potential human lncRNA–disease associations have become important tasks of bioinformatics, which would benefit human complex diseases mechanism understanding at lncRNA level, disease biomarker detection and disease diagnosis, treatment, prognosis and prevention. Furthermore, we introduced some state-of-the-art computational models, which could be effectively used to identify disease-related lncRNAs on a large scale and select the most promising disease-related lncRNAs for experimental validation. We also analyzed the limitations of these models and discussed the future directions of developing computational models for lncRNA research.

HGIMDA: Heterogeneous graph inference for miRNA-disease association prediction

Recently, microRNAs (miRNAs) have drawn more and more attentions because accumulating experimental studies have indicated miRNA could play critical roles in multiple biological processes as well as the development and progression of human complex diseases. Using the huge number of known heterogeneous biological datasets to predict potential associations between miRNAs and diseases is an important topic in the field of biology, medicine, and bioinformatics. In this study, considering the limitations in the previous computational methods, we developed the computational model of Heterogeneous Graph Inference for MiRNA-Disease Association prediction (HGIMDA) to uncover potential miRNA-disease associations by integrating miRNA functional similarity, disease semantic similarity, Gaussian interaction profile kernel similarity, and experimentally verified miRNA-disease associations into a heterogeneous graph. HGIMDA obtained AUCs of 0.8781 and 0.8077 based on global and local leave-one-out cross validation, respectively. Furthermore, HGIMDA was applied to three important human cancers for performance evaluation. As a result, 90% (Colon Neoplasms), 88% (Esophageal Neoplasms) and 88% (Kidney Neoplasms) of top 50 predicted miRNAs are confirmed by recent experiment reports. Furthermore, HGIMDA could be effectively applied to new diseases and new miRNAs without any known associations, which overcome the important limitations of many previous computational models.

PBMDA: A novel and effective path-based computational model for miRNA-disease association prediction

In the recent few years, an increasing number of studies have shown that microRNAs (miRNAs) play critical roles in many fundamental and important biological processes. As one of pathogenetic factors, the molecular mechanisms underlying human complex diseases still have not been completely understood from the perspective of miRNA. Predicting potential miRNA-disease associations makes important contributions to understanding the pathogenesis of diseases, developing new drugs, and formulating individualized diagnosis and treatment for diverse human complex diseases. Instead of only depending on expensive and time-consuming biological experiments, computational prediction models are effective by predicting potential miRNA-disease associations, prioritizing candidate miRNAs for the investigated diseases, and selecting those miRNAs with higher association probabilities for further experimental validation. In this study, Path-Based MiRNA-Disease Association (PBMDA) prediction model was proposed by integrating known human miRNA-disease associations, miRNA functional similarity, disease semantic similarity, and Gaussian interaction profile kernel similarity for miRNAs and diseases. This model constructed a heterogeneous graph consisting of three interlinked sub-graphs and further adopted depth-first search algorithm to infer potential miRNA-disease associations. As a result, PBMDA achieved reliable performance in the frameworks of both local and global LOOCV (AUCs of 0.8341 and 0.9169, respectively) and 5-fold cross validation (average AUC of 0.9172). In the cases studies of three important human diseases, 88% (Esophageal Neoplasms), 88% (Kidney Neoplasms) and 90% (Colon Neoplasms) of top-50 predicted miRNAs have been manually confirmed by previous experimental reports from literatures. Through the comparison performance between PBMDA and other previous models in case studies, the reliable performance also demonstrates that PBMDA could serve as a powerful computational tool to accelerate the identification of disease-miRNA associations.

A MapReduce based parallel SVM for large-scale predicting protein-protein interactions

Abstract Protein–protein interactions (PPIs) are crucial to most biochemical processes, including metabolic cycles, DNA transcription and replication, and signaling cascades. Although large amount of protein–protein interaction data for different species has been generated by high-throughput experimental techniques, the number is still limited compared to the total number of possible PPIs. Furthermore, the experimental methods for identifying PPIs are both time-consuming and expensive. Therefore, it is urgent and challenging to develop automated computational methods to efficiently and accurately predict PPIs. In this article, we propose a novel MapReduce-based parallel SVM model for large-scale predicting protein–protein interactions only using the information of protein sequences. First, the local sequential features represented by autocorrelation descriptor are extracted from protein sequences. Then the MapReduce framework is employed to train support vector machine (SVM) classifiers in a distributed way, obtaining significant improvement in training time while maintaining a high level of accuracy. The experimental results demonstrate that the proposed parallel algorithms not only can tackle large-scale PPIs dataset, but also perform well in terms of the evaluation metrics of speedup and accuracy. Consequently, the proposed approach can be considered as a new promising and powerful tools for large-scale predicting PPI with excellent performance and less time.

IRWRLDA: improved random walk with restart for lncRNA-disease association prediction

In recent years, accumulating evidences have shown that the dysregulations of lncRNAs are associated with a wide range of human diseases. It is necessary and feasible to analyze known lncRNA-disease associations, predict potential lncRNA-disease associations, and provide the most possible lncRNA-disease pairs for experimental validation. Considering the limitations of traditional Random Walk with Restart (RWR), the model of Improved Random Walk with Restart for LncRNA-Disease Association prediction (IRWRLDA) was developed to predict novel lncRNA-disease associations by integrating known lncRNA-disease associations, disease semantic similarity, and various lncRNA similarity measures. The novelty of IRWRLDA lies in the incorporation of lncRNA expression similarity and disease semantic similarity to set the initial probability vector of the RWR. Therefore, IRWRLDA could be applied to diseases without any known related lncRNAs. IRWRLDA significantly improved previous classical models with reliable AUCs of 0.7242 and 0.7872 in two known lncRNA-disease association datasets downloaded from the lncRNADisease database, respectively. Further case studies of colon cancer and leukemia were implemented for IRWRLDA and 60% of lncRNAs in the top 10 prediction lists have been confirmed by recent experimental reports.

FMLNCSIM: fuzzy measure-based lncRNA functional similarity calculation model.

Accumulating experimental studies have indicated the influence of lncRNAs on various critical biological processes as well as disease development and progression. Calculating lncRNA functional similarity is of high value in inferring lncRNA functions and identifying potential lncRNA-disease associations. However, little effort has been attempt to measure the functional similarity among lncRNAs on a large scale. In this study, we developed a Fuzzy Measure-based LNCRNA functional SIMilarity calculation model (FMLNCSIM) based on the assumption that functionally similar lncRNAs tend to be associated with similar diseases. The performance improvement of FMLNCSIM mainly comes from the combination of information content and the concept of fuzzy measure, which was applied to the directed acyclic graphs of disease MeSH descriptors. To evaluate the effectiveness of FMLNCSIM, we further combined it with the previously proposed model of Laplacian Regularized Least Squares for lncRNA-Disease Association (LRLSLDA). As a result, the integrated model, LRLSLDA-FMLNCSIM, achieve good performance in the frameworks of global LOOCV (AUCs of 0.8266 and 0.9338 based on LncRNADisease and MNDR database) and 5-fold cross validation (average AUCs of 0.7979 and 0.9237 based on LncRNADisease and MNDR database), which significantly improve the performance of previous classical models. It is anticipated that FMLNCSIM could be used for searching functionally similar lncRNAs and inferring lncRNA functions in the future researches.

t-LSE: a novel robust geometric approach for modeling protein-protein interaction networks.

Protein-protein interaction (PPI) networks provide insights into understanding of biological processes, function and the underlying complex evolutionary mechanisms of the cell. Modeling PPI network is an important and fundamental problem in system biology, where it is still of major concern to find a better fitting model that requires less structural assumptions and is more robust against the large fraction of noisy PPIs. In this paper, we propose a new approach called t-logistic semantic embedding (t-LSE) to model PPI networks. t-LSE tries to adaptively learn a metric embedding under the simple geometric assumption of PPI networks, and a non-convex cost function was adopted to deal with the noise in PPI networks. The experimental results show the superiority of the fit of t-LSE over other network models to PPI data. Furthermore, the robust loss function adopted here leads to big improvements for dealing with the noise in PPI network. The proposed model could thus facilitate further graph-based studies of PPIs and may help infer the hidden underlying biological knowledge. The Matlab code implementing the proposed method is freely available from the web site: http://home.ustc.edu.cn/~yzh33108/PPIModel.htm.

ILNCSIM: improved lncRNA functional similarity calculation model

Increasing observations have indicated that lncRNAs play a significant role in various critical biological processes and the development and progression of various human diseases. Constructing lncRNA functional similarity networks could benefit the development of computational models for inferring lncRNA functions and identifying lncRNA-disease associations. However, little effort has been devoted to quantifying lncRNA functional similarity. In this study, we developed an Improved LNCRNA functional SIMilarity calculation model (ILNCSIM) based on the assumption that lncRNAs with similar biological functions tend to be involved in similar diseases. The main improvement comes from the combination of the concept of information content and the hierarchical structure of disease directed acyclic graphs for disease similarity calculation. ILNCSIM was combined with the previously proposed model of Laplacian Regularized Least Squares for lncRNA-Disease Association to further evaluate its performance. As a result, new model obtained reliable performance in the leave-one-out cross validation (AUCs of 0.9316 and 0.9074 based on MNDR and Lnc2cancer databases, respectively), and 5-fold cross validation (AUCs of 0.9221 and 0.9033 for MNDR and Lnc2cancer databases), which significantly improved the prediction performance of previous models. It is anticipated that ILNCSIM could serve as an effective lncRNA function prediction model for future biomedical researches.