Prioritize Candidate Disease Genes Research Articles

A novel candidate disease gene prioritization method using deep graph convolutional networks and semi-supervised learning

BackgroundSelecting and prioritizing candidate disease genes is necessary before conducting laboratory studies as identifying disease genes from a large number of candidate genes using laboratory methods, is a very costly and time-consuming task. There are many machine learning-based gene prioritization methods. These methods differ in various aspects including the feature vectors of genes, the used datasets with different structures, and the learning model. Creating a suitable feature vector for genes and an appropriate learning model on a variety of data with different and non-Euclidean structures, including graphs, as well as the lack of negative data are very important challenges of these methods. The use of graph neural networks has recently emerged in machine learning and other related fields, and they have demonstrated superior performance for a broad range of problems.MethodsIn this study, a new semi-supervised learning method based on graph convolutional networks is presented using the novel constructing feature vector for each gene. In the proposed method, first, we construct three feature vectors for each gene using terms from the Gene Ontology (GO) database. Then, we train a graph convolution network on these vectors using protein–protein interaction (PPI) network data to identify disease candidate genes. Our model discovers hidden layer representations encoding in both local graph structure as well as features of nodes. This method is characterized by the simultaneous consideration of topological information of the biological network (e.g., PPI) and other sources of evidence. Finally, a validation has been done to demonstrate the efficiency of our method.ResultsSeveral experiments are performed on 16 diseases to evaluate the proposed method's performance. The experiments demonstrate that our proposed method achieves the best results, in terms of precision, the area under the ROC curve (AUCs), and F1-score values, when compared with eight state-of-the-art network and machine learning-based disease gene prioritization methods.ConclusionThis study shows that the proposed semi-supervised learning method appropriately classifies and ranks candidate disease genes using a graph convolutional network and an innovative method to create three feature vectors for genes based on the molecular function, cellular component, and biological process terms from GO data.

Unravelling the role of hub genes associated with cardio renal syndrome through an integrated bioinformatics approach

Interactions of the heart and kidney provide basis for the cardiorenal syndrome, a condition in which failure of one organ (either the heart or the kidney) leads to, or exacerbates, failure of the other organ. This heterogeneous and complex clinical entity is linked to higher morbidity and mortality, thus, warranting identification of novel molecular biomarkers that can be implemented to early diagnosis of cardiorenal syndrome (CRS) patients and to predict their disease stage and clinical outcome. Here, we used a microarray dataset for the identification of key differentially expressed genes (DEGs). Initial analysis based on the cut off criteria [i.e., p -value 0.5] revealed 11 upregulated and 10 down-regulated DEGs. All these 21 DEGs were subjected to network analysis separately that showed 5 genes (ADRB2, DAB2, CX3CR1, DHRS9 and CCZ1B) in upregulated and 6 genes (FOS, FOSB, EGR1, ABCA1, DUSP1, and CXCL8) in downregulated network modules. Ten functionally enriched DEGs out of 11 were further subjected to determine the cardiorenal syndrome-specific miRNA-mRNA regulatory network. Finally, resulting 12 node network revealed 4 hub genes (DAB2: upregulated and FOS, EGR1, and CXCL8: downregulated) associated with 8 miRNAs (hsa-let-7b-5p, hsa-miR-17-5p, hsa-miR-147a, hsa-miR-16-5p, hsa-miR-129-2-3p, hsa-miR-124,3p, hsa-miR-20a-5p, and hsa-miR-429). In Feed-Forward Loop (FFL) analysis among these four hub genes, three namely DAB2, FOS and EGR1 showed their roles in regulation and inhibition. With the assumption of this disease candidate gene prioritization, we report that DAB2, FOS, EGR1 and CXCL8 may serve as robust biomarkers in CRS.

Disease gene prediction with privileged information and heteroscedastic dropout.

MotivationRecently, machine learning models have achieved tremendous success in prioritizing candidate genes for genetic diseases. These models are able to accurately quantify the similarity among disease and genes based on the intuition that similar genes are more likely to be associated with similar diseases. However, the genetic features these methods rely on are often hard to collect due to high experimental cost and various other technical limitations. Existing solutions of this problem significantly increase the risk of overfitting and decrease the generalizability of the models.ResultsIn this work, we propose a graph neural network (GNN) version of the Learning under Privileged Information paradigm to predict new disease gene associations. Unlike previous gene prioritization approaches, our model does not require the genetic features to be the same at training and test stages. If a genetic feature is hard to measure and therefore missing at the test stage, our model could still efficiently incorporate its information during the training process. To implement this, we develop a Heteroscedastic Gaussian Dropout algorithm, where the dropout probability of the GNN model is determined by another GNN model with a mirrored GNN architecture. To evaluate our method, we compared our method with four state-of-the-art methods on the Online Mendelian Inheritance in Man dataset to prioritize candidate disease genes. Extensive evaluations show that our model could improve the prediction accuracy when all the features are available compared to other methods. More importantly, our model could make very accurate predictions when >90% of the features are missing at the test stage.Availability and implementationOur method is realized with Python 3.7 and Pytorch 1.5.0 and method and data are freely available at: https://github.com/juanshu30/Disease-Gene-Prioritization-with-Privileged-Information-and-Heteroscedastic-Dropout.

DiSNEP: a Disease-Specific gene Network Enhancement to improve Prioritizing candidate disease genes.

Biological network-based strategies are useful in prioritizing genes associated with diseases. Several comprehensive human gene networks such as STRING, GIANT and HumanNet were developed and used in network-assisted algorithms to identify disease-associated genes. However, none of these networks are disease-specific and may not accurately reflect gene interactions for a specific disease. Aiming to improve disease gene prioritization using networks, we propose a Disease-Specific Network Enhancement Prioritization (DiSNEP) framework. DiSNEP first enhances a comprehensive gene network specifically for a disease through a diffusion process on a gene-gene similarity matrix derived from disease omics data. The enhanced disease-specific gene network thus better reflects true gene interactions for the disease and may improve prioritizing disease-associated genes subsequently. In simulations, DiSNEP that uses an enhanced disease-specific network prioritizes more true signal genes than comparison methods using a general gene network or without prioritization. Applications to prioritize cancer-associated gene expression and DNA methylation signal genes for five cancer types from The Cancer Genome Atlas (TCGA) project suggest that more prioritized candidate genes by DiSNEP are cancer-related according to the DisGeNET database than those prioritized by the comparison methods, consistently across all five cancer types considered, and for both gene expression and DNA methylation signal genes.

Genome-wide prediction and prioritization of human aging genes by data fusion: a machine learning approach

BackgroundMachine learning can effectively nominate novel genes for various research purposes in the laboratory. On a genome-wide scale, we implemented multiple databases and algorithms to predict and prioritize the human aging genes (PPHAGE).ResultsWe fused data from 11 databases, and used Naïve Bayes classifier and positive unlabeled learning (PUL) methods, NB, Spy, and Rocchio-SVM, to rank human genes in respect with their implication in aging. The PUL methods enabled us to identify a list of negative (non-aging) genes to use alongside the seed (known age-related) genes in the ranking process. Comparison of the PUL algorithms revealed that none of the methods for identifying a negative sample were advantageous over other methods, and their simultaneous use in a form of fusion was critical for obtaining optimal results (PPHAGE is publicly available at https://cbb.ut.ac.ir/pphage).ConclusionWe predict and prioritize over 3,000 candidate age-related genes in human, based on significant ranking scores. The identified candidate genes are associated with pathways, ontologies, and diseases that are linked to aging, such as cancer and diabetes. Our data offer a platform for future experimental research on the genetic and biological aspects of aging. Additionally, we demonstrate that fusion of PUL methods and data sources can be successfully used for aging and disease candidate gene prioritization.

One for all and all for One: Improving replication of genetic studies through network diffusion.

Improving accuracy in genetic studies would greatly accelerate understanding the genetic basis of complex diseases. One approach to achieve such an improvement for risk variants identified by the genome wide association study (GWAS) approach is to incorporate previously known biology when screening variants across the genome. We developed a simple approach for improving the prioritization of candidate disease genes that incorporates a network diffusion of scores from known disease genes using a protein network and a novel integration with GWAS risk scores, and tested this approach on a large Alzheimer disease (AD) GWAS dataset. Using a statistical bootstrap approach, we cross-validated the method and for the first time showed that a network approach improves the expected replication rates in GWAS studies. Several novel AD genes were predicted including CR2, SHARPIN, and PTPN2. Our re-prioritized results are enriched for established known AD-associated biological pathways including inflammation, immune response, and metabolism, whereas standard non-prioritized results were not. Our findings support a strategy of considering network information when investigating genetic risk factors.

Prioritizing disease genes with an improved dual label propagation framework

BackgroundPrioritizing disease genes is trying to identify potential disease causing genes for a given phenotype, which can be applied to reveal the inherited basis of human diseases and facilitate drug development. Our motivation is inspired by label propagation algorithm and the false positive protein-protein interactions that exist in the dataset. To the best of our knowledge, the false positive protein-protein interactions have not been considered before in disease gene prioritization. Label propagation has been successfully applied to prioritize disease causing genes in previous network-based methods. These network-based methods use basic label propagation, i.e. random walk, on networks to prioritize disease genes in different ways. However, all these methods can not deal with the situation in which plenty false positive protein-protein interactions exist in the dataset, because the PPI network is used as a fixed input in previous methods. This important characteristic of data source may cause a large deviation in results.ResultsA novel network-based framework IDLP is proposed to prioritize candidate disease genes. IDLP effectively propagates labels throughout the PPI network and the phenotype similarity network. It avoids the method falling when few disease genes are known. Meanwhile, IDLP models the bias caused by false positive protein interactions and other potential factors by treating the PPI network matrix and the phenotype similarity matrix as the matrices to be learnt. By amending the noises in training matrices, it improves the performance results significantly. We conduct extensive experiments over OMIM datasets, and IDLP has demonstrated its effectiveness compared with eight state-of-the-art approaches. The robustness of IDLP is also validated by doing experiments with disturbed PPI network. Furthermore, We search the literatures to verify the predicted new genes got by IDLP are associated with the given diseases, the high prediction accuracy shows IDLP can be a powerful tool to help biologists discover new disease genes.ConclusionsIDLP model is an effective method for disease gene prioritization, particularly for querying phenotypes without known associated genes, which would be greatly helpful for identifying disease genes for less studied phenotypes.Availabilityhttps://github.com/nkiip/IDLP

Open Community Challenge Reveals Molecular Network Modules with Key Roles in Diseases

Identification of modules in molecular networks is at the core of many current analysis methods in biomedical research. However, how well different approaches identify disease-relevant modules in different types of networks remains poorly understood. We launched the "Disease Module Identification DREAM Challenge", an open competition to comprehensively assess module identification methods across diverse gene, protein and signaling networks. Predicted network modules were tested for association with complex traits and diseases using a unique collection of 180 genome-wide association studies (GWAS). While a number of approaches were successful in terms of discovering complementary trait-associated modules, consensus predictions derived from the challenge submissions performed best. We find that most of these modules correspond to core disease-relevant pathways, which often comprise therapeutic targets and correctly prioritize candidate disease genes. This community challenge establishes benchmarks, tools and guidelines for molecular network analysis to study human disease biology (https://synapse.org/modulechallenge).

Chronic obstructive pulmonary disease candidate gene prioritization based on metabolic networks and functional information.

Chronic obstructive pulmonary disease (COPD) is a multi-factor disease, in which metabolic disturbances played important roles. In this paper, functional information was integrated into a COPD-related metabolic network to assess similarity between genes. Then a gene prioritization method was applied to the COPD-related metabolic network to prioritize COPD candidate genes. The gene prioritization method was superior to ToppGene and ToppNet in both literature validation and functional enrichment analysis. Top-ranked genes prioritized from the metabolic perspective with functional information could promote the better understanding about the molecular mechanism of this disease. Top 100 genes might be potential markers for diagnostic and effective therapies.

Constructing an integrated gene similarity network for the identification of disease genes

BackgroundDiscovering novel genes that are involved human diseases is a challenging task in biomedical research. In recent years, several computational approaches have been proposed to prioritize candidate disease genes. Most of these methods are mainly based on protein-protein interaction (PPI) networks. However, since these PPI networks contain false positives and only cover less half of known human genes, their reliability and coverage are very low. Therefore, it is highly necessary to fuse multiple genomic data to construct a credible gene similarity network and then infer disease genes on the whole genomic scale.ResultsWe proposed a novel method, named RWRB, to infer causal genes of interested diseases. First, we construct five individual gene (protein) similarity networks based on multiple genomic data of human genes. Then, an integrated gene similarity network (IGSN) is reconstructed based on similarity network fusion (SNF) method. Finally, we employee the random walk with restart algorithm on the phenotype-gene bilayer network, which combines phenotype similarity network, IGSN as well as phenotype-gene association network, to prioritize candidate disease genes. We investigate the effectiveness of RWRB through leave-one-out cross-validation methods in inferring phenotype-gene relationships. Results show that RWRB is more accurate than state-of-the-art methods on most evaluation metrics. Further analysis shows that the success of RWRB is benefited from IGSN which has a wider coverage and higher reliability comparing with current PPI networks. Moreover, we conduct a comprehensive case study for Alzheimer’s disease and predict some novel disease genes that supported by literature.ConclusionsRWRB is an effective and reliable algorithm in prioritizing candidate disease genes on the genomic scale. Software and supplementary information are available at http://nclab.hit.edu.cn/~tianzhen/RWRB/.

Exploiting Negative Sample Selection for Prioritizing Candidate Disease Genes

A major challenge in bio-medicine is finding the genetic causes of human diseases, and researchers are often faced with a large number of candidate genes. Gene prioritization methods provide a valuable support in guiding researchers to detect reliable candidate causative-genes for a disease under study. Indeed, such methods rank genes according to their association with a disease of interest. Actually, the majority of genetic disorders has few or none causative genes associated with them; this induces a high labeling unbalance in the corresponding ranking problems, thus linking the need of achieving reliable solutions to the adoption of imbalance-aware techniques. We propose the use of an expressly designed imbalance-aware methodology for prioritizing genes, which first rebalances the training set entries through a negative selection procedure, then applies a learning algorithm 'sensitive' to the misclassification of positive instances, to provide the gene ranking. The algorithm has a reduced time complexity, which makes feasible its application on large-sized datasets. The validation of this methodology proved its competitiveness with state-of-art techniques on a benchmark composed of 708 selected Medical Subject Headings diseases, and provided some putative novel gene-disease associations.

Construction of reliable heterogeneous network using protein sequence similarity for the prioritization of candidate disease genes

Identifying candidate disease genes are significant to improve medical care. In previous research works the Random walk with restart and diffusion profile (RWRDP) and Random walk-based algorithm on the reliable heterogeneous network (RWRHN) were used to prioritize the candidate disease genes. The topological and phenotype similarity was used to predict the candidate disease gene in the existing systems. But this similarity measure does not predict the candidate disease gene effectively. To overcome these difficulties the existing algorithms have been improved to predict the candidate disease genes. In order to improve the performance measure and reduce the prediction error, Random walk-based algorithm on the reliable heterogeneous network-Piecewise linear regression-protein sequence similarity (RWRHN-PLR-SS) is introduced. Then the candidate diseases genes are ranked. Finally RWRHN-PLR-SS is used to predict novel causal genes for 20 diseases, including breast cancer, diabetes mellitus type 2, Cancer and Prostate cancer, Alzheimer disease, Atrial fibrillation as well as to detect disease-related protein complexes. The experimental results show that the proposed algorithms achieve higher performance compared with the existing and the other proposed algorithms.

GenePANDA\u2014a novel network-based gene prioritizing tool for complex diseases

Here we describe GenePANDA, a novel network-based tool for prioritizing candidate disease genes. GenePANDA assesses whether a gene is likely a candidate disease gene based on its relative distance to known disease genes in a functional association network. A unique feature of GenePANDA is the introduction of adjusted network distance derived by normalizing the raw network distance between two genes with their respective mean raw network distance to all other genes in the network. The use of adjusted network distance significantly improves GenePANDA’s performance on prioritizing complex disease genes. GenePANDA achieves superior performance over five previously published algorithms for prioritizing disease genes. Finally, GenePANDA can assist in prioritizing functionally important SNPs identified by GWAS.

Gene co-expression analysis for functional classification and gene-disease predictions.

Gene co-expression networks can be used to associate genes of unknown function with biological processes, to prioritize candidate disease genes or to discern transcriptional regulatory programmes. With recent advances in transcriptomics and next-generation sequencing, co-expression networks constructed from RNA sequencing data also enable the inference of functions and disease associations for non-coding genes and splice variants. Although gene co-expression networks typically do not provide information about causality, emerging methods for differential co-expression analysis are enabling the identification of regulatory genes underlying various phenotypes. Here, we introduce and guide researchers through a (differential) co-expression analysis. We provide an overview of methods and tools used to create and analyse co-expression networks constructed from gene expression data, and we explain how these can be used to identify genes with a regulatory role in disease. Furthermore, we discuss the integration of other data types with co-expression networks and offer future perspectives of co-expression analysis.

Disease gene prioritization by integrating tissue-specific molecular networks using a robust multi-network model.

BackgroundAccurately prioritizing candidate disease genes is an important and challenging problem. Various network-based methods have been developed to predict potential disease genes by utilizing the disease similarity network and molecular networks such as protein interaction or gene co-expression networks. Although successful, a common limitation of the existing methods is that they assume all diseases share the same molecular network and a single generic molecular network is used to predict candidate genes for all diseases. However, different diseases tend to manifest in different tissues, and the molecular networks in different tissues are usually different. An ideal method should be able to incorporate tissue-specific molecular networks for different diseases.ResultsIn this paper, we develop a robust and flexible method to integrate tissue-specific molecular networks for disease gene prioritization. Our method allows each disease to have its own tissue-specific network(s). We formulate the problem of candidate gene prioritization as an optimization problem based on network propagation. When there are multiple tissue-specific networks available for a disease, our method can automatically infer the relative importance of each tissue-specific network. Thus it is robust to the noisy and incomplete network data. To solve the optimization problem, we develop fast algorithms which have linear time complexities in the number of nodes in the molecular networks. We also provide rigorous theoretical foundations for our algorithms in terms of their optimality and convergence properties. Extensive experimental results show that our method can significantly improve the accuracy of candidate gene prioritization compared with the state-of-the-art methods.ConclusionsIn our experiments, we compare our methods with 7 popular network-based disease gene prioritization algorithms on diseases from Online Mendelian Inheritance in Man (OMIM) database. The experimental results demonstrate that our methods recover true associations more accurately than other methods in terms of AUC values, and the performance differences are significant (with paired t-test p-values less than 0.05). This validates the importance to integrate tissue-specific molecular networks for studying disease gene prioritization and show the superiority of our network models and ranking algorithms toward this purpose. The source code and datasets are available at http://nijingchao.github.io/CRstar/.Electronic supplementary materialThe online version of this article (doi:10.1186/s12859-016-1317-x) contains supplementary material, which is available to authorized users.

HybridRanker: Integrating network topology and biomedical knowledge to prioritize cancer candidate genes

In the past few years, many researches have been conducted on identifying and prioritizing disease-related genes with the goal of achieving significant improvements in treatment and drug discovery. Both experimental and computational approaches have been exploited in recent studies to explore disease-susceptible genes. The experimental methods for identification of these genes are usually time-consuming and expensive. As a result, a substantial number of these studies have shown interest in utilizing computational techniques, commonly known as gene prioritization methods. From a conceptual point of view, these methods combine various sources of information about a particular disease of interest and then use it to discover and prioritize candidate disease genes. In this paper, we propose a gene prioritization method (HybridRanker), which exploits network topological features, as well as several biomedical data sources to identify candidate disease genes. In this approach, the genes are characterized using both local and global features of a protein-protein interaction (PPI) network. Furthermore, to obtain improved results for a particular disease of interest, HybridRanker incorporates data from diseases with similar symptoms and also from its comorbid diseases. We applied this new approach to identify and prioritize candidate disease genes of colorectal cancer (CRC) and the efficiency of HybridRanker was confirmed by leave-one-out cross-validation test. Moreover, in comparison with several well-known prioritization methods, HybridRanker shows higher performance in terms of different criteria.

Integrating phenotypic features and tissue-specific information to prioritize disease genes

Prioritization of candidate disease genes is crucial for improving medical care, and is one of the fundamental challenges in the post-genomic era. In recent years, different network-based methods for gene prioritization are proposed. Previous studies on gene prioritization show that tissue-specific protein-protein interaction (PPI) networks built by integrating PPIs with tissue-specific gene expression profiles can perform better than tissue-na¨ive global PPI network. Based on the observations that diseases with similar phenotypes are likely to have common related genes, and genes associated with the same phenotype tend to interact with each other, we propose a method to prioritize disease genes based on a heterogeneous network built by integrating phenotypic features and tissue-specific information. In this heterogeneous network, the PPI network is built by integrating phenotypic features with a tissue-specific PPI network, and the disease network consists of the diseases that are associated with the same phenotype and tissue as the query disease. To determine the impacts of these two factors on gene prioritization, we test three typical network-based prioritization methods on heterogeneous networks consisting of combinations of different PPIs and disease networks built with or without phenotypic features and tissue-specific information. We also compare the proposed method with other tissuespecific networks. The results of case studies reveals that integrating phenotypic features with a tissue-specific PPI network improves the prioritization results. Moreover, the disease networks generated using our method not only show comparable performance with the widely used disease similarity dataset of 5080 human diseases, but are also effective for diseases that are not in the dataset.

SoftPanel: a website for grouping diseases and related disorders for generation of customized panels.

BackgroundTargeted next-generation sequencing is playing an increasingly important role in biological research and clinical diagnosis by allowing researchers to sequence high priority genes at much higher depths and at a fraction of the cost of whole genome or exome sequencing. However, in designing the panel of genes to be sequenced, investigators need to consider the tradeoff between the better sensitivity of a broad panel and the higher specificity of a potentially more relevant panel. Although tools to prioritize candidate disease genes have been developed, the great majority of these require prior knowledge and a set of seed genes as input, which is only possible for diseases with a known genetic etiology.ResultsTo meet the demands of both researchers and clinicians, we have developed a user-friendly website called SoftPanel. This website is intended to serve users by allowing them to input a single disorder or a disorder group and generate a panel of genes predicted to underlie the disorder of interest. Various methods of retrieval including a keyword search, browsing of an arborized list of International Classification of Diseases, 10th revision (ICD-10) codes or using disorder phenotypic similarities can be combined to define a group of disorders and the genes known to be associated with them. Moreover, SoftPanel enables users to expand or refine a gene list by utilizing several biological data resources. In addition to providing users with the facility to create a “hard” panel that contains an exact gene list for targeted sequencing, SoftPanel also enables generation of a “soft” panel of genes, which may be used to further filter a significantly altered set of genes identified through whole genome or whole exome sequencing. The service and data provided by SoftPanel can be accessed at http://www.isb.pku.edu.cn/SoftPanel/. A tutorial page is included for trying out sample data and interpreting results.ConclusionSoftPanel provides a convenient and powerful tool for creating a targeted panel of potential disease genes while supporting different forms of input. SoftPanel may be utilized in both genomics research and personalized medicine.Electronic supplementary materialThe online version of this article (doi:10.1186/s12859-016-0998-5) contains supplementary material, which is available to authorized users.

Prediction and Validation of Disease Genes Using HeteSim Scores.

Deciphering the gene disease association is an important goal in biomedical research. In this paper, we use a novel relevance measure, called HeteSim, to prioritize candidate disease genes. Two methods based on heterogeneous networks constructed using protein-protein interaction, gene-phenotype associations, and phenotype-phenotype similarity, are presented. In HeteSim_MultiPath (HSMP), HeteSim scores of different paths are combined with a constant that dampens the contributions of longer paths. In HeteSim_SVM (HSSVM), HeteSim scores are combined with a machine learning method. The 3-fold experiments show that our non-machine learning method HSMP performs better than the existing non-machine learning methods, our machine learning method HSSVM obtains similar accuracy with the best existing machine learning method CATAPULT. From the analysis of the top 10 predicted genes for different diseases, we found that HSSVM avoid the disadvantage of the existing machine learning based methods, which always predict similar genes for different diseases. The data sets and Matlab code for the two methods are freely available for download at http://lab.malab.cn/data/HeteSim/index.jsp.

Prioritizing Candidate Disease Genes Combined with Semantic Similarity by Walking on the Heterogeneous Network

Prioritizing Candidate Disease Genes Combined with Semantic Similarity by Walking on the Heterogeneous Network