Cancer subtype discovery and biomarker identification via a new robust network clustering algorithm

Genetic architecture of inter-specific and -generic grass hybrids by network analysis on multi-omics data

BACKGROUND

Understanding the mechanisms underlining forage production and its biomass nutritive quality at the omics level is crucial for boosting the output of high-quality dry matter per unit of land. Despite the advent of multiple omics integration for the study of biological systems in major crops, investigations on forage species are still scarce.

RESULTS

Our results identified substantial changes in gene co-expression and metabolite-metabolite network topologies as a result of genetic perturbation by hybridizing L. perenne with another species within the genus (L. multiflorum) relative to across genera (F. pratensis). However, conserved hub genes and hub metabolomic features were detected between pedigree classes, some of which were highly heritable and displayed one or more significant edges with agronomic traits in a weighted omics-phenotype network. In spite of tagging relevant biological molecules as, for example, the light-induced rice 1 (LIR1), hub features were not necessarily better explanatory variables for omics-assisted prediction than features stochastically sampled and all available regressors.

CONCLUSIONS

The utilization of computational techniques for the reconstruction of co-expression networks facilitates the identification of key omic features that serve as central nodes and demonstrate correlation with the manifestation of observed traits. Our results also indicate a robust association between early multi-omic traits measured in a greenhouse setting and phenotypic traits evaluated under field conditions.

A Joint Graphical Model for Inferring Gene Networks Across Multiple Subpopulations and Data Types

Reconstructing gene networks from gene expression data is a long-standing challenge. In most applications, the observations can be divided into several distinct but related subpopulations and the gene expression measurements can be collected from multiple data types. Most existing methods are designed to estimate a single gene network from a single dataset. These methods may be suboptimal since they do not exploit the similarities and differences among different subpopulations and data types. In this article, we propose a joint graphical model to estimate the multiple gene networks simultaneously. Our model decomposes each subpopulation-specific gene network as a sum of common and unique components and imposes a group lasso penalty on gene networks corresponding to different data types. The gene network variations across subpopulations can be learned automatically by the decompositions of networks, and the similarities and differences among data types can be captured by the group lasso penalty. The simulation studies demonstrate that our method outperforms the state-of-the-art methods. We also apply our method to the cancer genome atlas breast cancer datasets to reconstruct subtype-specific gene networks. Hub nodes in the estimated subnetworks unique to individual cancer subtypes rediscover well-known genes associated with breast cancer subtypes and provide interesting predictions.

Joint reconstruction of multiple gene networks by simultaneously capturing inter-tumor and intra-tumor heterogeneity

MOTIVATION

Reconstruction of cancer gene networks from gene expression data is important for understanding the mechanisms underlying human cancer. Due to heterogeneity, the tumor tissue samples for a single cancer type can be divided into multiple distinct subtypes (inter-tumor heterogeneity) and are composed of non-cancerous and cancerous cells (intra-tumor heterogeneity). If tumor heterogeneity is ignored when inferring gene networks, the edges specific to individual cancer subtypes and cell types cannot be characterized. However, most existing network reconstruction methods do not simultaneously take inter-tumor and intra-tumor heterogeneity into account.

RESULTS

In this article, we propose a new Gaussian graphical model-based method for jointly estimating multiple cancer gene networks by simultaneously capturing inter-tumor and intra-tumor heterogeneity. Given gene expression data of heterogeneous samples for different cancer subtypes, a non-cancerous network shared across different cancer subtypes and multiple subtype-specific cancerous networks are estimated jointly. Tumor heterogeneity can be revealed by the difference in the estimated networks. The performance of our method is first evaluated using simulated data, and the results indicate that our method outperforms other state-of-the-art methods. We also apply our method to The Cancer Genome Atlas breast cancer data to reconstruct non-cancerous and subtype-specific cancerous gene networks. Hub nodes in the networks estimated by our method perform important biological functions associated with breast cancer development and subtype classification.

AVAILABILITY AND IMPLEMENTATION

The source code is available at https://github.com/Zhangxf-ccnu/NETI2.

SUPPLEMENTARY INFORMATION

Supplementary data are available at Bioinformatics online.

Identifying Gene Network Rewiring Using Robust Differential Graphical Model with Multivariate t-Distribution

Identifying gene network rewiring under different biological conditions is important for understanding the mechanisms underlying complex diseases. Gaussian graphical models, which assume the data follow the multivariate normal distribution, are widely used to identify gene network rewiring. However, the normality assume often fails in reality since the data are contaminated by extreme outliers in general. In this study, we propose a new robust differential graphical model to identify gene network rewiring between two conditions based on the multivariate t-distribution. The multivariate t-distribution is more robust to outliers than the normal distribution since it has heavy tails and allows values far from the mean. A fused lasso penalty is used to borrow information across conditions to improve the results. We develop an expectation maximization algorithm to solve the optimization model. Experiment results on simulated data show that our method outperforms the state-of-the-art methods. Our method is also applied to identify gene network rewiring between luminal A and basal-like subtypes of breast cancer, and gene network rewiring between the proneural and mesenchymal subtypes of glioblastoma. Several key genes which drive gene network rewiring are discovered.

Pathway-based deep clustering for molecular subtyping of cancer

Cancer is a genetic disease comprising multiple subtypes that have distinct molecular characteristics and clinical features. Cancer subtyping helps in improving personalized treatment and making decision, as different cancer subtypes respond differently to the treatment. The increasing availability of cancer related genomic data provides the opportunity to identify molecular subtypes. Several unsupervised machine learning techniques have been applied on molecular data of the tumor samples to identify cancer subtypes that are genetically and clinically distinct. However, most clustering methods often fail to efficiently cluster patients due to the challenges imposed by high-throughput genomic data and its non-linearity. In this paper, we propose a pathway-based deep clustering method (PACL) for molecular subtyping of cancer, which incorporates gene expression and biological pathway database to group patients into cancer subtypes. The main contribution of our model is to discover high-level representations of biological data by learning complex hierarchical and nonlinear effects of pathways. We compared the performance of our model with a number of benchmark clustering methods that recently have been proposed in cancer subtypes. We assessed the hypothesis that clusters (subtypes) may be associated to different survivals by logrank tests. PACL showed the lowest p-value of the logrank test against the benchmark methods. It demonstrates the patient groups clustered by PACL may correspond to subtypes which are significantly associated with distinct survival distributions. Moreover, PACL provides a solution to comprehensively identify subtypes and interpret the model in the biological pathway level. The open-source software of PACL in PyTorch is publicly available at https://github.com/tmallava/PACL.

Cancer Subtype Discovery Using Prognosis-Enhanced Neural Network Classifier in Multigenomic Data

Objective:

The main objective in studying large-scale cancer omics is to identify molecular mechanisms of cancer and discover novel biomedical targets. This work not only discovers the cancer subtypes in genome scale data by using clustering and classification but also measures their accuracy.

Methods:

Initially, candidate cancer subtypes are recognized by max-flow/min-cut graph clustering. Finally, prognosis-enhanced neural network classifier is proposed for classification. We analyzed the heterogeneity and identified the subtypes of glioblastoma multiforme, an aggressive adult brain tumor, from 215 samples with microRNA expression (12 042 genes). The samples were classified into 4 different classes such as mesenchymal, classical, proneural, and neural subtypes owing to mutations and gene expression. The results are measured using the metrics such as silhouette width, biological stability index, clustering accuracy, precision, recall, and f-measure.

Results:

Max-flow/min-cut clustering produces higher clustering accuracy of 88.93% for 215 samples. The proposed prognosis-enhanced neural network classifier algorithm produces higher accuracy results of 89.2% for 215 samples efficiently.

Conclusion:

From the experimental results, the proposed prognosis-enhanced neural network classifier is seen as an alternative, which is full of promise for cancer subtype prediction in genome scale data.

Joint L1/2-Norm Constraint and Graph-Laplacian PCA Method for Feature Extraction

Principal Component Analysis (PCA) as a tool for dimensionality reduction is widely used in many areas. In the area of bioinformatics, each involved variable corresponds to a specific gene. In order to improve the robustness of PCA-based method, this paper proposes a novel graph-Laplacian PCA algorithm by adopting L_1/2 constraint (L_1/2 gLPCA) on error function for feature (gene) extraction. The error function based on L_1/2-norm helps to reduce the influence of outliers and noise. Augmented Lagrange Multipliers (ALM) method is applied to solve the subproblem. This method gets better results in feature extraction than other state-of-the-art PCA-based methods. Extensive experimental results on simulation data and gene expression data sets demonstrate that our method can get higher identification accuracies than others.

Disease biomarker identification from gene network modules for metastasized breast cancer

Advancement in science has tended to improve treatment of fatal diseases such as cancer. A major concern in the area is the spread of cancerous cells, technically refered to as metastasis into other organs beyond the primary organ. Treatment in such a stage of cancer is extremely difficult and usually palliative only. In this study, we focus on finding gene-gene network modules which are functionally similar in nature in the case of breast cancer. These modules extracted during the disease progression stages are analyzed using p-value and their associated pathways. We also explore interesting patterns associated with the causal genes, viz., SCGB1D2, MET, CYP1B1 and MMP9 in terms of expression similarity and pathway contexts. We analyze the genes involved in both the stages- non metastasis and metastatsis and change in their expression values, their associated pathways and roles as the disease progresses from one stage to another. We discover three additional pathways viz., Glycerophospholipid metablism, h-Efp pathway and CARM1 and Regulation of Estrogen Receptor, which can be related to the metastasis phase of breast cancer. These new pathways can be further explored to identify their relevance during the progression of the disease.

Characteristic Gene Selection Based on Robust Graph Regularized Non-Negative Matrix Factorization

Many methods have been considered for gene selection and analysis of gene expression data. Nonetheless, there still exists the considerable space for improving the explicitness and reliability of gene selection. To this end, this paper proposes a novel method named robust graph regularized non-negative matrix factorization for characteristic gene selection using gene expression data, which mainly contains two aspects: Firstly, enforcing L₂₁-norm minimization on error function which is robust to outliers and noises in data points. Secondly, it considers that the samples lie in low-dimensional manifold which embeds in a high-dimensional ambient space, and reveals the data geometric structure embedded in the original data. To demonstrate the validity of the proposed method, we apply it to gene expression data sets involving various human normal and tumor tissue samples and the results demonstrate that the method is effective and feasible.

Differential network analysis from cross-platform gene expression data

Understanding how the structure of gene dependency network changes between two patient-specific groups is an important task for genomic research. Although many computational approaches have been proposed to undertake this task, most of them estimate correlation networks from group-specific gene expression data independently without considering the common structure shared between different groups. In addition, with the development of high-throughput technologies, we can collect gene expression profiles of same patients from multiple platforms. Therefore, inferring differential networks by considering cross-platform gene expression profiles will improve the reliability of network inference. We introduce a two dimensional joint graphical lasso (TDJGL) model to simultaneously estimate group-specific gene dependency networks from gene expression profiles collected from different platforms and infer differential networks. TDJGL can borrow strength across different patient groups and data platforms to improve the accuracy of estimated networks. Simulation studies demonstrate that TDJGL provides more accurate estimates of gene networks and differential networks than previous competing approaches. We apply TDJGL to the PI3K/AKT/mTOR pathway in ovarian tumors to build differential networks associated with platinum resistance. The hub genes of our inferred differential networks are significantly enriched with known platinum resistance-related genes and include potential platinum resistance-related genes.

An NMF-L2,1-Norm Constraint Method for Characteristic Gene Selection

Recent research has demonstrated that characteristic gene selection based on gene expression data remains faced with considerable challenges. This is primarily because gene expression data are typically high dimensional, negative, non-sparse and noisy. However, existing methods for data analysis are able to cope with only some of these challenges. In this paper, we address all of these challenges with a unified method: nonnegative matrix factorization via the L_2,1-norm (NMF-L_2,1). While L_2,1-norm minimization is applied to both the error function and the regularization term, our method is robust to outliers and noise in the data and generates sparse results. The application of our method to plant and tumor gene expression data demonstrates that NMF-L_2,1 can extract more characteristic genes than other existing state-of-the-art methods.

Estimation of multiple networks in Gaussian mixture models

We aim to estimate multiple networks in the presence of sample heterogeneity, where the independent samples (i.e. observations) may come from different and unknown populations or distributions. Specifically, we consider penalized estimation of multiple precision matrices in the framework of a Gaussian mixture model. A major innovation is to take advantage of the commonalities across the multiple precision matrices through possibly nonconvex fusion regularization, which for example makes it possible to achieve simultaneous discovery of unknown disease subtypes and detection of differential gene (dys)regulations in functional genomics. We embed in the EM algorithm one of two recently proposed methods for estimating multiple precision matrices in Gaussian graphical models. We demonstrate the feasibility and potential usefulness of the proposed methods in an application to glioblastoma subtype discovery and differential gene network analysis with a microarray gene expression data set. We also conduct realistic simulation studies to evaluate and compare the performance of various methods.

Importance of proximity measures in clustering of cancer and miRNA datasets: proposal of an automated framework

Distance plays an important role in the clustering process for allocating data points to different clusters.

Integrated Genomic and Network-Based Analyses of Complex Diseases and Human Disease Network

A disease phenotype generally reflects various pathobiological processes that interact in a complex network. The highly interconnected nature of the human protein interaction network (interactome) indicates that, at the molecular level, it is difficult to consider diseases as being independent of one another. Recently, genome-wide molecular measurements, data mining and bioinformatics approaches have provided the means to explore human diseases from a molecular basis. The exploration of diseases and a system of disease relationships based on the integration of genome-wide molecular data with the human interactome could offer a powerful perspective for understanding the molecular architecture of diseases. Recently, subnetwork markers have proven to be more robust and reliable than individual biomarker genes selected based on gene expression profiles alone, and achieve higher accuracy in disease classification. We have applied one of these methodologies to idiopathic dilated cardiomyopathy (IDCM) data that we have generated using a microarray and identified significant subnetworks associated with the disease. In this paper, we review the recent endeavours in this direction, and summarize the existing methodologies and computational tools for network-based analysis of complex diseases and molecular relationships among apparently different disorders and human disease network. We also discuss the future research trends and topics of this promising field.

A P-Norm Robust Feature Extraction Method for Identifying Differentially Expressed Genes

In current molecular biology, it becomes more and more important to identify differentially expressed genes closely correlated with a key biological process from gene expression data. In this paper, based on the Schatten p-norm and L_p-norm, a novel p-norm robust feature extraction method is proposed to identify the differentially expressed genes. In our method, the Schatten p-norm is used as the regularization function to obtain a low-rank matrix and the L_p-norm is taken as the error function to improve the robustness to outliers in the gene expression data. The results on simulation data show that our method can obtain higher identification accuracies than the competitive methods. Numerous experiments on real gene expression data sets demonstrate that our method can identify more differentially expressed genes than the others. Moreover, we confirmed that the identified genes are closely correlated with the corresponding gene expression data.

Pathway activity inference for multiclass disease classification through a mathematical programming optimisation framework

BACKGROUND

Applying machine learning methods on microarray gene expression profiles for disease classification problems is a popular method to derive biomarkers, i.e. sets of genes that can predict disease state or outcome. Traditional approaches where expression of genes were treated independently suffer from low prediction accuracy and difficulty of biological interpretation. Current research efforts focus on integrating information on protein interactions through biochemical pathway datasets with expression profiles to propose pathway-based classifiers that can enhance disease diagnosis and prognosis. As most of the pathway activity inference methods in literature are either unsupervised or applied on two-class datasets, there is good scope to address such limitations by proposing novel methodologies.

RESULTS

A supervised multiclass pathway activity inference method using optimisation techniques is reported. For each pathway expression dataset, patterns of its constituent genes are summarised into one composite feature, termed pathway activity, and a novel mathematical programming model is proposed to infer this feature as a weighted linear summation of expression of its constituent genes. Gene weights are determined by the optimisation model, in a way that the resulting pathway activity has the optimal discriminative power with regards to disease phenotypes. Classification is then performed on the resulting low-dimensional pathway activity profile.

CONCLUSIONS

The model was evaluated through a variety of published gene expression profiles that cover different types of disease. We show that not only does it improve classification accuracy, but it can also perform well in multiclass disease datasets, a limitation of other approaches from the literature. Desirable features of the model include the ability to control the maximum number of genes that may participate in determining pathway activity, which may be pre-specified by the user. Overall, this work highlights the potential of building pathway-based multi-phenotype classifiers for accurate disease diagnosis and prognosis problems.