High-dimensional Gene Expression Data Research Articles

Discovering and interpreting transcriptomic drivers of imaging traits using neural networks.

Cancer heterogeneity is observed at multiple biological levels. To improve our understanding of these differences and their relevance in medicine, approaches to link organ- and tissue-level information from diagnostic images and cellular-level information from genomics are needed. However, these 'radiogenomic' studies often use linear or shallow models, depend on feature selection, or consider one gene at a time to map images to genes. Moreover, no study has systematically attempted to understand the molecular basis of imaging traits based on the interpretation of what the neural network has learned. These studies are thus limited in their ability to understand the transcriptomic drivers of imaging traits, which could provide additional context for determining clinical outcomes. We present a neural network-based approach that takes high-dimensional gene expression data as input and performs non-linear mapping to an imaging trait. To interpret the models, we propose gene masking and gene saliency to extract learned relationships from radiogenomic neural networks. In glioblastoma patients, our models outperformed comparable classifiers (>0.10 AUC) and our interpretation methods were validated using a similar model to identify known relationships between genes and molecular subtypes. We found that tumor imaging traits had specific transcription patterns, e.g. edema and genes related to cellular invasion, and 10 radiogenomic traits were significantly predictive of survival. We demonstrate that neural networks can model transcriptomic heterogeneity to reflect differences in imaging and can be used to derive radiogenomic traits with clinical value. https://github.com/novasmedley/deepRadiogenomics. whsu@mednet.ucla.edu. Supplementary data are available at Bioinformatics online.

RefDNN: a reference drug based neural network for more accurate prediction of anticancer drug resistance

Cancer is one of the most difficult diseases to treat owing to the drug resistance of tumour cells. Recent studies have revealed that drug responses are closely associated with genomic alterations in cancer cells. Numerous state-of-the-art machine learning models have been developed for prediction of drug responses using various genomic data and diverse drug molecular information, but those methods are ineffective to predict drug response to untrained drugs and gene expression patterns, which is known as the cold-start problem. In this study, we present a novel deep neural network model, termed RefDNN, for improved prediction of drug resistance and identification of biomarkers related to drug response. RefDNN exploits a collection of drugs, called reference drugs, to learn representations for a high-dimensional gene expression vector and a molecular structure vector of a drug and predicts drug response labels using the reference drug-based representations. These calculations come from the observation that similar chemicals have similar effects. The proposed model not only outperformed existing computational prediction models in most comparative experiments, but also showed more robust prediction for untrained drugs and cancer types than traditional machine learning models. RefDNN exploits the ElasticNet regularization to deal with high-dimensional gene expression data, which allows identification of gene markers associated with drug resistance. Lastly, we described an application of RefDNN in exploring a new candidate drug for liver cancer. As the proposed model can guarantee good prediction of drug responses to untrained drugs for given gene expression patterns, it may be of potential benefit in drug repositioning and personalized medicine.

Feature selection and classification for gene expression data using novel correlation based overlapping score method via Chou’s 5-steps rule

The analysis of omics data together with knowledge-based interpretation can help obtaining important information regarding different biological processes and to reflect the current physiological status of tissue and cells. The main challenge, however, is to analyze high-dimensional gene expression data consisting of a massive amount of redundant genes in extracting disease-related information. To address this problem, gene selection, that eliminates redundant and irrelevant genes, has been a key step. In current article, a feature selection technique is proposed that exploit correlation based overlapping analysis of expression data across classes. The proposed correlation based overlapping score (COS) technique is compared with state-of-the-art gene selection approaches using real-world benchmark microarray datasets. In an experimental evaluation, the COS algorithm outperforms the other methods with minimum misclassification errors obtained via boosting, random forest and k-nearest neighbour (kNN) classifiers. Moreover, the proposed technique is more stable than the other techniques in gene selection.

Non-Negative Symmetric Low-Rank Representation Graph Regularized Method for Cancer Clustering Based on Score Function.

As an important approach to cancer classification, cancer sample clustering is of particular importance for cancer research. For high dimensional gene expression data, examining approaches to selecting characteristic genes with high identification for cancer sample clustering is an important research area in the bioinformatics field. In this paper, we propose a novel integrated framework for cancer clustering known as the non-negative symmetric low-rank representation with graph regularization based on score function (NSLRG-S). First, a lowest rank matrix is obtained after NSLRG decomposition. The lowest rank matrix preserves the local data manifold information and the global data structure information of the gene expression data. Second, we construct the Score function based on the lowest rank matrix to weight all of the features of the gene expression data and calculate the score of each feature. Third, we rank the features according to their scores and select the feature genes for cancer sample clustering. Finally, based on selected feature genes, we use the K-means method to cluster the cancer samples. The experiments are conducted on The Cancer Genome Atlas (TCGA) data. Comparative experiments demonstrate that the NSLRG-S framework can significantly improve the clustering performance.

Using sufficient direction factor model to analyze latent activities associated with breast cancer survival.

High-dimensional gene expression data often exhibit intricate correlation patterns as the result of coordinated genetic regulation. In practice, however, it is difficult to directly measure these coordinated underlying activities. Analysis of breast cancer survival data with gene expressions motivates us to use a two-stage latent factor approach to estimate these unobserved coordinated biologicalprocesses. Compared to existing approaches, our proposed procedure has several unique characteristics. In the first stage, an important distinction is that our procedure incorporates prior biological knowledge about gene-pathway membership into the analysis and explicitly model the effects of genetic pathways on the latent factors. Second, to characterize the molecular heterogeneity of breast cancer, our approach provides estimates specific to each cancer subtype. Finally, our proposed framework incorporates sparsity condition due to the fact that genetic networks are oftensparse. In the second stage, we investigate the relationship between latent factor activity levels and survival time with censoring using a general dimension reduction model in the survival analysis context. Combining the factor model and sufficient direction model provides an efficient way of analyzing high-dimensional data and reveals some interesting relations in the breast cancer gene expressiondata.

Interpretable deep neural network for cancer survival analysis by integrating genomic and clinical data

BackgroundUnderstanding the complex biological mechanisms of cancer patient survival using genomic and clinical data is vital, not only to develop new treatments for patients, but also to improve survival prediction. However, highly nonlinear and high-dimension, low-sample size (HDLSS) data cause computational challenges to applying conventional survival analysis.ResultsWe propose a novel biologically interpretable pathway-based sparse deep neural network, named Cox-PASNet, which integrates high-dimensional gene expression data and clinical data on a simple neural network architecture for survival analysis. Cox-PASNet is biologically interpretable where nodes in the neural network correspond to biological genes and pathways, while capturing the nonlinear and hierarchical effects of biological pathways associated with cancer patient survival. We also propose a heuristic optimization solution to train Cox-PASNet with HDLSS data. Cox-PASNet was intensively evaluated by comparing the predictive performance of current state-of-the-art methods on glioblastoma multiforme (GBM) and ovarian serous cystadenocarcinoma (OV) cancer. In the experiments, Cox-PASNet showed out-performance, compared to the benchmarking methods. Moreover, the neural network architecture of Cox-PASNet was biologically interpreted, and several significant prognostic factors of genes and biological pathways were identified.ConclusionsCox-PASNet models biological mechanisms in the neural network by incorporating biological pathway databases and sparse coding. The neural network of Cox-PASNet can identify nonlinear and hierarchical associations of genomic and clinical data to cancer patient survival. The open-source code of Cox-PASNet in PyTorch implemented for training, evaluation, and model interpretation is available at: https://github.com/DataX-JieHao/Cox-PASNet.

Nature-Inspired Compressed Sensing for Transcriptomic Profiling From Random Composite Measurements.

Transcriptomic profiling is a high-throughput approach to measure gene expression levels under different experimental conditions at different timings. With the development of the related technologies such as single-cell RNA-Seq, the dimensions of gene expression data are increased to hundreds of thousands or more for high-resolution insights. There is a long-lasting challenge in exploiting the relations between transcriptomic profiles and random composite measurements. To address it, we proposed a mathematical framework based on differential evolution (global search) with the help of compressed sensing (local search) termed as DECS. Exploiting the inherent sparse nature of gene expression data, the proposed DECS method can learn the sparse module dictionaries and levels from the low-dimensional random composite measurements for reconstructing the high-dimensional gene expression data with significant orders of magnitude (e.g. 200 × ). Several experiments were conducted to compare DECS with three benchmark methods, demonstrating that the proposed DECS outperforms the benchmark methods and can recover most of the gene expression patterns. The underlying reasons are discussed and illustrated by revealing the related mechanistic insights through extensive benchmarks on nine GSE datasets and their sensitivity analysis.

Gene expression based survival prediction for cancer patients-A topic modeling approach.

Cancer is one of the leading cause of death, worldwide. Many believe that genomic data will enable us to better predict the survival time of these patients, which will lead to better, more personalized treatment options and patient care. As standard survival prediction models have a hard time coping with the high-dimensionality of such gene expression data, many projects use some dimensionality reduction techniques to overcome this hurdle. We introduce a novel methodology, inspired by topic modeling from the natural language domain, to derive expressive features from the high-dimensional gene expression data. There, a document is represented as a mixture over a relatively small number of topics, where each topic corresponds to a distribution over the words; here, to accommodate the heterogeneity of a patient’s cancer, we represent each patient (≈ document) as a mixture over cancer-topics, where each cancer-topic is a mixture over gene expression values (≈ words). This required some extensions to the standard LDA model—e.g., to accommodate the real-valued expression values—leading to our novel discretized Latent Dirichlet Allocation (dLDA) procedure. After using this dLDA to learn these cancer-topics, we can then express each patient as a distribution over a small number of cancer-topics, then use this low-dimensional “distribution vector” as input to a learning algorithm—here, we ran the recent survival prediction algorithm, MTLR, on this representation of the cancer dataset. We initially focus on the METABRIC dataset, which describes each of n = 1,981 breast cancer patients using the r = 49,576 gene expression values, from microarrays. Our results show that our approach (dLDA followed by MTLR) provides survival estimates that are more accurate than standard models, in terms of the standard Concordance measure. We then validate this “dLDA+MTLR” approach by running it on the n = 883 Pan-kidney (KIPAN) dataset, over r = 15,529 gene expression values—here using the mRNAseq modality—and find that it again achieves excellent results. In both cases, we also show that the resulting model is calibrated, using the recent “D-calibrated” measure. These successes, in two different cancer types and expression modalities, demonstrates the generality, and the effectiveness, of this approach. The dLDA+MTLR source code is available at https://github.com/nitsanluke/GE-LDA-Survival.

Incorporating genetic networks into case-control association studies with high-dimensional DNA methylation data

BackgroundIn human genetic association studies with high-dimensional gene expression data, it has been well known that statistical selection methods utilizing prior biological network knowledge such as genetic pathways and signaling pathways can outperform other methods that ignore genetic network structures in terms of true positive selection. In recent epigenetic research on case-control association studies, relatively many statistical methods have been proposed to identify cancer-related CpG sites and their corresponding genes from high-dimensional DNA methylation array data. However, most of existing methods are not designed to utilize genetic network information although methylation levels between linked genes in the genetic networks tend to be highly correlated with each other.ResultsWe propose new approach that combines data dimension reduction techniques with network-based regularization to identify outcome-related genes for analysis of high-dimensional DNA methylation data. In simulation studies, we demonstrated that the proposed approach overwhelms other statistical methods that do not utilize genetic network information in terms of true positive selection. We also applied it to the 450K DNA methylation array data of the four breast invasive carcinoma cancer subtypes from The Cancer Genome Atlas (TCGA) project.ConclusionsThe proposed variable selection approach can utilize prior biological network information for analysis of high-dimensional DNA methylation array data. It first captures gene level signals from multiple CpG sites using data a dimension reduction technique and then performs network-based regularization based on biological network graph information. It can select potentially cancer-related genes and genetic pathways that were missed by the existing methods.

A Master Slave Parallel Genetic Algorithm for Feature Selection in High Dimensional Datasets

Feature Selection in High Dimensional Datasets is a combinatorial problem as it selects the optimal subsets from N dimensional data having 2N possible subsets. Genetic Algorithms are generally a good choice for feature selection in large datasets, though for some high dimensional problems it may take varied amount of time - few seconds, few hours or even few days. Therefore, it is important to use Genetic Algorithms that can give quality results in reasonably acceptable time limit. For this purpose, it is becoming necessary to implement Genetic Algorithms in an efficient manner. In this paper, a Master Slave Parallel Genetic Algorithm is implemented as a Feature Selection procedure to diminish the time intricacies of sequential genetic algorithm. This paper describes the speed gains in parallel Master-Slave Genetic Algorithm and also discusses the theoretical analysis of optimal number of slaves required for an efficient master slave implementation. The experiments are performed on three high-dimensional gene expression data. As Genetic Algorithm is a wrapper technique and takes more time to find the importance of any feature, Information Gain technique is used first as pre-processing task to remove the irrelevant features.

ScGen predicts single-cell perturbation responses.

Accurately modeling cellular response to perturbations is a central goal of computational biology. While such modeling has been based on statistical, mechanistic and machine learning models in specific settings, no generalization of predictions to phenomena absent from training data (out-of-sample) has yet been demonstrated. Here, we present scGen (https://github.com/theislab/scgen), a model combining variational autoencoders and latent space vector arithmetics for high-dimensional single-cell gene expression data. We show that scGen accurately models perturbation and infection response of cells across cell types, studies and species. In particular, we demonstrate that scGen learns cell-type and species-specific responses implying that it captures features that distinguish responding from non-responding genes and cells. With the upcoming availability of large-scale atlases of organs in a healthy state, we envision scGen to become a tool for experimental design through in silico screening of perturbation response in the context of disease and drug treatment.

On the Performance of Variable Selection and Classification via Rank-Based Classifier

In high-dimensional gene expression data analysis, the accuracy and reliability of cancer classification and selection of important genes play a very crucial role. To identify these important genes and predict future outcomes (tumor vs. non-tumor), various methods have been proposed in the literature. But only few of them take into account correlation patterns and grouping effects among the genes. In this article, we propose a rank-based modification of the popular penalized logistic regression procedure based on a combination of ℓ 1 and ℓ 2 penalties capable of handling possible correlation among genes in different groups. While the ℓ 1 penalty maintains sparsity, the ℓ 2 penalty induces smoothness based on the information from the Laplacian matrix, which represents the correlation pattern among genes. We combined logistic regression with the BH-FDR (Benjamini and Hochberg false discovery rate) screening procedure and a newly developed rank-based selection method to come up with an optimal model retaining the important genes. Through simulation studies and real-world application to high-dimensional colon cancer gene expression data, we demonstrated that the proposed rank-based method outperforms such currently popular methods as lasso, adaptive lasso and elastic net when applied both to gene selection and classification.

A distribution-free test of independence based on mean variance index

A new test based on mean variance (MV) index is proposed for testing the independence between a categorical random variable Y and a continuous one X. The MV index can be considered as the weighted average of Cramér–von Mises distances between the conditional distribution functions of X given each class of Y and the unconditional distribution function of X. The MV index is zero if and only if X and Y are independent. The new MV test between X and Y enjoys several appealing merits. First, an explicit form of the asymptotic null distribution is derived under the independence between X and Y. It provides an efficient way to compute critical values and p-value. Second, no assumption on the distributions of two random variables is required and the new test statistic is invariant under one-to-one transformations of the continuous random variable. It is essentially a rank test and distribution-free, so it is resistant to heavy-tailed distributions and extreme values in practice. Monte Carlo simulations demonstrate its excellent finite-sample performance. In applications, the MV test is used in two high dimensional gene expression data to detect the significant genes associated with tumor types.

In silico markers: an evolutionary and statistical approach to select informative genes of human breast cancer subtypes.

Recent advancement in bioinformatics offers the ability to identify informative genes from high dimensional gene expression data. Selection of informative genes from these large datasets has emerged as an issue of major concern among researchers. Gene functionality and regulatory mechanisms can be understood through the analysis of these gene expression data. Here, we present a computational method to identify informative genes for breast cancer subtypes such as Basal, human epidermal growth factor receptor 2 (Her2), luminal A (LumA), and luminal B (LumB). The proposed In Silico Markers method is a wrapper feature selection method based on Least Absolute Shrinkage and Selection Operator (LASSO), Covariance Matrix Adaptation Evolution Strategy (CMA-ES) and Support Vector Machine (SVM) as a classifier. Moreover, the composite measure consisting of relevance, redundancy, and rank score of frequently appeared genes are used to select informative genes. The informative genes are validated by statistical and biologically relevant criteria. For a comparative evaluation of the proposed approach, biological similarity score designed on semantic similarity measure of GO terms are investigated. Further, the proposed technique is evaluated with 7 existing gene selection techniques using two-class annotated breast cancer subtype datasets. The utilization of this method can bring about the discovery of informative genes. Furthermore, under multiple criteria decision-making set-up, informative genes selected by the In Silico Markers are found to be admirable than the compared methods selected genes.

A fast and efficient count-based matrix factorization method for detecting cell types from single-cell RNAseq data

BackgroundSingle-cell RNA sequencing (scRNAseq) data always involves various unwanted variables, which would be able to mask the true signal to identify cell-types. More efficient way of dealing with this issue is to extract low dimension information from high dimensional gene expression data to represent cell-type structure. In the past two years, several powerful matrix factorization tools were developed for scRNAseq data, such as NMF, ZIFA, pCMF and ZINB-WaVE. But the existing approaches either are unable to directly model the raw count of scRNAseq data or are really time-consuming when handling a large number of cells (e.g. n>500).ResultsIn this paper, we developed a fast and efficient count-based matrix factorization method (single-cell negative binomial matrix factorization, scNBMF) based on the TensorFlow framework to infer the low dimensional structure of cell types. To make our method scalable, we conducted a series of experiments on three public scRNAseq data sets, brain, embryonic stem, and pancreatic islet. The experimental results show that scNBMF is more powerful to detect cell types and 10 - 100 folds faster than the scRNAseq bespoke tools.ConclusionsIn this paper, we proposed a fast and efficient count-based matrix factorization method, scNBMF, which is more powerful for detecting cell type purposes. A series of experiments were performed on three public scRNAseq data sets. The results show that scNBMF is a more powerful tool in large-scale scRNAseq data analysis. scNBMF was implemented in R and Python, and the source code are freely available at https://github.com/sqsun.

A class imbalance-aware Relief algorithm for the classification of tumors using microarray gene expression data

DNA microarray data has been widely used in cancer research due to the significant advantage helped to successfully distinguish between tumor classes. However, typical gene expression data usually presents a high-dimensional imbalanced characteristic, which poses severe challenge for traditional machine learning methods to construct a robust classifier performing well on both the minority and majority classes. As one of the most successful feature weighting techniques, Relief is considered to particularly suit to handle high-dimensional problems. Unfortunately, almost all relief-based methods have not taken the class imbalance distribution into account. This study identifies that existing Relief-based algorithms may underestimate the features with the discernibility ability of minority classes, and ignore the distribution characteristic of minority class samples. As a result, an additional bias towards being classified into the majority classes can be introduced. To this end, a new method, named imRelief, is proposed for efficiently handling high-dimensional imbalanced gene expression data. imRelief can correct the bias towards to the majority classes, and consider the scattered distributional characteristic of minority class samples in the process of estimating feature weights. This way, imRelief has the ability to reward the features which perform well at separating the minority classes from other classes. Experiments on four microarray gene expression data sets demonstrate the effectiveness of imRelief in both feature weighting and feature subset selection applications.

Variable selection with group LASSO approach: Application to Cox regression with frailty model

In analysis of survival outcomes supplemented with both clinical information and high-dimensional gene expression data, use of the traditional Cox proportional hazards model fails to meet some emerging needs in biomedical research. First, the number of covariates is generally much larger the sample size. Secondly, predicting an outcome based on individual gene expression is inadequate because multiple biological processes and functional pathways regulate phenotypic expression. Another challenge is that the Cox model assumes that populations are homogenous, implying that all individuals have the same risk of death, which is rarely true due to unmeasured risk factors among populations. In this paper we propose group LASSO with gamma-distributed frailty for variable selection in Cox regression by extending previous scholarship to account for heterogeneity among group structures related to exposure and susceptibility. The consistency property of the proposed method is established. This method is appropriate for addressing a wide variety of research questions from genetics to air pollution. Simulated and real world data analysis shows promising performance by group LASSO compared with other methods, including group SCAD and group MCP. Future research directions include expanding the use of frailty with adaptive group LASSO and sparse group LASSO methods.

A primal dual active set with continuation algorithm for high-dimensional nonconvex SICA-penalized regression

ABSTRACTThe smooth integration of counting and absolute deviation (SICA) penalty has been demonstrated theoretically and practically to be effective in nonconvex penalization for variable selection and parameter estimation. However, solving the nonconvex optimization problem associated with SICA penalty in high-dimensional setting remains to be enriched, mainly due to the singularity at the origin and the nonconvexity of the SICA penalty function. In this paper, we develop a fast primal dual active set (PDAS) with continuation algorithm for solving the nonconvex SICA-penalized least squares in high dimensions. Upon introducing the dual variable, the PDAS algorithm iteratively identify and update the active set in the optimization using both the primal and dual information, and then solve a low-dimensional least square problem on the active set. When combined with a continuation strategy and a high-dimensional Bayesian information criterion (BIC) selector on the tuning parameters, the proposed algorithm is very efficient and accurate. Extensive simulation studies and analysis of a high-dimensional microarray gene expression data are presented to illustrate the performance of the proposed method.

Graph-Based Hub Gene Selection Technique Using Protein Interaction Information: Application to Sample Classification.

Classification of samples of gene expression profile plays a significant role in prediction and diagnosis of diseases. In the task of sample classification, a robust feature selection algorithm is very much essential to identify the important genes from the high dimensional gene expression data. This paper explores the information of protein-protein interaction with a graph mining technique for finding a proper subset of features (genes), which further takes part in sample classification. Here, our contribution for feature selection is three-fold: first, all the genes are grouped into different clusters based on the integrated information of the gene expression values and their protein interactions using a multi-objective optimization based clustering approach. Second, the confidence scores of the protein interactions are incorporated in a popular graph mining algorithm namely Goldberg algorithm to find out the relevant features. These features are the topologically and functionally significant genes, named as hub genes. Finally, these hub genes are identified varying the degrees of the nodes, and those are utilized for the sample classification task. Different machine learning classifiers are exploited for this purpose, and the classification performance is measured with respect to various performance metrics namely accuracy, sensitivity, specificity, precision, F-measure, and Mathews coefficient correlation. Comparative analysis with respect to two baselines and several existing approaches proves the efficiency of the proposed approach. Furthermore, the robustness of the identified hub-gene modules is endorsed using some strong biological significance analysis.

Group-sparse SVD Models via $L_1$- and $L_0$-norm Penalties and Their Applications in Biological Data

Sparse Singular Value Decomposition (SVD) models have been proposed for biclustering high dimensional gene expression data to identify block patterns with similar expressions. However, these models do not take into account prior group effects upon variable selection. To this end, we first propose group-sparse SVD models with group Lasso ( $GL_1$ G L 1 -SVD) and group $L_0$ L 0 -norm penalty ( $GL_0$ G L 0 -SVD) for non-overlapping group structure of variables. However, such group-sparse SVD models limit their applicability in some problems with overlapping structure. Thus, we also propose two group-sparse SVD models with overlapping group Lasso ( $OGL_1$ O G L 1 -SVD) and overlapping group $L_0$ L 0 -norm penalty ( $OGL_0$ O G L 0 -SVD). We first adopt an alternating iterative strategy to solve $GL_1$ G L 1 -SVD based on a block coordinate descent method, and $GL_0$ G L 0 -SVD based on a projection method. The key of solving $OGL_1$ O G L 1 -SVD is a proximal operator with overlapping group Lasso penalty. We employ an alternating direction method of multipliers (ADMM) to solve the proximal operator. Similarly, we develop an approximate method to solve $OGL_0$ O G L 0 -SVD. Applications of these methods and comparison with competing ones using simulated data demonstrate their effectiveness. Extensive applications of them onto several real gene expression data with gene prior group knowledge identify some biologically interpretable gene modules.