Dynamic correlations are pervasive in high-throughput data. Large numbers of gene pairs can change their correlation patterns in response to observed/unobserved changes in physiological states. ...Finding changes in correlation patterns can reveal important regulatory mechanisms. Currently there is no method that can effectively detect global dynamic correlation patterns in a dataset. Given the challenging nature of the problem, the currently available methods use genes as surrogate measurements of physiological states, which cannot faithfully represent true underlying biological signals. In this study we develop a new method that directly identifies strong latent dynamic correlation signals from the data matrix, named DCA: Dynamic Correlation Analysis. At the center of the method is a new metric for the identification of pairs of variables that are highly likely to be dynamically correlated, without knowing the underlying physiological states that govern the dynamic correlation. We validate the performance of the method with extensive simulations. We applied the method to three real datasets: a single cell RNA-seq dataset, a bulk RNA-seq dataset, and a microarray gene expression dataset. In all three datasets, the method reveals novel latent factors with clear biological meaning, bringing new insights into the data.
Full text
Available for:
DOBA, IZUM, KILJ, NUK, PILJ, PNG, SAZU, SIK, UILJ, UKNU, UL, UM, UPUK
In predictive model development, gene expression data is associated with the unique challenge that the number of samples (n) is much smaller than the amount of features (p). This "n ≪ p" property has ...prevented classification of gene expression data from deep learning techniques, which have been proved powerful under "n > p" scenarios in other application fields, such as image classification. Further, the sparsity of effective features with unknown correlation structures in gene expression profiles brings more challenges for classification tasks. To tackle these problems, we propose a newly developed classifier named Forest Deep Neural Network (fDNN), to integrate the deep neural network architecture with a supervised forest feature detector. Using this built-in feature detector, the method is able to learn sparse feature representations and feed the representations into a neural network to mitigate the overfitting problem. Simulation experiments and real data analyses using two RNA-seq expression datasets are conducted to evaluate fDNN's capability. The method is demonstrated a useful addition to current predictive models with better classification performance and more meaningful selected features compared to ordinary random forests and deep neural networks.
Full text
Available for:
IZUM, KILJ, NUK, PILJ, PNG, SAZU, UL, UM, UPUK
Abstract
Motivation
Gene expression data represents a unique challenge in predictive model building, because of the small number of samples (n) compared with the huge amount of features (p). This ...'n≪p' property has hampered application of deep learning techniques for disease outcome classification. Sparse learning by incorporating external gene network information could be a potential solution to this issue. Still, the problem is very challenging because (i) there are tens of thousands of features and only hundreds of training samples, (ii) the scale-free structure of the gene network is unfriendly to the setup of convolutional neural networks.
Results
To address these issues and build a robust classification model, we propose the Graph-Embedded Deep Feedforward Networks (GEDFN), to integrate external relational information of features into the deep neural network architecture. The method is able to achieve sparse connection between network layers to prevent overfitting. To validate the method's capability, we conducted both simulation experiments and real data analysis using a breast invasive carcinoma RNA-seq dataset and a kidney renal clear cell carcinoma RNA-seq dataset from The Cancer Genome Atlas. The resulting high classification accuracy and easily interpretable feature selection results suggest the method is a useful addition to the current graph-guided classification models and feature selection procedures.
Availability and implementation
The method is available at https://github.com/yunchuankong/GEDFN.
Supplementary information
Supplementary data are available at Bioinformatics online.
In the integrative analyses of omics data, it is often of interest to extract data representation from one data type that best reflect its relations with another data type. This task is traditionally ...fulfilled by linear methods such as canonical correlation analysis (CCA) and partial least squares (PLS). However, information contained in one data type pertaining to the other data type may be complex and in nonlinear form. Deep learning provides a convenient alternative to extract low-dimensional nonlinear data embedding. In addition, the deep learning setup can naturally incorporate the effects of clinical confounding factors into the integrative analysis. Here we report a deep learning setup, named Autoencoder-based Integrative Multi-omics data Embedding (AIME), to extract data representation for omics data integrative analysis. The method can adjust for confounder variables, achieve informative data embedding, rank features in terms of their contributions, and find pairs of features from the two data types that are related to each other through the data embedding. In simulation studies, the method was highly effective in the extraction of major contributing features between data types. Using two real microRNA-gene expression datasets, one with confounder variables and one without, we show that AIME excluded the influence of confounders, and extracted biologically plausible novel information. The R package based on Keras and the TensorFlow backend is available at https://github.com/tianwei-yu/AIME.
Full text
Available for:
DOBA, IZUM, KILJ, NUK, PILJ, PNG, SAZU, SIK, UILJ, UKNU, UL, UM, UPUK
Abstract
Motivation
A unique challenge in predictive model building for omics data has been the small number of samples (n) versus the large amount of features (p). This ‘n≪p’ property brings ...difficulties for disease outcome classification using deep learning techniques. Sparse learning by incorporating known functional relationships between the biological units, such as the graph-embedded deep feedforward network (GEDFN) model, has been a solution to this issue. However, such methods require an existing feature graph, and potential mis-specification of the feature graph can be harmful on classification and feature selection.
Results
To address this limitation and develop a robust classification model without relying on external knowledge, we propose a forest graph-embedded deep feedforward network (forgeNet) model, to integrate the GEDFN architecture with a forest feature graph extractor, so that the feature graph can be learned in a supervised manner and specifically constructed for a given prediction task. To validate the method’s capability, we experimented the forgeNet model with both synthetic and real datasets. The resulting high classification accuracy suggests that the method is a valuable addition to sparse deep learning models for omics data.
Availability and implementation
The method is available at https://github.com/yunchuankong/forgeNet.
Contact
tianwei.yu@emory.edu
Supplementary information
Supplementary data are available at Bioinformatics online.
The receiver operating characteristic (ROC) curve is an important tool to gauge the performance of classifiers. In certain situations of high-throughput data analysis, the data is heavily ...class-skewed, i.e. most features tested belong to the true negative class. In such cases, only a small portion of the ROC curve is relevant in practical terms, rendering the ROC curve and its area under the curve (AUC) insufficient for the purpose of judging classifier performance. Here we define an ROC surface (ROCS) using true positive rate (TPR), false positive rate (FPR), and true discovery rate (TDR). The ROC surface, together with the associated quantities, volume under the surface (VUS) and FDR-controlled area under the ROC curve (FCAUC), provide a useful approach for gauging classifier performance on class-skewed high-throughput data. The implementation as an R package is available at http://userwww.service.emory.edu/~tyu8/ROCS/.
Full text
Available for:
DOBA, IZUM, KILJ, NUK, PILJ, PNG, SAZU, SIK, UILJ, UKNU, UL, UM, UPUK
The biological regulatory system is highly dynamic. Correlations between functionally related genes change over different biological conditions, which are often unobserved in the data. At the gene ...level, the dynamic correlations result in three-way gene interactions involving a pair of genes that change correlation, and a third gene that reflects the underlying cellular conditions. This type of ternary relation can be quantified by the Liquid Association statistic. Studying these three-way interactions at the gene triplet level have revealed important regulatory mechanisms in the biological system. Currently, due to the extremely large amount of possible combinations of triplets within a high-throughput gene expression dataset, no method is available to examine the ternary relationship at the biological system level and formally address the false discovery issue.
Here we propose a new method, Hypergraph for Dynamic Correlation (HDC), to construct module-level three-way interaction networks. The method is able to present integrative uniform hypergraphs to reflect the global dynamic correlation pattern in the biological system, providing guidance to down-stream gene triplet-level analyses. To validate the method's ability, we conducted two real data experiments using a melanoma RNA-seq dataset from The Cancer Genome Atlas (TCGA) and a yeast cell cycle dataset. The resulting hypergraphs are clearly biologically plausible, and suggest novel relations relevant to the biological conditions in the data.
We believe the new approach provides a valuable alternative method to analyze omics data that can extract higher order structures. The software is at https://github.com/yunchuankong/HypergraphDynamicCorrelation .
Full text
Available for:
DOBA, IZUM, KILJ, NUK, PILJ, PNG, SAZU, SIK, UILJ, UKNU, UL, UM, UPUK
Motivation: Liquid chromatography-mass spectrometry (LC/MS) profiling is a promising approach for the quantification of metabolites from complex biological samples. Significant challenges exist in ...the analysis of LC/MS data, including noise reduction, feature identification/ quantification, feature alignment and computation efficiency. Result: Here we present a set of algorithms for the processing of high-resolution LC/MS data. The major technical improvements include the adaptive tolerance level searching rather than hard cutoff or binning, the use of non-parametric methods to fine-tune intensity grouping, the use of run filter to better preserve weak signals and the model-based estimation of peak intensities for absolute quantification. The algorithms are implemented in an R package apLCMS, which can efficiently process large LC/ MS datasets. Availability: The R package apLCMS is available at www.sph.emory.edu/apLCMS. Contact: tyu8@sph.emory.edu Supplementary information: Supplementary data are available at Bioinformatics online.
Remote sensing image scene classification is an important task of remote sensing image interpretation, which has recently been well addressed by the convolutional neural network owing to its powerful ...learning ability. However, due to the multiple types of geographical information and redundant background information of the remote sensing images, most of the CNN-based methods, especially those based on a single CNN model and those ignoring the combination of global and local features, exhibit limited performance on accurate classification. To compensate for such insufficiency, we propose a new dual-model deep feature fusion method based on an attention cascade global–local network (ACGLNet). Specifically, we use two popular CNNs as the feature extractors to extract complementary multiscale features from the input image. Considering the characteristics of the global and local features, the proposed ACGLNet filters the redundant background information from the low-level features through the spatial attention mechanism, followed by which the locally attended features are fused with the high-level features. Then, bilinear fusion is employed to produce the fused representation of the dual model, which is finally fed to the classifier. Through extensive experiments on four public remote sensing scene datasets, including UCM, AID, PatternNet, and OPTIMAL-31, we demonstrate the feasibility of the proposed method and its superiority over the state-of-the-art scene classification methods.
Full text
Available for:
IZUM, KILJ, NUK, PILJ, PNG, SAZU, UL, UM, UPUK
Modular structures are ubiquitous across various types of biological networks. The study of network modularity can help reveal regulatory mechanisms in systems biology, evolutionary biology and ...developmental biology. Identifying putative modular latent structures from high-throughput data using exploratory analysis can help better interpret the data and generate new hypotheses. Unsupervised learning methods designed for global dimension reduction or clustering fall short of identifying modules with factors acting in linear combinations.
We present an exploratory data analysis method named MLSA (Modular Latent Structure Analysis) to estimate modular latent structures, which can find co-regulative modules that involve non-coexpressive genes.
Through simulations and real-data analyses, we show that the method can recover modular latent structures effectively. In addition, the method also performed very well on data generated from sparse global latent factor models. The R code is available at http://userwww.service.emory.edu/~tyu8/MLSA/.
Full text
Available for:
DOBA, IZUM, KILJ, NUK, PILJ, PNG, SAZU, SIK, UILJ, UKNU, UL, UM, UPUK