Knowledge-based gene expression classification via matrix factorization

MOTIVATION: Modern machine learning methods based on matrix decomposition techniques, like independent component analysis (ICA) or non-negative matrix factorization (NMF), provide new and efficient analysis tools which are currently explored to analyze gene expression profiles. These exploratory feature extraction techniques yield expression modes (ICA) or metagenes (NMF). These extracted features are considered indicative of underlying regulatory processes. They can as well be applied to the classification of gene expression datasets by grouping samples into different categories for diagnostic purposes or group genes into functional categories for further investigation of related metabolic pathways and regulatory networks. RESULTS: In this study we focus on unsupervised matrix factorization techniques and apply ICA and sparse NMF to microarray datasets. The latter monitor the gene expression levels of human peripheral blood cells during differentiation from monocytes to macrophages. We show that these tools are able to identify relevant signatures in the deduced component matrices and extract informative sets of marker genes from these gene expression profiles. The methods rely on the joint discriminative power of a set of marker genes rather than on single marker genes. With these sets of marker genes, corroborated by leave-one-out or random forest cross-validation, the datasets could easily be classified into related diagnostic categories. The latter correspond to either monocytes versus macrophages or healthy vs Niemann Pick C disease patients.     

A flexible R package for nonnegative matrix factorization

Background  

Nonnegative Matrix Factorization (NMF) is an unsupervised learning technique that has been applied successfully in several fields, including signal processing, face recognition and text mining. Recent applications of NMF in bioinformatics have demonstrated its ability to extract meaningful information from high-dimensional data such as gene expression microarrays. Developments in NMF theory and applications have resulted in a variety of algorithms and methods. However, most NMF implementations have been on commercial platforms, while those that are freely available typically require programming skills. This limits their use by the wider research community.     

Extraction of food consumption systems by nonnegative matrix factorization (NMF) for the assessment of food choices

In Western countries where food supply is satisfactory, consumers organize their diets around a large combination of foods. It is the purpose of this article to examine how recent nonnegative matrix factorization (NMF) techniques can be applied to food consumption data to understand these combinations. Such data are nonnegative by nature and of high dimension. The NMF model provides a representation of consumption data through latent vectors with nonnegative coefficients, that we call consumption systems (CS), in a small number. As the NMF approach may encourage sparsity of the data representation produced, the resulting CS are easily interpretable. Beyond the illustration of its properties we provide through a simple simulation result, the NMF method is applied to data issued from a French consumption survey. The numerical results thus obtained are displayed and thoroughly discussed. A clustering based on the k-means method is also achieved in the resulting latent consumption space, to recover food consumption patterns easily usable for nutritionists.     

Gene expression data analysis

Microarrays are one of the latest breakthroughs in experimental molecular biology, which allow monitoring of gene expression for tens of thousands of genes in parallel and are already producing huge amounts of valuable data. Analysis and handling of such data is becoming one of the major bottlenecks in the utilization of the technology. The raw microarray data are images, which have to be transformed into gene expression matrices--tables where rows represent genes, columns represent various samples such as tissues or experimental conditions, and numbers in each cell characterize the expression level of the particular gene in the particular sample. These matrices have to be analyzed further, if any knowledge about the underlying biological processes is to be extracted. In this paper we concentrate on discussing bioinformatics methods used for such analysis. We briefly discuss supervised and unsupervised data analysis and its applications, such as predicting gene function classes and cancer classification. Then we discuss how the gene expression matrix can be used to predict putative regulatory signals in the genome sequences. In conclusion we discuss some possible future directions.     

A Framework for Regularized Non-Negative Matrix Factorization,with Application to the Analysis of Gene Expression Data

Non-negative matrix factorization (NMF) condenses high-dimensional data into lower-dimensional models subject to the requirement that data can only be added, never subtracted. However, the NMF problem does not have a unique solution, creating a need for additional constraints (regularization constraints) to promote informative solutions. Regularized NMF problems are more complicated than conventional NMF problems, creating a need for computational methods that incorporate the extra constraints in a reliable way. We developed novel methods for regularized NMF based on block-coordinate descent with proximal point modification and a fast optimization procedure over the alpha simplex. Our framework has important advantages in that it (a) accommodates for a wide range of regularization terms, including sparsity-inducing terms like the penalty, (b) guarantees that the solutions satisfy necessary conditions for optimality, ensuring that the results have well-defined numerical meaning, (c) allows the scale of the solution to be controlled exactly, and (d) is computationally efficient. We illustrate the use of our approach on in the context of gene expression microarray data analysis. The improvements described remedy key limitations of previous proposals, strengthen the theoretical basis of regularized NMF, and facilitate the use of regularized NMF in applications.     

CloudNMF: A MapReduce Implementation of Nonnegative Matrix Factorization for Large-scale Biological Datasets

In the past decades,advances in high-throughput technologies have led to the generation of huge amounts of biological data that require analysis and interpretation.Recently,nonnegative matrix factorization(NMF) has been introduced as an efficient way to reduce the complexity of data as well as to interpret them,and has been applied to various fields of biological research.In this paper,we present CloudNMF,a distributed open-source implementation of NMF on a MapReduce framework.Experimental evaluation demonstrated that CloudNMF is scalable and can be used to deal with huge amounts of data,which may enable various kinds of a high-throughput biological data analysis in the cloud.CloudNMF is freely accessible at http://admis.fudan.edu.cn/projects/CloudNMF.html.     

Sparse non-negative matrix factorizations via alternating non-negativity-constrained least squares for microarray data analysis

MOTIVATION: Many practical pattern recognition problems require non-negativity constraints. For example, pixels in digital images and chemical concentrations in bioinformatics are non-negative. Sparse non-negative matrix factorizations (NMFs) are useful when the degree of sparseness in the non-negative basis matrix or the non-negative coefficient matrix in an NMF needs to be controlled in approximating high-dimensional data in a lower dimensional space. RESULTS: In this article, we introduce a novel formulation of sparse NMF and show how the new formulation leads to a convergent sparse NMF algorithm via alternating non-negativity-constrained least squares. We apply our sparse NMF algorithm to cancer-class discovery and gene expression data analysis and offer biological analysis of the results obtained. Our experimental results illustrate that the proposed sparse NMF algorithm often achieves better clustering performance with shorter computing time compared to other existing NMF algorithms. AVAILABILITY: The software is available as supplementary material.     

The emergence of pattern discovery techniques in computational biology

In the past few years, pattern discovery has been emerging as a generic tool of choice for tackling problems from the computational biology domain. In this presentation, and after defining the problem in its generality, we review some of the algorithms that have appeared in the literature and describe several applications of pattern discovery to problems from computational biology.     

Nonnegative tensor factorization for continuous EEG classification

In this paper we present a method for continuous EEG classification, where we employ nonnegative tensor factorization (NTF) to determine discriminative spectral features and use the Viterbi algorithm to continuously classify multiple mental tasks. This is an extension of our previous work on the use of nonnegative matrix factorization (NMF) for EEG classification. Numerical experiments with two data sets in BCI competition, confirm the useful behavior of the method for continuous EEG classification.     

LinkNMF: Identification of histone modification modules in the human genome using nonnegative matrix factorization

Histone modifications are ubiquitous processes involved in various cellular mechanisms. Systemic analysis of multiple chromatin modifications has been used to characterize various chromatin states associated with functional DNA elements, gene expression, and specific biological functions. However, identification of modular modification patterns is still required to understand the functional associations between histone modification patterns and specific chromatin/DNA binding factors. To recognize modular modification patterns, we developed a novel algorithm that combines nonnegative matrix factorization (NMF) and a clique-detection algorithm. We applied it, called LinkNMF, to generate a comprehensive modification map in human CD4 + T cell promoter regions. Initially, we identified 11 modules not recognized by conventional approaches. The modules were grouped into two major classes: gene activation and repression. We found that genes targeted by each module were enriched with distinguishable biological functions, suggesting that each modular pattern plays a unique functional role. To explain the formation of modular patterns, we investigated the module-specific binding patterns of chromatin regulators. Application of LinkNMF to histone modification maps of diverse cells and developmental stages will be helpful for understanding how histone modifications regulate gene expression. The algorithm is available on our website at biodb.kaist.ac.kr/LinkNMF.     

Entropy based sub-dimensional evaluation and selection method for DNA microarray data classification

DNA microarray allows the measurement of expression levels of tens of thousands of genes simultaneously and has many applications in biology and medicine. Microarray data are very noisy and this makes it difficult for data analysis and classification. Sub-dimension based methods can overcome the noise problem by partitioning the conditions into sub-groups, performing classification with each group and integrating the results. However, there can be many sub-dimensional groups, which lead to a high computational complexity. In this paper, we propose an entropy-based method to evaluate and select important sub-dimensions and eliminate unimportant ones. This improves the computational efficiency considerably. We have tested our method on four microarray datasets and two other real-world datasets and the experiment results prove the effectiveness of our method.     

SPARCoC: A New Framework for Molecular Pattern Discovery and Cancer Gene Identification

It is challenging to cluster cancer patients of a certain histopathological type into molecular subtypes of clinical importance and identify gene signatures directly relevant to the subtypes. Current clustering approaches have inherent limitations, which prevent them from gauging the subtle heterogeneity of the molecular subtypes. In this paper we present a new framework: SPARCoC (Sparse-CoClust), which is based on a novel Common-background and Sparse-foreground Decomposition (CSD) model and the Maximum Block Improvement (MBI) co-clustering technique. SPARCoC has clear advantages compared with widely-used alternative approaches: hierarchical clustering (Hclust) and nonnegative matrix factorization (NMF). We apply SPARCoC to the study of lung adenocarcinoma (ADCA), an extremely heterogeneous histological type, and a significant challenge for molecular subtyping. For testing and verification, we use high quality gene expression profiling data of lung ADCA patients, and identify prognostic gene signatures which could cluster patients into subgroups that are significantly different in their overall survival (with p-values < 0.05). Our results are only based on gene expression profiling data analysis, without incorporating any other feature selection or clinical information; we are able to replicate our findings with completely independent datasets. SPARCoC is broadly applicable to large-scale genomic data to empower pattern discovery and cancer gene identification.     

Limited-Memory Fast Gradient Descent Method for Graph Regularized Nonnegative Matrix Factorization

Graph regularized nonnegative matrix factorization (GNMF) decomposes a nonnegative data matrix to the product of two lower-rank nonnegative factor matrices, i.e., and () and aims to preserve the local geometric structure of the dataset by minimizing squared Euclidean distance or Kullback-Leibler (KL) divergence between X and WH. The multiplicative update rule (MUR) is usually applied to optimize GNMF, but it suffers from the drawback of slow-convergence because it intrinsically advances one step along the rescaled negative gradient direction with a non-optimal step size. Recently, a multiple step-sizes fast gradient descent (MFGD) method has been proposed for optimizing NMF which accelerates MUR by searching the optimal step-size along the rescaled negative gradient direction with Newton''s method. However, the computational cost of MFGD is high because 1) the high-dimensional Hessian matrix is dense and costs too much memory; and 2) the Hessian inverse operator and its multiplication with gradient cost too much time. To overcome these deficiencies of MFGD, we propose an efficient limited-memory FGD (L-FGD) method for optimizing GNMF. In particular, we apply the limited-memory BFGS (L-BFGS) method to directly approximate the multiplication of the inverse Hessian and the gradient for searching the optimal step size in MFGD. The preliminary results on real-world datasets show that L-FGD is more efficient than both MFGD and MUR. To evaluate the effectiveness of L-FGD, we validate its clustering performance for optimizing KL-divergence based GNMF on two popular face image datasets including ORL and PIE and two text corpora including Reuters and TDT2. The experimental results confirm the effectiveness of L-FGD by comparing it with the representative GNMF solvers.     

Spinal afferent neurons projecting to the rat lung and pleura express acid sensitive channels

The molecular mechanisms of Idiopathic Pulmonary Fibrosis (IPF) remain elusive. Transforming Growth Factor beta 1(TGF-β1) is a key effector cytokine in the development of lung fibrosis. We used microarray and computational biology strategies to identify genes whose expression is significantly altered in alveolar epithelial cells (A549) in response to TGF-β1, IL-4 and IL-13 and Epstein Barr virus. A549 cells were exposed to 10 ng/ml TGF-β1, IL-4 and IL-13 at serial time points. Total RNA was used for hybridisation to Affymetrix Human Genome U133A microarrays. Each in vitro time-point was studied in duplicate and an average RMA value computed. Expression data for each time point was compared to control and a signal log ratio of 0.6 or greater taken to identify significant differential regulation. Using normalised RMA values and unsupervised Average Linkage Hierarchical Cluster Analysis, a list of 312 extracellular matrix (ECM) proteins or modulators of matrix turnover was curated via Onto-Compare and Gene-Ontology (GO) databases for baited cluster analysis of ECM associated genes. Interrogation of the dataset using ontological classification focused cluster analysis revealed coordinate differential expression of a large cohort of extracellular matrix associated genes. Of this grouping members of the ADAM (A disintegrin and Metalloproteinase domain containing) family of genes were differentially expressed. ADAM gene expression was also identified in EBV infected A549 cells as well as IL-13 and IL-4 stimulated cells. We probed pathologenomic activities (activation and functional activity) of ADAM19 and ADAMTS9 using siRNA and collagen assays. Knockdown of these genes resulted in diminished production of collagen in A549 cells exposed to TGF-β1, suggesting a potential role for these molecules in ECM accumulation in IPF.     

BEST: a novel computational approach for comparing gene expression patterns from early stages of Drosophila melanogaster development

Embryonic gene expression patterns are an indispensable part of modern developmental biology. Currently, investigators must visually inspect numerous images containing embryonic expression patterns to identify spatially similar patterns for inferring potential genetic interactions. The lack of a computational approach to identify pattern similarities is an impediment to advancement in developmental biology research because of the rapidly increasing amount of available embryonic gene expression data. Therefore, we have developed computational approaches to automate the comparison of gene expression patterns contained in images of early stage Drosophila melanogaster embryos (prior to the beginning of germ-band elongation); similarities and differences in gene expression patterns in these early stages have extensive developmental effects. Here we describe a basic expression search tool (BEST) to retrieve best matching expression patterns for a given query expression pattern and a computational device for gene interaction inference using gene expression pattern images and information on the associated genotypes and probes. Analysis of a prototype collection of Drosophila gene expression pattern images is presented to demonstrate the utility of these methods in identifying biologically meaningful matches and inferring gene interactions by direct image content analysis. In particular, the use of BEST searches for gene expression patterns is akin to that of BLAST searches for finding similar sequences. These computational developmental biology methodologies are likely to make the great wealth of embryonic gene expression pattern data easily accessible and to accelerate the discovery of developmental networks.