scholarly journals Adversarial generation of gene expression data

2021 ◽  
Author(s):  
Ramon Viñas ◽  
Helena Andrés-Terré ◽  
Pietro Liò ◽  
Kevin Bryson
Keyword(s):  
Gene Expression ◽  
Gene Expression Data ◽  
Synthetic Data ◽  
Gene Clusters ◽  
Supplementary Information ◽  
Expression Data ◽  
Generative Adversarial Network ◽  
Adversarial Network ◽  
Wide Range ◽  
Transcriptomics Data

Abstract Motivation High-throughput gene expression can be used to address a wide range of fundamental biological problems, but datasets of an appropriate size are often unavailable. Moreover, existing transcriptomics simulators have been criticized because they fail to emulate key properties of gene expression data. In this article, we develop a method based on a conditional generative adversarial network to generate realistic transcriptomics data for Escherichia coli and humans. We assess the performance of our approach across several tissues and cancer-types. Results We show that our model preserves several gene expression properties significantly better than widely used simulators, such as SynTReN or GeneNetWeaver. The synthetic data preserve tissue- and cancer-specific properties of transcriptomics data. Moreover, it exhibits real gene clusters and ontologies both at local and global scales, suggesting that the model learns to approximate the gene expression manifold in a biologically meaningful way. Availability and implementation Code is available at: https://github.com/rvinas/adversarial-gene-expression. Supplementary information Supplementary data are available at Bioinformatics online.

scholarly journals Adversarial generation of gene expression data

2019 ◽  
Author(s):  
Ramon Viñas ◽  
Helena Andrés-Terré ◽  
Pietro Liò ◽  
Kevin Bryson
Keyword(s):  
Gene Expression ◽  
Gene Expression Data ◽  
Regulatory Networks ◽  
Network Inference ◽  
Turing Test ◽  
Expression Data ◽  
Generative Adversarial Network ◽  
Adversarial Network ◽  
Inference Algorithms ◽  
Gene Regulatory

AbstractThe problem of reverse engineering gene regulatory networks from high-throughput expression data is one of the biggest challenges in bioinformatics. In order to benchmark network inference algorithms, simulators of well-characterized expression datasets are often required. However, existing simulators have been criticized because they fail to emulate key properties of gene expression data.In this study we address two problems. First, we propose mechanisms to faithfully assess the realism of a synthetic gene expression dataset. Second, we design an adversarial simulator of expression data, gGAN, based on a Generative Adversarial Network. We show that our model outperforms existing simulators by a large margin, achieving realism scores that are up to 17 times higher than those of GeneNetWeaver and SynTReN. More importantly, our results show that gGAN is, to our best knowledge, the first simulator that passes the Turing test for gene expression data proposed by Maier et al. (2013).

scholarly journals Network Completion for Static Gene Expression Data

2014 ◽  
Vol 2014 ◽  
pp. 1-9 ◽  
Author(s):  
Natsu Nakajima ◽  
Tatsuya Akutsu
Keyword(s):  
Gene Expression ◽  
Gene Expression Data ◽  
Synthetic Data ◽  
Optimal Solution ◽  
Genetic Networks ◽  
Expression Data ◽  
Initial Network ◽  
Static Data ◽  
Normal Gene ◽  
Stationary Conditions

We tackle the problem of completing and inferring genetic networks under stationary conditions from static data, where network completion is to make the minimum amount of modifications to an initial network so that the completed network is most consistent with the expression data in which addition of edges and deletion of edges are basic modification operations. For this problem, we present a new method for network completion using dynamic programming and least-squares fitting. This method can find an optimal solution in polynomial time if the maximum indegree of the network is bounded by a constant. We evaluate the effectiveness of our method through computational experiments using synthetic data. Furthermore, we demonstrate that our proposed method can distinguish the differences between two types of genetic networks under stationary conditions from lung cancer and normal gene expression data.

CURVE-BASED CLUSTERING OF TIME COURSE GENE EXPRESSION DATA USING SELF-ORGANIZING MAPS

2009 ◽  
Vol 07 (04) ◽  
pp. 645-661 ◽  
Author(s):  
XIN CHEN
Keyword(s):  
Gene Expression ◽  
Gene Expression Data ◽  
Regulatory Networks ◽  
Time Course ◽  
Clustering Algorithm ◽  
Expression Patterns ◽  
Self Organizing Map ◽  
Expression Data ◽  
Wide Range ◽  
Self Organizing

There is an increasing interest in clustering time course gene expression data to investigate a wide range of biological processes. However, developing a clustering algorithm ideal for time course gene express data is still challenging. As timing is an important factor in defining true clusters, a clustering algorithm shall explore expression correlations between time points in order to achieve a high clustering accuracy. Moreover, inter-cluster gene relationships are often desired in order to facilitate the computational inference of biological pathways and regulatory networks. In this paper, a new clustering algorithm called CurveSOM is developed to offer both features above. It first presents each gene by a cubic smoothing spline fitted to the time course expression profile, and then groups genes into clusters by applying a self-organizing map-based clustering on the resulting splines. CurveSOM has been tested on three well-studied yeast cell cycle datasets, and compared with four popular programs including Cluster 3.0, GENECLUSTER, MCLUST, and SSClust. The results show that CurveSOM is a very promising tool for the exploratory analysis of time course expression data, as it is not only able to group genes into clusters with high accuracy but also able to find true time-shifted correlations of expression patterns across clusters.

scholarly journals INTERRELATED TWO-WAY CLUSTERING AND ITS APPLICATION ON GENE EXPRESSION DATA

2005 ◽  
Vol 14 (04) ◽  
pp. 577-597 ◽  
Author(s):  
CHUN TANG ◽  
AIDONG ZHANG
Keyword(s):  
Gene Expression ◽  
Gene Expression Data ◽  
Domain Knowledge ◽  
Gene Clusters ◽  
Data Sets ◽  
Messenger Rnas ◽  
Expression Data ◽  
Large Numbers ◽  
Clustering Approach ◽  
Mrna Expression Profiling

Microarray technologies are capable of simultaneously measuring the signals for thousands of messenger RNAs and large numbers of proteins from single samples. Arrays are now widely used in basic biomedical research for mRNA expression profiling and are increasingly being used to explore patterns of gene expression in clinical research. Most research has focused on the interpretation of the meaning of the microarray data which are transformed into gene expression matrices where usually the rows represent genes, the columns represent various samples. Clustering samples can be done by analyzing and eliminating of irrelevant genes. However, majority methods are supervised (or assisted by domain knowledge), less attention has been paid on unsupervised approaches which are important when little domain knowledge is available. In this paper, we present a new framework for unsupervised analysis of gene expression data, which applies an interrelated two-way clustering approach on the gene expression matrices. The goal of clustering is to identify important genes and perform cluster discovery on samples. The advantage of this approach is that we can dynamically manipulate the relationship between the gene clusters and sample groups while conducting an iterative clustering through both of them. The performance of the proposed method with various gene expression data sets is also illustrated.

scholarly journals Addressing confounding artifacts in reconstruction of gene co-expression networks

2017 ◽  
Author(s):  
Princy Parsana ◽  
Claire Ruberman ◽  
Andrew E. Jaffe ◽  
Michael C. Schatz ◽  
Alexis Battle ◽  
...  
Keyword(s):  
Gene Expression ◽  
Gene Expression Data ◽  
Network Inference ◽  
Principal Component ◽  
Network Reconstruction ◽  
Common Interest ◽  
Expression Data ◽  
Reconstruction Algorithms ◽  
Wide Range ◽  
False Discoveries

AbstractBackgroundGene co-expression networks capture diverse biological relationships between genes, and are important tools in predicting gene function and understanding disease mechanisms. Functional interactions between genes have not been fully characterized for most organisms, and therefore reconstruction of gene co-expression networks has been of common interest in a variety of settings. However, methods routinely used for reconstruction of gene co-expression networks do not account for confounding artifacts known to affect high dimensional gene expression measurements.ResultsIn this study, we show that artifacts such as batch effects in gene expression data confound commonly used network reconstruction algorithms. Both theoretically and empirically, we demonstrate that removing the effects of top principal components from gene expression measurements prior to network inference can reduce false discoveries, especially when well annotated technical covariates are not available. Using expression data from the GTEx project in multiple tissues and hundreds of individuals, we show that this latent factor residualization approach often reduces false discoveries in the reconstructed networks.ConclusionNetwork reconstruction is susceptible to confounders that affect measurements of gene expression. Even controlling for major individual known technical covariates fails to fully eliminate confounding variation from the data. In studies where a wide range of annotated technical factors are measured and available, correcting gene expression data with multiple covariates can also improve network reconstruction, but such extensive annotations are not always available. Our study shows that principal component correction, which does not depend on study design or annotation of all relevant confounders, removes patterns of artifactual variation and improves network reconstruction in both simulated data, and gene expression data from GTEx project. We have implemented our PC correction approach in the Bioconductor package sva which can be used prior to network reconstruction with a range of methods.

scholarly journals Model-based clustering of multi-tissue gene expression data

2019 ◽  
Author(s):  
Pau Erola ◽  
Johan L M Björkegren ◽  
Tom Michoel
Keyword(s):  
Gene Expression ◽  
Gene Expression Data ◽  
Clustering Algorithm ◽  
Expression Profiles ◽  
Individual Characteristics ◽  
Supplementary Information ◽  
Expression Data ◽  
Model Based ◽  
Tissue Gene Expression ◽  
Lemon Tree

Abstract Motivation Recently, it has become feasible to generate large-scale, multi-tissue gene expression data, where expression profiles are obtained from multiple tissues or organs sampled from dozens to hundreds of individuals. When traditional clustering methods are applied to this type of data, important information is lost, because they either require all tissues to be analyzed independently, ignoring dependencies and similarities between tissues, or to merge tissues in a single, monolithic dataset, ignoring individual characteristics of tissues. Results We developed a Bayesian model-based multi-tissue clustering algorithm, revamp, which can incorporate prior information on physiological tissue similarity, and which results in a set of clusters, each consisting of a core set of genes conserved across tissues as well as differential sets of genes specific to one or more subsets of tissues. Using data from seven vascular and metabolic tissues from over 100 individuals in the STockholm Atherosclerosis Gene Expression (STAGE) study, we demonstrate that multi-tissue clusters inferred by revamp are more enriched for tissue-dependent protein-protein interactions compared to alternative approaches. We further demonstrate that revamp results in easily interpretable multi-tissue gene expression associations to key coronary artery disease processes and clinical phenotypes in the STAGE individuals. Availability and implementation Revamp is implemented in the Lemon-Tree software, available at https://github.com/eb00/lemon-tree Supplementary information Supplementary data are available at Bioinformatics online.

scholarly journals Inferring TF activities and activity regulators from gene expression data with constraints from TF perturbation data

2020 ◽  
Author(s):  
Cynthia Z Ma ◽  
Michael R Brent
Keyword(s):  
Gene Expression ◽  
Gene Expression Data ◽  
Large Scale ◽  
Supplementary Information ◽  
Activity Levels ◽  
Expression Data ◽  
Gene Expression Matrix ◽  
Perturbation Data ◽  
Carry Over ◽  
Necessary And Sufficient

Abstract Motivation The activity of a transcription factor (TF) in a sample of cells is the extent to which it is exerting its regulatory potential. Many methods of inferring TF activity from gene expression data have been described, but due to the lack of appropriate large-scale datasets, systematic and objective validation has not been possible until now. Results We systematically evaluate and optimize the approach to TF activity inference in which a gene expression matrix is factored into a condition-independent matrix of control strengths and a condition-dependent matrix of TF activity levels. We find that expression data in which the activities of individual TFs have been perturbed are both necessary and sufficient for obtaining good performance. To a considerable extent, control strengths inferred using expression data from one growth condition carry over to other conditions, so the control strength matrices derived here can be used by others. Finally, we apply these methods to gain insight into the upstream factors that regulate the activities of yeast TFs Gcr2, Gln3, Gcn4 and Msn2. Availability and implementation Evaluation code and data are available at https://doi.org/10.5281/zenodo.4050573. Contact [email protected] Supplementary information Supplementary data are available at Bioinformatics online.

Sign in / Sign up

Export Citation Format

Share Document