Detecting Multivariate Gene Interactions in RNA-Seq Data Using Optimal Bayesian Classification

Knight, Jason; Ivanov, Ivan; Triff, Karen; Chapkin, Robert S.; Dougherty, Edward R.

doi:10.1109/tcbb.2015.2485223

Cited by 10 publications

(8 citation statements)

References 31 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This paper considers a Gaussian model, in which we can derive closed-form solutions, as the case with the OBC. Since many practical problems cannot be approximated by a Gaussian model, an important aspect of OBC development has been the utilization of MCMC methods [35], [36]. In a forthcoming paper, we extend the OBTL setting to count data with a Negative Binomial model, in which the inference of parameters is done by MCMC.…”

Section: Discussionmentioning

confidence: 99%

Optimal Bayesian Transfer Learning

Karbalayghareh

Qian

Dougherty

2018

IEEE Trans. Signal Process.

Self Cite

View full text Add to dashboard Cite

Transfer learning has recently attracted significant research attention, as it simultaneously learns from different source domains, which have plenty of labeled data, and transfers the relevant knowledge to the target domain with limited labeled data to improve the prediction performance. We propose a Bayesian transfer learning framework, in the homogeneous transfer learning scenario, where the source and target domains are related through the joint prior density of the model parameters. The modeling of joint prior densities enables better understanding of the "transferability" between domains. We define a joint Wishart distribution for the precision matrices of the Gaussian feature-label distributions in the source and target domains to act like a bridge that transfers the useful information of the source domain to help classification in the target domain by improving the target posteriors. Using several theorems in multivariate statistics, the posteriors and posterior predictive densities are derived in closed forms with hypergeometric functions of matrix argument, leading to our novel closed-form and fast Optimal Bayesian Transfer Learning (OBTL) classifier. Experimental results on both synthetic and real-world benchmark data confirm the superb performance of the OBTL compared to the other state-of-the-art transfer learning and domain adaptation methods.

show abstract

Section: Discussionmentioning

confidence: 99%

Optimal Bayesian Transfer Learning

Karbalayghareh

Qian

Dougherty

2018

IEEE Trans. Signal Process.

Self Cite

View full text Add to dashboard Cite

show abstract

“…This is not generally the case. Markov-chain-Monte-Carlo (MCMC) OBC methods were introduced in [17, 18] for RNA-Seq application, and are usually used in real-world settings where Gaussian models are not appropriate. Other applications include liquid chromatography-mass spectrometry data [19], selection reaction monitoring data [20], and classification based on dynamical measurements of single-gene expression measurements [21].…”

Section: Classificationmentioning

confidence: 99%

A Nonmathematical Review of Optimal Operator and Experimental Design for Uncertain Scientific Models with Application to Genomics

Dougherty

2019

Self Cite

View full text Add to dashboard Cite

Introduction: The most basic aspect of modern engineering is the design of operators to act on physical systems in an optimal manner relative to a desired objective – for instance, designing a control policy to autonomously direct a system or designing a classifier to make decisions regarding the system. These kinds of problems appear in biomedical science, where physical models are created with the intention of using them to design tools for diagnosis, prognosis, and therapy. Methods: In the classical paradigm, our knowledge regarding the model is certain; however, in practice, especially with complex systems, our knowledge is uncertain and operators must be designed while taking this uncertainty into account. The related concepts of intrinsically Bayesian robust operators and optimal Bayesian operators treat operator design under uncertainty. An objective-based experimental design procedure is naturally related to operator design: We would like to perform an experiment that maximally reduces our uncertainty as it pertains to our objective. Results & Discussion: This paper provides a nonmathematical review of optimal Bayesian operators directed at biomedical scientists. It considers two applications important to genomics, structural intervention in gene regulatory networks and classification. Conclusion: The salient point regarding intrinsically Bayesian operators is that uncertainty is quantified relative to the scientific model, and the prior distribution is on the parameters of this model. Optimization has direct physical (biological) meaning. This is opposed to the common method of placing prior distributions on the parameters of the operator, in which case there is a scientific gap between operator design and the phenomena.

show abstract

“…A methodology [18] in which observed count data is modelled as being negative binomially distributed is proposed to infer gene regulatory networks using RNA-seq time series data. To identify multivariate gene interaction in RNA-seq data, an application of BEE and OBC is demonstrated [19] to differentiate biological phenotypes. To infer gene regulatory network Legendre neural network (LNN) is proposed [20] and to www.ijacsa.thesai.org optimize the parameters of Legendre neural network, Firefly algorithm is used.…”

Section: Related Workmentioning

confidence: 99%

A Simple Approach for Representation of Gene Regulatory Networks (GRN)

Haq¹,

Ferzund²,

Hussain³

2018

ijacsa

View full text Add to dashboard Cite

Gene expressions are controlled by a series of processes known as Gene Regulation, and their abstract mapping is represented by Gene Regulatory Network (GRN) which is a descriptive model of gene interactions. Reverse engineering GRNs can reveal the complexity of gene interactions whose comprehension can lead to several other details. RNA-seq data provides better measurement of gene expressions; however it is difficult to infer GRNs using it because of its discreteness. Multiple other methods have already been proposed to infer GRN using RNA-seq data, but these methodologies are difficult to grasp. In this paper, a simple model is presented to infer GRNs, using RNA-seq based coexpression map provided by GeneFriends database, and a graph-based database tool is used to create regulatory network. The obtained results show that it is convenient to use graph database tools to work with regulatory networks instead of developing a new model from scratch.

show abstract

Detecting Multivariate Gene Interactions in RNA-Seq Data Using Optimal Bayesian Classification

Cited by 10 publications

References 31 publications

Optimal Bayesian Transfer Learning

Optimal Bayesian Transfer Learning

A Nonmathematical Review of Optimal Operator and Experimental Design for Uncertain Scientific Models with Application to Genomics

A Simple Approach for Representation of Gene Regulatory Networks (GRN)

Contact Info

Product

Resources

About