The Use of Informed Priors in Biclustering of Gene Expression with the Hierarchical Dirichlet Process.

Date

2019-02-26

Author

Tercan, Bahar
Acar, Aybar Can

Metadata

Show full item record

This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.

Item Usage Stats

158
views

0
downloads

We motivate and describe the application of Hierarchical Dirichlet Process (HDP) models to the "soft" biclustering of gene expression data, in which we obtain modules (biclusters) where the affiliation of genes and samples with the modules are weighted, instead of being hard memberships. As a distinct contribution, we propose a method which HDP is informed with prior beliefs, significantly increasing the quality of the biclustering in terms of both the correctness of the number of modules inferred, and the precision of these modules, especially when evidence is sparse. We outline two such informed priors; one based on co-expression relationships inherent in the data, the other based on an externally provided regulatory network. We validate these results and compare the performance of our approach to Weighted Gene Correlation Network Analysis (WGCNA), another model that features weighted modules. We have, to this end, performed experiments on semi-synthetic data. The results show that HDP, with the addition of a well-informed prior, is able to capture the correct number of modules with increased accuracy. Furthermore, the model becomes robust to changes in the strength of the prior. We conclude by discussing these results and the benefits provided by our approach for gene expression analysis and network validation.

Subject Keywords

Gene expression, Analytical models, Data models, Cancer, Biological system modeling, Bioinformatics, Probabilistic logic, Transcriptomics, Gene expression analysis, Mixed-membership models, Bayesian non-parametrics, Hierarchical Dirichlet process (HDP), Systems biology, Bioinformatics, Probabilistic algorithms

URI

https://hdl.handle.net/11511/31264

Journal

IEEE/ACM transactions on computational biology and bioinformatics

DOI

https://doi.org/10.1109/tcbb.2019.2901676

Collections

Graduate School of Informatics, Article

Suggestions

OpenMETU
Core

The Usage of Two Level Random Intercept Model Specifications in the Analysis of Achievement in Mathematics Gökalp Yavuz, Fulya (2013-12-01) Hierarchical models are highly useful tools for clustered and multilevel type of data and coefficients can vary by clusters in these models. In this study, several types of two-level random intercept model specifications are used to compare the mathematics scores of 8th grade students from three different safe and orderly levels of schools, after taking into account of variation both between classes and between students within the same class. The data obtained from Trends in International Mathematics and Sc...
A Methodology to develop process ontology from organizational guidelines written in natural language Gürbüz, Özge; Demirörs, Onur; Department of Information Systems (2017) Integrating ontologies with process modeling improves data representations and makes it easier to query, store and reuse processes at the semantics level. Therefore, in recent years, this topic has become increasingly popular. The studies in the literature have proposed methods for the integration process either to relate domain ontologies to process models or to transform process models to process ontologies. Another way to establish the integration between ontologies and process models is to develop proce...
Compatible and incompatible abstractions in Bayesian networks Yet, Barbaros (2014-05-01) The graphical structure of a Bayesian network (BN) makes it a technology well-suited for developing decision support models from a combination of domain knowledge and data. The domain knowledge of experts is used to determine the graphical structure of the BN, corresponding to the relationships and between variables, and data is used for learning the strength of these relationships. However, the available data seldom match the variables in the structure that is elicited from experts, whose models may be qui...
A Hypergraph based framework for representing aggregated user profiles, employing it for a recommender system and personalized search through a hypernetwork method Tarakçı, Hilal; Manguoğlu, Murat; Çiçekli, Fehime Nihan; Department of Computer Engineering (2017) In this thesis, we present a hypergraph based user modeling framework to aggregate partial profiles of the individual and obtain a complete, semantically enriched, multi-domain user model. We also show that the constructed user model can be used to support different personalization services including recommendation. We evaluated the user model against datasets consisting of user's social accounts including Facebook, Twitter, LinkedIn and Stack Overflow. The evaluation results confirmed that the proposed use...
Model-integrated development of field artillery federation object model Özhan, Gürkan; Dinç, Ali Cem; Oğuztüzün, Mehmet Halit S. (2010-12-01) This paper presents the automatic transformation of a Field Artillery Conceptual Data Model (FADM) into a High Level Architecture (HLA) Object Model Template (OMT) Model (HOM). It is part of a series of transformations from field artillery mission space to federation architecture to executable distributed simulation code. The approach followed in the course of this work adheres to the Model-Driven Engineering (MDE) philosophy. The model transformation is carried out with the Graph Rewriting and Transformati...

Citation Formats

B. Tercan and A. C. Acar, “The Use of Informed Priors in Biclustering of Gene Expression with the Hierarchical Dirichlet Process.,” IEEE/ACM transactions on computational biology and bioinformatics, 2019, Accessed: 00, 2020. [Online]. Available: https://hdl.handle.net/11511/31264.