Limits...
Novel Application of Junction Trees to the Interpretation of Epigenetic Differences among Lung Cancer Subtypes.

Pineda AL, Gopalakrishnan V - AMIA Jt Summits Transl Sci Proc (2015)

Bottom Line: We propose a novel workflow, called Junction trees to Knowledge (J2K) framework, for creating interpretable graphical representations that can be derived directly from in silico analysis of microarray data.Our workflow has three steps, preprocessing (discretization and feature selection), construction of a Bayesian network and, its subsequent transformation into a Junction tree.We found relevant cliques of methylated sites that are junctions of the network along with potential methylation biomarkers in the lung cancer pathogenesis.

View Article: PubMed Central - PubMed

Affiliation: The PRoBE Lab, Department of Biomedical Informatics, University of Pittsburgh School of Medicine, Pittsburgh, PA.

ABSTRACT
In this era of precision medicine, understanding the epigenetic differences in lung cancer subtypes could lead to personalized therapies by possibly reversing these alterations. Traditional methods for analyzing microarray data rely on the use of known pathways. We propose a novel workflow, called Junction trees to Knowledge (J2K) framework, for creating interpretable graphical representations that can be derived directly from in silico analysis of microarray data. Our workflow has three steps, preprocessing (discretization and feature selection), construction of a Bayesian network and, its subsequent transformation into a Junction tree. We used data from the Cancer Genome Atlas to perform preliminary analyses of this J2K framework. We found relevant cliques of methylated sites that are junctions of the network along with potential methylation biomarkers in the lung cancer pathogenesis.

No MeSH data available.


Related in: MedlinePlus

EBMC-derived JT, where the squares represent junctions while the circles represent cliques. An example is provided to show the importance of the JT to identify central cliques with important genes.
© Copyright Policy
Related In: Results  -  Collection


getmorefigures.php?uid=PMC4525224&req=5

f3-2092351: EBMC-derived JT, where the squares represent junctions while the circles represent cliques. An example is provided to show the importance of the JT to identify central cliques with important genes.

Mentions: As a conceptual method, we proposed the use of JTs as way of clarifying the structure of BNs. In Figure 3, we show the corresponding JT representation of the BNs seen in Figure 2. In the EBMC-derived JT representation we can start to think of new hypothesis with a greater biological relevance. For example, looking at the central clique (central circle) it is easy to see that there are key molecules that are worthwhile examining carefully, because a perturbation in this clique would have an impact on the entire structure. The central clique has the following genes: SELENBP1, AKR1B10, LPP, SH3BP1, BCDIN3, KRTHB4, MAPK8, TCF2. We used the suite NextBio® to test the association of this clique to different tissues and diseases in the known literature and curated studies. This suite finds that the central clique is associated with the epithelial cells of nasal turbinates, and the epithelial cells of bronchial large airways, and that it also correlates with esophageal cancer cell line OE21. The clique (and specially SELENBP1) is associated to the Selenium binding protein which is considered to be a tumor suppressor and a prognostic marker [28].


Novel Application of Junction Trees to the Interpretation of Epigenetic Differences among Lung Cancer Subtypes.

Pineda AL, Gopalakrishnan V - AMIA Jt Summits Transl Sci Proc (2015)

EBMC-derived JT, where the squares represent junctions while the circles represent cliques. An example is provided to show the importance of the JT to identify central cliques with important genes.
© Copyright Policy
Related In: Results  -  Collection

Show All Figures
getmorefigures.php?uid=PMC4525224&req=5

f3-2092351: EBMC-derived JT, where the squares represent junctions while the circles represent cliques. An example is provided to show the importance of the JT to identify central cliques with important genes.
Mentions: As a conceptual method, we proposed the use of JTs as way of clarifying the structure of BNs. In Figure 3, we show the corresponding JT representation of the BNs seen in Figure 2. In the EBMC-derived JT representation we can start to think of new hypothesis with a greater biological relevance. For example, looking at the central clique (central circle) it is easy to see that there are key molecules that are worthwhile examining carefully, because a perturbation in this clique would have an impact on the entire structure. The central clique has the following genes: SELENBP1, AKR1B10, LPP, SH3BP1, BCDIN3, KRTHB4, MAPK8, TCF2. We used the suite NextBio® to test the association of this clique to different tissues and diseases in the known literature and curated studies. This suite finds that the central clique is associated with the epithelial cells of nasal turbinates, and the epithelial cells of bronchial large airways, and that it also correlates with esophageal cancer cell line OE21. The clique (and specially SELENBP1) is associated to the Selenium binding protein which is considered to be a tumor suppressor and a prognostic marker [28].

Bottom Line: We propose a novel workflow, called Junction trees to Knowledge (J2K) framework, for creating interpretable graphical representations that can be derived directly from in silico analysis of microarray data.Our workflow has three steps, preprocessing (discretization and feature selection), construction of a Bayesian network and, its subsequent transformation into a Junction tree.We found relevant cliques of methylated sites that are junctions of the network along with potential methylation biomarkers in the lung cancer pathogenesis.

View Article: PubMed Central - PubMed

Affiliation: The PRoBE Lab, Department of Biomedical Informatics, University of Pittsburgh School of Medicine, Pittsburgh, PA.

ABSTRACT
In this era of precision medicine, understanding the epigenetic differences in lung cancer subtypes could lead to personalized therapies by possibly reversing these alterations. Traditional methods for analyzing microarray data rely on the use of known pathways. We propose a novel workflow, called Junction trees to Knowledge (J2K) framework, for creating interpretable graphical representations that can be derived directly from in silico analysis of microarray data. Our workflow has three steps, preprocessing (discretization and feature selection), construction of a Bayesian network and, its subsequent transformation into a Junction tree. We used data from the Cancer Genome Atlas to perform preliminary analyses of this J2K framework. We found relevant cliques of methylated sites that are junctions of the network along with potential methylation biomarkers in the lung cancer pathogenesis.

No MeSH data available.


Related in: MedlinePlus