DEEPAligner: Deep encoding of pathways to align epigenetic signatures

• Published in: Computational biology and chemistry 2018-02, Vol.72, p.87-95
• Main Authors: Visakh, R., Abdul Nazeer, K.A.
• Format: Article
• Language: English
• Subjects: Deep encoding; Differential gene expression; Differential gene methylation; Epigenetics; Pathway-pathway interaction network
• ISSN: 1476-9271; 1476-928X
• DOI: 10.1016/j.compbiolchem.2018.01.002

[Display omitted] •Epigenetic mechanisms like DNA Methylation regulate biological pathways.•Pathways encode strong methylation signatures that distinguish biologically distinct subtypes.•A novel signature-based alignment method called Deep Encoded Epigenetic Pathway Aligner (DEEPAligner) is proposed to identify conserved methylation patterns across pathways.•Experiments on four benchmark cancer datasets reveal epigenetic signatures that are conserved in cancer-specific and across-cancer subtypes.•This research fosters recent efforts in tumor molecular pathology of cancer. Recently, differential DNA Methylation is known to affect the regulatory mechanism of biological pathways. A pathway encompasses a set of interacting genes or gene products that altogether perform a given biological function. Pathways often encode strong methylation signatures that are capable of distinguishing biologically distinct subtypes. Even though Next Generation Sequencing techniques such as MeDIP-seq and MBD-isolated genome sequencing (MiGS) allow for genome-wide identification of clinical and biological subtypes, there is a pressing need for computational methods to compare epigenetic signatures across pathways. A novel alignment method, called DEEPAligner (Deep Encoded Epigenetic Pathway Aligner), is proposed in this paper that finds functionally consistent and topologically sound alignments of epigenetic signatures from pathway networks. A deep embedding framework is used to obtain epigenetic signatures from pathways which are then aligned for functional consistency and local topological similarity. Experiments on four benchmark cancer datasets reveal epigenetic signatures that are conserved in cancer-specific and across-cancer subtypes. The proposed deep embedding framework obtains highly coherent signatures that are aligned for biological as well as structural orthology. Comparison with state-of-the-art network alignment methods clearly suggest that the proposed method obtains topologically and functionally more consistent alignments. http://bdbl.nitc.ac.in/DEEPAligner