IJBST 2017 Volume 10 Issue 9

International Journal of BioSciences and Technology (IJBST) ISSN: 0974-3987

IJBST Journal Group -- Open Access -- NO Fees -- NO Processing Charges -- 100% Non Profit Initiatives

The IJBST Journal Group subscribes to the San Francisco Declaration on Research Assessment and the The European Code of Conduct for Research Integrity

The IJBST Journal Group Archive can also be accessed at https://archive.org/details/IJBSTJournalGroup

Time Evolving Undirected Graphical Model for Protein-Protein Interaction Networks. Yasanthi Malika Hirimutugoda. IJBST (2017), 10(9):67-75

FULL TEXT PDF:

FULL TEXT SWF:

Title:

Time Evolving Undirected Graphical Model for Protein-Protein Interaction Networks

Authors & Affiliation:

Yasanthi Malika Hirimutugoda

Department of Information Technology, Sri Lanka Institute of Advanced Technological Education, Sri Lanka

yasanthimalika@yahoo.com

ABSTRACT:

Proteins are the workhorses of the cell that perform biological functions by interacting with other proteins. Many statistical methods for protein-protein interaction (PPI) have been studied without considering time-dependent changes in networks and the functionalities. These time-dependent functional and topological changes in the network are very crucial for identifying malfunctioning regulatory pathways at different disease stages. I introduced a novel method that models PPI networks as being dynamic in nature and evolving time-varying multivariate distribution with Conditional Random Fields (CRF). This research is directed towards implementing this new combinatorial algorithm on massively parallel architectures such as Graphics Processing Units (GPUs) for efficient computations for large scale bioinformatics datasets. I compared Conditional Random Fields (CRF) and the proposed novel method using CRF combined with the Block Coordinate Descent algorithm for human protein-protein interaction data set. Both are implemented on GPU-Accelerated Computing Architecture and the proposed novel method showed the advantages in predicting protein-protein interaction sites. I also show that the proposed approach is more efficient in 6.13% than standalone CRF++ in predicting protein-protein interaction sites.

Keywords: Proteins, time-varying, parallel, architectures, Conditional Random Fields (CRF), Graphics Processing Units, Block Coordinate Descent algorithm