Parallel Matrix Multiplication Algorithms Acquire Connected Network Motifs

Abstract

The network of interactions between biomolecules is essential to biological processes. Many studies have shown that molecular networks can be analyzed by breaking them down into smaller modules known as network motifs. We hypothesize that identifying the set of possible 5-node motifs and 6-node motifs embedded in a network is a necessary step to elucidate the complex topology of a network. Accomplishing this goal requires determining the complete set of motifs that are composed of five and six connected nodes. 
 We developed a parallel algorithm to reduce time consumption that tackles the exponential problem. It is implemented in matrix multiplication insert in the process of identifying isomorphic patterns and removing the isolated and disconnected patterns. The experiment showed that the parallelization matrix multiplication algorithm is approximately 1.4 times faster than serial programming for identifying 5-node motifs and approximately 1.3 times faster than serial programming for identifying 6-node motifs with all the nodes connected