摘要：This study introduces a two-level strategy for efficient execution of multiple sequence alignment (MSA) of complex heterogeneous sequences. The two levels of the proposed technique are comprised of: designing the discrete firefly algorithm (DFFA) for the formation and implementation of makespan minimisation on parallel machines, followed by performing Ctrie-based caching for pairwise alignment to reduce the load on the data servers for handling multiple queries. The proposed strategy addresses a multi-client problem that aims to acquire the full advantage of the computational power of parallel connected machines. Further, it is shown that the inclusion of Ctrie as caching mechanism successively improves the performance of the system with accretion in several sequences. Performance of proposed DFFA is also compared with discrete versions of four swarm intelligence based algorithms at the criteria of makespan minimisation and the rate of convergence on two kinds of complex and diverse datasets. The work is unique in this sense: it is the first swarm-intelligence-based implementation for the addressed problem; it is so far the first approach for Ctrie based caching of the MSA on the scheduled parallel machines; hybridisation of DFFA with Ctrie for caching the MSA results is also a novel implementation.
