The Distribution and Deposition Algorithm for Multiple Sequences Sets

“Sequences set” is a mathematical model used in many applications such as scheduling, text process and biological sequences analysis. As the number of the sequences becomes larger, “single” sequence set model is not appropriate for the rapidly increasing problem sizes. For example, more and more text processing applications separate a single big text file into multiple files before processing. For these applications, the underline mathematical model is “multiple sequences sets” (MSS). Though there is increasing use of MSS, there is little research on how to process MSS efficiently. To process multiple sequences sets, sequences are first distributed to different sets, sequences for each set are then processed. Deriving effective algorithm for MSS processing is both interesting and challenging. In this paper, we tried to formulated the problem of Process of Multiple Sequences Sets (PMSS) by first defined the cost functions and performance ratio. Based on these, the PMSS problem is formulated as to minimize the total cost of process. We have proposed two greedy algorithms for the PMSS problem, which are based on generalization of algorithms for single sequences set. Then based on the analysis of the features of multiple sequences sets, we have proposed the Distribution and Deposition (DDA) algorithm and DDA* algorithm for PMSS problem. In DDA algorithm, the sequences are first distributed to multiple sets according to their alphabet contents; then sequences in each set are processed by deposition algorithm. The DDA* algorithm differs from the DDA algorithm in that the DDA* algorithm distributes sequences by clustering based on a set of sequence features (alphabet content is one of the properties). Experiments show that DDA and DDA* always output results with smaller costs than other algorithms, and DDA* outperforms DDA in most instances. This indicates that distribution of sequences to multiple sets according to sequence features before processing sequences on each set is beneficial. The DDA and DDA* algorithms are also efficient both in time and space.