BWT: An Index Structure to Speed-Up Both Exact and Inexact String Matching

Abstract

The BWT transformation of a string is originally proposed for string compression, but can also be used to speed up string matchings. In this chapter, we address two issues around this mechanism: (1) how to use BWT to improve the running time of a multiple pattern string matching process; and (2) how to integrate mismatching information into a search of BWT arrays to expedite string matching with k mismatches. For the first problem, we will first construct the BWT array of a target string s, denoted as BWT(s); and then establish a trie structure over a set of pattern strings \( \varvec{R}\,\varvec{ = }\,\left\{ {r_{1} , \ldots ,r_{l} } \right\} \), denoted as T(R). By scanning BWT(s) against T(R), the time spent for finding occurrences of r i ’s can be significantly reduced. For the second problem, for a given pattern string r, we will precompute its mismatching information (over some different substrings of it, denoted as M(r)) and construct a tree structure, called a mismatching tree, to record the mismatches between r and s during a search of BWT(s) against r. In this process, the mismatching tree can be effectively utilized to do some kind of useful mismatching information derivation based on M(r) to avoid any possible redundancy. Extensive experiments have been done to compare our methods with the existing ones, which show that for both the problems described above our methods are promising.