A New Efficient Data Structure for Storage and Retrieval of Multiple Biosequences

摘要

Today's genome analysis applications require sequence representations allowing for fast access to their contents while also being memory-efficient enough to facilitate analyses of large-scale data. While a wide variety of sequence representations exist, lack of a generic implementation of efficient sequence storage has led to a plethora of poorly reusable or programming language-specific implementations. We present a novel, space-efficient data structure (GtEncseq) for storing multiple biological sequences of variable alphabet size, with customizable character transformations, wildcard support, and an assortment of internal representations optimized for different distributions of wildcards and sequence lengths. For the human genome (3.1 gigabases, including 237 million wildcard characters) our representation requires only 2 + 8cdot 10^{-6} bits per character. Implemented in C, our portable software implementation provides a variety of methods for random and sequential access to characters and substrings (including different reading directions) using an object-oriented interface. In addition, it includes access to metadata like sequence descriptions or character distributions. The library is extensible to be used from various scripting languages. GtEncseq is much more versatile than previous solutions, adding features that were previously unavailable. Benchmarks show that it is competitive with respect to space and time requirements.