GPU技术作为加速蛋白质序列局部复杂性分析的平台。

GPU technology as a platform for accelerating local complexity analysis of protein sequences.

作者信息

Papadopoulos Agathoklis, Kirmitzoglou Ioannis, Promponas Vasilis J, Theocharides Theocharis

出版信息

Annu Int Conf IEEE Eng Med Biol Soc. 2013;2013:2684-7. doi: 10.1109/EMBC.2013.6610093.

DOI:10.1109/EMBC.2013.6610093

Abstract

The use of GPGPU programming paradigm (running CUDA-enabled algorithms on GPU cards) in Bioinformatics showed promising results [1]. As such a similar approach can be used to speedup other algorithms such as CAST, a popular tool used for masking low-complexity regions (LCRs) in protein sequences [2] with increased sensitivity. We developed and implemented a CUDA-enabled version (GPU_CAST) of the multi-threaded version of CAST software first presented in [3] and optimized in [4]. The proposed software implementation uses the nVIDIA CUDA libraries and the GPGPU programming paradigm to take advantage of the inherent parallel characteristics of the CAST algorithm to execute the calculations on the GPU card of the host computer system. The GPU-based implementation presented in this work, is compared against the multi-threaded, multi-core optimized version of CAST [4] and yielded speedups of 5x-10x for large protein sequence datasets.

摘要

在生物信息学中使用通用并行图形处理单元（GPGPU）编程范式（在支持CUDA的图形处理器卡上运行算法）已显示出有前景的结果[1]。因此，类似的方法可用于加速其他算法，如CAST，这是一种用于掩盖蛋白质序列中低复杂性区域（LCR）的常用工具[2]，且具有更高的灵敏度。我们开发并实现了CAST软件多线程版本的支持CUDA的版本（GPU_CAST），该版本首次在[3]中提出，并在[4]中进行了优化。所提出的软件实现使用英伟达CUDA库和GPGPU编程范式，以利用CAST算法固有的并行特性，在主机系统的图形处理器卡上执行计算。本文提出的基于图形处理器的实现方法，与CAST的多线程、多核优化版本[4]进行了比较，对于大型蛋白质序列数据集，加速比达到了5倍至10倍。