Managing Complex Workflows in Bioinformatics: An Interactive Toolkit With GPU Acceleration
Managing Complex Workflows in Bioinformatics: An Interactive Toolkit With GPU Acceleration
复制标题
DOI：
10.1109/tnb.2018.2837122
复制
发表时间：
2018-07-01
影响因子：
3.9
通讯作者：
Mallawaarachchi, Vijini
中科院分区：
文献类型：
--
作者：
Welivita, Anuradha;Perera, Indika;Mallawaarachchi, Vijini
生物信息学研究在下一代测序等技术的帮助下继续以越来越大的规模向前发展，并提供工具支持以实现生物信息学过程的自动化。随着这种增长，大量的生物数据以前所未有的速度积累，需要高性能和高吞吐量的计算技术来处理这些数据集。使用硬件加速器，例如图形处理单元（GPU）和分布式计算，可以加速高性能计算环境中的大数据处理。它们能够实现更高的并行度，从而提高吞吐量。在本文中，我们介绍BioWorkflow，一个交互式的工作流管理系统，自动化的生物信息学分析与调度并行任务的能力，使用GPU加速和分布式计算。本文介绍了一个案例研究进行评估的一个复杂的工作流程与分支BioWorkflow执行的性能。结果表明，在多个序列比对计算期间，通过利用GPU获得了x2.89量级的增益，并且通过并行执行图节点获得了平均x2.832量级的速度增益（在n =5的情况下）。对于复杂的工作流程，综合速度提升了1.71倍。这证实了通过GPU加速和工作流节点的并发执行而具有并行性时比主流顺序工作流执行的预期更高的加速。该工具还提供了一个全面的用户界面，具有更好的交互性，可用于管理复杂的工作流程;系统可用性量表得分为82.9，证实该系统具有较高的可用性。
Bioinformatics research continues to advance at an increasing scale with the help of techniques such as next-generation sequencing and the availability of tool support to automate bioinformatics processes. With this growth, a large amount of biological data gets accumulated at an unprecedented rate, demanding high-performance and high-throughput computing technologies for processing such datasets. Use of hardware accelerators, such as graphics processing units (GPUs) and distributed computing, accelerates the processing of big data in high-performance computing environments. They enable higher degrees of parallelism to be achieved, thereby increasing the throughput. In this paper, we introduce BioWorkflow, an interactive workflow management system to automate the bioinformatics analyses with the capability of scheduling parallel tasks with the use of GPU-accelerated and distributed computing. This paper describes a case study carried out to evaluate the performance of a complex workflow with branching executed by BioWorkflow. The results indicate the gains of x2.89 magnitude by utilizing GPUs and gains in speed by average x2.832 magnitude (over n =5 scenarios) by parallel execution of graph nodes during multiple sequence alignment calculations. Combined speed-ups are achieved x1.71 times for complex workflows. This confirms the expected higher speed-ups when having parallelism through GPU-acceleration and concurrent execution of workflow nodes than the mainstream sequential workflow execution. The tool also provides a comprehensive user interface with better interactivity for managing complex workflows; a system usability scale score of 82.9 is confirmed high usability for the system.