基于GPU优化的分子对接虚拟药物筛选方法的比较分析
GPU-optimized Approaches to Molecular Docking-based Virtual Screening in Drug Discovery: A Comparative Analysis
摘要：
COVID-19显示了对流行病做出快速反应的重要性。发现一种新药是一个非常漫长和复杂的过程，并且可以通过使用计算机模拟来加速初步阶段。特别是，虚拟筛选是一个计算机模拟阶段，需要将大量可能的候选药物筛选到可管理的数量。本文介绍了实现和比较分析的两个GPU优化实现的虚拟筛选算法针对新的GPU架构。第一种方法采用传统的方法，将评估单个分子所需的计算分散到整个GPU中。第二种使用批处理方法，该方法利用GPU的并行架构并行评估更多分子，而不考虑处理单个分子的延迟。本文介绍了所提出的解决方案的优点和缺点，突出了影响性能的实施细节。实验结果突出了两种方法在NVIDIA A100 GPU上运行时在几个目标分子数据库上的不同性能。这两种实现方式对于要处理的数据具有很强的依赖性。对于这两种情况，性能都在提高，同时降低了目标分子的尺寸（原子和可旋转键的数量）。这两种方法显示了不同的行为，相对于要筛选的分子数据库的大小。虽然延迟时间更快（分子更少）达到吞吐量方面的性能平台，但批量处理需要更大的分子集。然而，在初始过渡期之后的性能要高得多（高达5倍加速）。最后，为了检查这两种实现的效率，我们使用指令屋顶线方法深入分析了它们的工作负载特性。
英文摘要：
COVID-19 has shown the importance of having a fast response against pandemics. Finding a novel drug is a very long and complex procedure, and it is possible to accelerate the preliminary phases by using computer simulations. In particular, virtual screening is an in-silico phase that is needed to filter a large set of possible drug candidates to a manageable number. This paper presents the implementations and a comparative analysis of two GPU-optimized implementations of a virtual screening algorithm targeting novel GPU architectures. The first adopts a traditional approach that spreads the computation required to evaluate a single molecule across the entire GPU. The second uses a batched approach that exploits the parallel architecture of the GPU to evaluate more molecules in parallel, without considering the latency to process a single molecule. The paper describes the advantages and disadvantages of the proposed solutions, highlighting implementation details that impact the performance. Experimental results highlight the different performance of the two methods on several target molecule databases while running on NVIDIA A100 GPUs. The two implementations have a strong dependency with respect to the data to be processed. For both cases, the performance is improving while reducing the dimension of the target molecules (number of atoms and rotatable bonds). The two methods demonstrated a different behavior with respect to the size of the molecule database to be screened. While the latency one reaches sooner (with fewer molecules) the performance plateau in terms of throughput, the batched one requires a larger set of molecules. However, the performances after the initial transient period are much higher (up to 5x speed-up). Finally, to check the efficiency of both implementations we deeply analyzed their workload characteristics using the instruction roof-line methodology.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
