Department of Computer Science, Stanford University, Stanford, California, USA.
J Chem Inf Model. 2010 Apr 26;50(4):560-4. doi: 10.1021/ci100011z.
LINGOs are a holographic measure of chemical similarity based on text comparison of SMILES strings. We present a new algorithm for calculating LINGO similarities amenable to parallelization on SIMD architectures (such as GPUs and vector units of modern CPUs). We show that it is nearly 3x as fast as existing algorithms on a CPU, and over 80x faster than existing methods when run on a GPU.
LINGOs 是一种基于 SMILES 字符串文本比较的化学相似性全息度量。我们提出了一种新的算法,可在 SIMD 架构(如 GPU 和现代 CPU 的向量单元)上进行并行化计算 LINGO 相似度。我们发现,它在 CPU 上的速度比现有算法快近 3 倍,在 GPU 上运行时比现有方法快 80 倍以上。