基于加权Tanimoto系数的三维分子结构相似性度量
Weighted Tanimoto Coefficient for 3D Molecule Structure Similarity Measurement
摘要:
分子结构相似性搜索是化学信息学中的一个重要应用,特别是在药物发现中。相似性搜索是一种常用的分子结构识别方法。它涉及到相似性搜索的三个主要的主成分:结构表示、加权方案和相似系数。本文在加权欧氏距离的基础上引入加权谷本系数,研究权函数对相似性搜索结果的影响。谷本系数是一种常用的相似性系数,用于衡量分子对之间的相似性。大多数研究领域发现相似性搜索是基于二进制或指纹数据的。同时,我们使用非二进制数据,并设置安非他明结构作为参考或目标结构和数据集的其余部分成为一个数据库结构。在整个研究中,它表明,肯定有一个不同的结果之间的相似性搜索和没有重量。
英文摘要:
Similarity searching of molecular structure has been an important application in the Chemoinformatics, especially in drug discovery. Similarity searching is a common method used for identification of molecular structure. It involve three main principal component of similarity searching: structure representation; weighting scheme; and similarity coefficient. In this paper, we introduces Weighted Tanimoto Coefficient based on weighted Euclidean distance in order to investigate the effect of weight function on the result for similarity searching. The Tanimoto coefficient is one of the popular similarity coefficients used to measure the similarity between pairs of the molecule. The most of research area found that the similarity searching is based on binary or fingerprint data. Meanwhile, we used non-binary data and was set amphetamine structure as a reference or targeted structure and the rest of the dataset becomes a database structure. Throughout this study, it showed that there is definitely gives a different result between a similarity searching with and without weight.
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。