Department of Computer Science and Information Engineering, National Taiwan University, Taipei, Taiwan.
J Comput Aided Mol Des. 2012 Jan;26(1):39-43. doi: 10.1007/s10822-011-9511-4. Epub 2011 Dec 27.
The usefulness and utility of QSAR modeling depends heavily on the ability to estimate the values of molecular descriptors relevant to the endpoints of interest followed by an optimized selection of descriptors to form the best QSAR models from a representative set of the endpoints of interest. The performance of a QSAR model is directly related to its molecular descriptors. QSAR modeling, specifically model construction and optimization, has benefited from its ability to borrow from other unrelated fields, yet the molecular descriptors that form QSAR models have remained basically unchanged in both form and preferred usage. There are many types of endpoints that require multiple classes of descriptors (descriptors that encode 1D through multi-dimensional, 4D and above, content) needed to most fully capture the molecular features and interactions that contribute to the endpoint. The advantages of QSAR models constructed from multiple, and different, descriptor classes have been demonstrated in the exploration of markedly different, and principally biological systems and endpoints. Multiple examples of such QSAR applications using different descriptor sets are described and that examined. The take-home-message is that a major part of the future of QSAR analysis, and its application to modeling biological potency, ADME-Tox properties, general use in virtual screening applications, as well as its expanding use into new fields for building QSPR models, lies in developing strategies that combine and use 1D through nD molecular descriptors.
QSAR 建模的有用性和实用性在很大程度上取决于估计与感兴趣终点相关的分子描述符值的能力，然后通过优化选择描述符来从一组有代表性的感兴趣终点中形成最佳的 QSAR 模型。QSAR 模型的性能与其分子描述符直接相关。QSAR 建模，特别是模型构建和优化，得益于它从其他不相关领域借鉴的能力，但构成 QSAR 模型的分子描述符在形式和首选用途上基本保持不变。有许多类型的终点需要多种类别的描述符（编码 1D 到多维、4D 及以上内容的描述符）来最全面地捕捉对终点有贡献的分子特征和相互作用。从多个不同描述符类别的构建 QSAR 模型的优势已经在探索明显不同的、主要是生物学系统和终点中得到了证明。本文描述并研究了使用不同描述符集的此类 QSAR 应用的多个示例。结论是，QSAR 分析及其在建模生物效力、ADME-Tox 性质、虚拟筛选应用中的一般用途以及将其扩展到构建 QSPR 模型的新领域的未来的一个重要部分在于开发结合和使用 1D 到 nD 分子描述符的策略。
