arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1701.06649physics.chem-phstat.ML
收藏

用于机器学习的恒定大小分子描述符

Constant Size Molecular Descriptors For Use With Machine Learning

Christopher R. Collins, Geoffrey J. Gordon, O. Anatole von Lilienfeld, David J. Yaron

摘要:

一组分子描述符的长度是独立的分子大小的机器学习模型,目标分子的热力学和电子特性的开发。这些功能进行了评估,通过监测性能的内核岭回归模型的研究数据集的有机小分子。这些特征包括连接性计数,它只需要分子的键合模式,和编码距离,它总结了键合和非键合原子之间的距离,因此需要完整的分子几何结构。除了具有恒定的大小之外,这些特征还总结了关于原子和键的局部环境的信息,使得模型可以利用由于分子之间存在相似的化学片段而产生的相似性。结合这两种类型的功能,导致模型的性能是可比的,或优于目前的最先进的。这里介绍的功能具有的优势,导致模型,可以在较小的分子上训练,然后成功地用于较大的分子。

英文摘要:

A set of molecular descriptors whose length is independent of molecular size is developed for machine learning models that target thermodynamic and electronic properties of molecules. These features are evaluated by monitoring performance of kernel ridge regression models on well-studied data sets of small organic molecules. The features include connectivity counts, which require only the bonding pattern of the molecule, and encoded distances, which summarize distances between both bonded and non-bonded atoms and so require the full molecular geometry. In addition to having constant size, these features summarize information regarding the local environment of atoms and bonds, such that models can take advantage of similarities resulting from the presence of similar chemical fragments across molecules. Combining these two types of features leads to models whose performance is comparable to or better than the current state of the art. The features introduced here have the advantage of leading to models that may be trained on smaller molecules and then used successfully on larger molecules.

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。

↑