arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2009.04522cs.LGphysics.chem-ph
收藏

基于图嵌入局部注意编码器的标量耦合常数预测

Scalar Coupling Constant Prediction Using Graph Embedding Local Attention Encoder

College of Computer Science and Technology, Guizhou University(贵州大学计算机科学与技术学院)

Caiqing Jian, Xinyu Cheng, Jian Zhang, Lihui Wang

摘要:

标量耦合常数(SCC)在分析有机物三维结构中起着关键作用,然而传统的用量子力学计算预测SCC非常耗时。为了高效、准确地计算SCC,提出了一种图嵌入局部自注意编码器(GELAE)模型。该模型首先提出了一种新的以键长、键角和二面角为变量的耦合系统不变结构表示,然后设计了一个嵌入图的邻接矩阵的局部自注意模块,以有效地提取耦合系统的特征,最后,采用改进的分类损失函数对SCC进行预测。为了验证所提出的方法的优越性,我们进行了一系列的比较实验,使用不同的结构表示,不同的注意力模块,和不同的损失。实验结果表明,与传统的化学键结构表示方法相比,本文提出的旋转和平移不变结构表示方法可以提高SCC预测的准确性,在图中嵌入局部自注意的情况下,预测模型在验证集上的平均绝对误差(MAE)从0.1603 Hz降低到0.1067 Hz;采用基于分类的损失函数代替定标回归损失,预测SCC的MAE可以降低到0.0963 HZ,接近CHAMPS数据集上的量子化学标准。

英文摘要:

Scalar coupling constant (SCC) plays a key role in the analysis of three-dimensional structure of organic matter, however, the traditional SCC prediction using quantum mechanical calculations is very time-consuming. To calculate SCC efficiently and accurately, we proposed a graph embedding local self-attention encoder (GELAE) model, in which, a novel invariant structure representation of the coupling system in terms of bond length, bond angle and dihedral angle was presented firstly, and then a local self-attention module embedded with the adjacent matrix of a graph was designed to extract effectively the features of coupling systems, finally, with a modified classification loss function, the SCC was predicted. To validate the superiority of the proposed method, we conducted a series of comparison experiments using different structure representations, different attention modules, and different losses. The experimental results demonstrate that, compared to the traditional chemical bond structure representations, the rotation and translation invariant structure representations proposed in this work can improve the SCC prediction accuracy; with the graph embedded local self-attention, the mean absolute error (MAE) of the prediction model in the validation set decreases from 0.1603 Hz to 0.1067 Hz; using the classification based loss function instead of the scaled regression loss, the MAE of the predicted SCC can be decreased to 0.0963 HZ, which is close to the quantum chemistry standard on CHAMPS dataset.

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。

↑