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 1907.08333cs.LGphysics.chem-phstat.ML
收藏

通过多模态深度学习进行毒性预测

Toxicity Prediction by Multimodal Deep Learning

Griffith University(格里菲斯大学);Indian Institute of Technology(印度理工学院);Morgan State University(摩根州立大学)

Abdul Karim, Jaspreet Singh, Avinash Mishra, Abdollah Dehzangi, M. A. Hakim Newton, Abdul Sattar

摘要:

化合物毒性水平的预测是定量构效关系(QSAR)建模中的一个重要问题。虽然毒性预测在最近通过深度学习取得了重大进展,但即使是最近的方法获得的预测准确度水平也不是很高。我们提出了一种使用多个异构神经网络类型和数据表示的多模态深度学习方法。我们通过字符串、图像和数字特征来表示化合物。我们训练全连接、卷积和递归神经网络及其集成。每种数据表示或神经网络类型都有其自身的优点和缺点。我们的动机是获得一个集体的性能,可以超越每个数据表示或每个神经网络类型的个人性能。在一个标准的毒性基准,我们提出的方法获得了显着更好的准确性水平比国家的最先进的毒性预测方法。

英文摘要:

Prediction of toxicity levels of chemical compounds is an important issue in Quantitative Structure-Activity Relationship (QSAR) modeling. Although toxicity prediction has achieved significant progress in recent times through deep learning, prediction accuracy levels obtained by even very recent methods are not yet very high. We propose a multimodal deep learning method using multiple heterogeneous neural network types and data representations. We represent chemical compounds by strings, images, and numerical features. We train fully connected, convolutional, and recurrent neural networks and their ensembles. Each data representation or neural network type has its own strengths and weaknesses. Our motivation is to obtain a collective performance that could go beyond individual performance of each data representation or each neural network type. On a standard toxicity benchmark, our proposed method obtains significantly better accuracy levels than that by the state-of-the-art toxicity prediction methods.

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。

↑