文献类型：期刊文献

英文题名：Insight mixed deep neural network architectures for molecular representation

作者：Zhao, Tianze[1]; Yin, Zhenyu[2]; Lu, Yong[1]; Cheng, Shaocong[3]; Li, Chunyan[4]

第一作者：Zhao, Tianze

机构：[1] School of Information Engineering, Minzu University of China, Beijing, 100081, China; [2] School of Economics and Management, Beijing Jiaotong University, Beijing, 100044, China; [3] College of Robotics, Beijing Union University, Beijing, 100101, China; [4] School of Informatics, Yunnan Normal University, Kunming, 650500, China

第一机构：School of Information Engineering, Minzu University of China, Beijing, 100081, China

通讯机构：[1]School of Information Engineering, Minzu University of China, Beijing, 100081, China

年份：2024

卷号：109

起止页码：299-306

外文期刊名：Alexandria Engineering Journal

收录：EI(收录号：20243717023280)

语种：英文

外文关键词：Neural network models - Prediction models

摘要：Learning molecular representation is a crucial task in the field of drug discovery, particularly for various specific applications such as predicting molecular properties. Current methods are mainly based on deep neural network models, such as convolutional neural networks (CNN), recurrent neural networks (RNN), graph neural networks (GNN) and their mixed models. However, these neural network models mentioned above do not provide detailed explanations for the ability to learn molecular representations and why such experimental results occurred. In this paper, we aim to compare the performance of these models in predicting molecular properties based on molecular representation, and give more insight into deep neural network architectures for specific molecular tasks. Our experimental results demonstrate that the graph neural network can obtain superior performance on the regression tasks, while the mixed deep neural network models show better performance on the classification tasks. Ablation study also gives more explanation and analysis to the experimental results. ? 2024