arXiv 1704.047182017-04stat.MLcs.LGq-bio.QM

基于深度学习的回归和多类模型用于急性口服毒性预测和自动化学特征提取

Deep Learning Based Regression and Multi-class Models for Acute Oral Toxicity Prediction with Automatic Chemical Feature Extraction

Center for Quantitative Biology, Academy for Advanced Interdisciplinary Studies, Peking University（北京大学前沿交叉学科研究院定量生物学中心）；Beijing National Laboratory for Molecular Sciences, State Key Laboratory for Structural Chemistry of Unstable and Stable Species, College of Chemistry and Molecular Engineering, Peking University（北京分子科学国家实验室，不稳定与稳定物种结构化学国家重点实验室，北京大学化学与分子工程学院）；Peking-Tsinghua Center for Life Sciences, Peking University（北京大学-清华大学生命科学联合中心）

Youjun Xu, Jianfeng Pei, Luhua Lai

备注：: 36 pages, 4 figures

阅读 PDF

arXiv 页面 ↗HTML 原文 ↗

摘要：

在化学信息学的定量结构-性质关系（QSPR）研究中，获得化学性质与化学特征之间可解释的关系是非常重要的。然而，QSPR模型的预测能力和可解释性通常是两个难以同时实现的不同目标。使用分子图编码卷积神经网络（MGE-CNN）的深度学习架构提供了一种构建具有高预测能力的可解释QSPR模型的通用策略。代替使用特定于应用的预设分子描述符或指纹，可以使用原始和相关特征来解析模型，而无需手动干预或选择。在这项研究中，我们使用MGE-CNN架构作为案例研究开发了化合物的急性口服毒性（AOT）模型。构建了三种高级预测模型：回归模型（deepAOT-R）、多分类模型（deepAOT-C）和多任务模型（deepAOT-CR）。这些模型大大优于以前报道的模型。对于包含1673种（测试集I）和375种（测试集II）化合物的两个外部数据集，deepAOT-R在测试集I上的R2和平均绝对误差（MAE）分别为0.864和0.195，deepAOT-C在测试集I和II上的预测准确率分别为95.5%和96.3%。对于测试集I，deepAOT-CR的两个外部预测准确度分别为95.0%和94.1%，而R2和MAE分别为0.861和0.204。

英文摘要：

For quantitative structure-property relationship (QSPR) studies in chemoinformatics, it is important to get interpretable relationship between chemical properties and chemical features. However, the predictive power and interpretability of QSPR models are usually two different objectives that are difficult to achieve simultaneously. A deep learning architecture using molecular graph encoding convolutional neural networks (MGE-CNN) provided a universal strategy to construct interpretable QSPR models with high predictive power. Instead of using application-specific preset molecular descriptors or fingerprints, the models can be resolved using raw and pertinent features without manual intervention or selection. In this study, we developed acute oral toxicity (AOT) models of compounds using the MGE-CNN architecture as a case study. Three types of high-level predictive models: regression model (deepAOT-R), multi-classification model (deepAOT-C) and multi-task model (deepAOT-CR) for AOT evaluation were constructed. These models highly outperformed previously reported models. For the two external datasets containing 1673 (test set I) and 375 (test set II) compounds, the R2 and mean absolute error (MAE) of deepAOT-R on the test set I were 0.864 and 0.195, and the prediction accuracy of deepAOT-C was 95.5% and 96.3% on the test set I and II, respectively. The two external prediction accuracy of deepAOT-CR is 95.0% and 94.1%, while the R2 and MAE are 0.861 and 0.204 for test set I, respectively.

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。