Amphetamine-type stimulants (ATS) drug classification using shallow one-dimensional convolutional neural network,Molecular Diversity

当前位置： X-MOL 学术 › Mol. Divers. › 论文详情

Our official English website, www.x-mol.net, welcomes your feedback! (Note: you will need to create a separate account there.)

Amphetamine-type stimulants (ATS) drug classification using shallow one-dimensional convolutional neural network
Molecular Diversity ( IF 3.9 ) Pub Date : 2021-08-02 , DOI: 10.1007/s11030-021-10289-1
Norfadzlia Mohd Yusof ₁ , Azah Kamilah Muda ₂ , Satrya Fajri Pratama ₂ , Ramon Carbo-Dorca ₃

Affiliation

Abstract

Amphetamine-type stimulants (ATS) drug analysis and identification are challenging and critical nowadays with the emergence production of new synthetic ATS drugs with sophisticated design compounds. In the present study, we proposed a one-dimensional convolutional neural network (1DCNN) model to perform ATS drug classification as an alternative method. We investigate as well as explore the classification behavior of 1DCNN with the utilization of the existing novel 3D molecular descriptors as ATS drugs representation to become the model input. The proposed 1DCNN model is composed of one convolutional layer to reduce the model complexity. Besides, pooling operation that is a standard part of traditional CNN is not applied in this architecture to have more features in the classification phase. The dropout regularization technique is employed to improve model generalization. Experiments were conducted to find the optimal values for three dominant hyper-parameters of the 1DCNN model which are the filter size, transfer function, and batch size. Our findings found that kernel size 11, exponential linear unit (ELU) transfer function and batch size 32 are optimal for the 1DCNN model. A comparison with several machine learning classifiers has shown that our proposed 1DCNN has achieved comparable performance with the Random Forest classifier and competitive performance with the others.

Graphic abstract

中文翻译：

使用浅层一维卷积神经网络的苯丙胺类兴奋剂 (ATS) 药物分类

摘要

如今，随着具有复杂设计化合物的新型合成 ATS 药物的出现，苯丙胺类兴奋剂 (ATS) 药物分析和鉴定具有挑战性和关键性。在本研究中，我们提出了一种一维卷积神经网络 (1DCNN) 模型来执行 ATS 药物分类作为替代方法。我们利用现有的新型 3D 分子描述符作为 ATS 药物表示作为模型输入来研究和探索 1DCNN 的分类行为。所提出的 1DCNN 模型由一个卷积层组成，以降低模型复杂度。此外，作为传统 CNN 标准部分的池化操作在该架构中未应用，以便在分类阶段具有更多特征。采用 dropout 正则化技术来提高模型泛化能力。进行了实验以找到 1DCNN 模型的三个主要超参数的最佳值，即滤波器大小、传递函数和批量大小。我们的研究结果发现，内核大小 11、指数线性单元 (ELU) 传递函数和批量大小 32 对于 1DCNN 模型是最佳的。与几个机器学习分类器的比较表明，我们提出的 1DCNN 已经实现了与随机森林分类器相当的性能和与其他分类器的竞争性能。指数线性单元 (ELU) 传递函数和批量大小 32 是 1DCNN 模型的最佳选择。与几个机器学习分类器的比较表明，我们提出的 1DCNN 已经实现了与随机森林分类器相当的性能和与其他分类器的竞争性能。指数线性单元 (ELU) 传递函数和批量大小 32 是 1DCNN 模型的最佳选择。与几个机器学习分类器的比较表明，我们提出的 1DCNN 已经实现了与随机森林分类器相当的性能和与其他分类器的竞争性能。

图形摘要

更新日期：2021-08-02

点击分享查看原文

点击收藏

阅读更多本刊新发论文本刊介绍/投稿指南