基于数据预处理深度置信网络的药物与非药物分类（英文）

禹龙; 牛苗; 田生伟; 孙霞; 李莉; 王梅; 孔军

doi:10.13568/j.cnki.651094.2018.01.002

您当前的位置：

首页 >

文章列表页 >

基于数据预处理深度置信网络的药物与非药物分类（英文）

研究精粹 | 更新时间：2026-01-21

- 基于数据预处理深度置信网络的药物与非药物分类（英文）
- 基于数据预处理深度置信网络的药物与非药物分类（英文）
- 新疆大学学报（自然科学版中英文） 2018年35卷第1期页码：4-12
- 作者机构：
  
  1. 新疆大学网路中心
  2. 新疆大学软件学院
  3. 新疆医科大学药学院
  4. 江南大学轻工业先进控制(教育部)重点实验室
  5. 新疆大学电气工程学院
- 作者简介：
- 基金信息：
  
  National Natural Science Foundation of China(31160341);Autonomous Region Science and Technology Talents Training Project(QN2016YX0051)
- DOI：10.13568/j.cnki.651094.2018.01.002
  中图分类号： TP18;TQ460
- 纸质出版：2018
- 稿件说明：
移动端阅览
[1]禹龙,牛苗,田生伟,等.基于数据预处理深度置信网络的药物与非药物分类（英文）[J],2018,35(01):4-12.
[1]禹龙,牛苗,田生伟,等.基于数据预处理深度置信网络的药物与非药物分类（英文）[J],2018,35(01):4-12. DOI： 10.13568/j.cnki.651094.2018.01.002.

DOI：10.13568/j.cnki.651094.2018.01.002.

摘要

制药工业的一个主要趋势是整合传统意义上被认为早期阶段药物发现的分子描述.为了更好的将药物和非药物分类

本文提出了基于深度信念网络(DBN)的分类模型.首先

对分子特征进行预处理以保证有价值的信息得到保留

其次

该模型将DBN和反向传播(BP)分类器结合去对药物/非药物进行检测和分类.DBN由几个受限玻尔兹曼机(RBM)层组成

当特征向量转移到下一层时这些RBM层尽可能多的保留具有重要的影响的信息.BP层训练的最后一个RBM层生成特征分类.结果表明

该方法是提取高层次特征的药物和非药物分类任务中一种成功的方法

分类精度高达85.3%

高于传统的支持向量机和神经网络方法.同时

预处理对分子特征的提取更为有效

从而在一定程度上提高了分类的准确性.

Abstract

One of the key trends in the pharmaceutical industry has been the integration of what have traditionally been considered as molecular descriptions of the early phases of drug discovery. In order to better classify drug and non-drug

a classified model based on deep belief network(DBN) is proposed in this paper. Firstly

the preprocessing of molecular features to guarantee the valuable information is retained. Secondly

the model is a hybrid of DBN and Back Propagation(BP) classifier to detect and classify drug/non-drug. The DBN builds consists of several restricted boltzmann machine(RBM) layers

which maintain as much information with important influence as possible when the feature vectors are transferred to next layer. The BP layer is trained to classify the features generated by the last RBM layer. The results showed that the method is a successful approach in the high-dimensional-feature for drug and non-drug classification task as the useful high-level features are extracted. The classified accuracy is up to 85.3% which is higher than the traditional methods such as support vector machine(SVM) and traditional neural network(NN). Meanwhile

the pre-process is more effective extract for molecular features so that the accuracy of classification has been improved to certain extent.

关键词

Keywords

references

Wei C P,Chen K A,Chen L C.Mining biomedical literature and ontologies for drug repositioning discovery[M]//Advances in Knowledge Discovery and Data Mining.Springer International Publishing,2014:373-384.

Ratti E,Trist D.Continuing evolution of the drug discovery process in the pharmaceutical industry[J].Pure and Applied Chemistry,2001,73(1):67-75.

Kola I,Landis J.Can the pharmaceutical industry reduce attrition rates[J].Nature reviews Drug discovery,2004,3(6):711-716.

Magid A G,Childers W E.Discovery of Innovative Therapeutics:Today’s Realities and Tomorrow’s Vision.2.Pharma Challenges and Their Commitment to Innovation[J].Journal of Medicinal Chemistry,2014,57(13):5525-5553.

Martin E J,Blaney J M,Siani M A,et al.Measuring diversity:experimental design of combinatorial libraries for drug discovery[J].Journal of medicinal chemistry,1995,38(7):1431-1436.

Egan W J,Merz K M,Baldwin J J.Prediction of drug absorption using multivariate statistics[J].Journal of Medicinal Chemistry,2000,43(21):3867-3877.

Brown R D,Martin Y C.The information content of 2D and 3D structural descriptors relevant to ligand-receptor binding[J].Journal of Chemical Information and Computer Sciences,1997,37(1):1-9.

Potter T,Matter H.Random or rational design?Evaluation of diverse compound subsets from chemical structure databases[J].Journal of medicinal chemistry,1998,41(2):478-488.

Lipinski C A,Lombardo F,Dominy B W,et al.Experimental and computational approaches to estimate solubility and permeability in drug discovery and development settings[J].Drug De1 Rev,1997,23:3-25.

Bemis G W,Murcko M A.The properties of known drugs.1.Molecular frameworks[J].Journal of Medicinal Chemistry,1996,39(15):2887-2893.

Bemis G W,Murcko M A.Properties of known drugs.2.Side chains[J].Journal of Medicinal Chemistry,1999,42(25):5095-5099.

Wang J,Hou T.Drug and drug candidate building block analysis[J].Journal of chemical information and modeling,2009,50(1):55-67.

Kathrin H,J u¨rgen B.Support vector machines for drug discovery[J].Expert Opinion on Drug Discovery,2013,9(1):93-104.

Todeschini R,Consonni V.Handbook of Molecular Descriptors[J].Methods and principles in Medicinal Chemistry,2000,8(4):80-100.

Li Q,Bender A,Pei J,et al.A large descriptor set and a probabilistic kernel-based classifier significantly improve druglikeness classification[J].Journal of chemical information and modeling,2007,47(3):1776-1786.

Frimurer T M,Bywater R,N?rum L,et al.Improving the odds in discriminating“drug-like”from“non drug-like”compounds[J].Journal of chemical information and computer sciences,2000,40(4):1315-1324.

Garc′?a-Sosa A T,Oja M,Hete′nyi C,et al.Drug Logit:Logistic Discrimination between Drugs and Nondrugs Including Disease-Specificity by Assigning Probabilities Based on Molecular Properties[J].Journal of Chemical Information&Modeling,2012,52(6):2165-2180.

Ajay A,Walters WP,Murcko MA.Can We Learn To Distinguish between“Drug-like”and“Nondrug-like”Molecules[J].Journal of Medicinal Chemistry,1998,41(18).

Sheng Tian.The prediction research of drug-like and bioavailability[R].Soochow University,2011.

Sadowski J,Kubinyi H.A scoring scheme for discriminating between drugs and nondrugs[J].Journal of Medicinal Chemistry,1998,41(18):3325-3329.

Sadowski J.Optimization of chemical libraries by neural networks[J].Current Opinion in Chemical Biology,2000,4(1):280-282.

Schneider G.Neural networks are useful tools for drug design[J].Neural Networks,2000,13(1):15-16(2).

Byvatov E,Fechner U,Sadowski J,et al.Comparison of support vector machine and artificial neural network systems for drug/n Nondrug classification[J].J chem inf comput sci,2003,35(4):1882-1889.

Korkmaz S,Zararsiz G,Goksuluk D.Drug/nondrug classification using support vector machines with various feature selection strategies[J].Computer methods and programs in biomedicine,2014,117(2):51-60.

Hinton G E,Salakhutdinov R R.Reducing the dimensionality of data with neural networks[J].Science,2006,313(5786):504-507.

Dahl G E,Yu D,Deng L,et al.Large vocabulary continuous speech recognition with context-dependent BN-HMMS[C].Proc of IEEE Int Conf on Acoustics,peech and Signal Processing Prague,2011:4688-4691.

Deselaers T,Hasan S,Bender O,et al.A deep learning proach to machine transliteration[C].Proc of the 4th orkshop on Statistical Machine Translation.Athens,2009:233-241.

Fasel I,Berry J.Deep belief networks for real-time xtraction of tongue contours from ultrasound durin speech[C].Proc of the 20th Int Conf on Pattern ecognition.Stroudsburg:Association for Computational,2010:1483-1486.

Deng L,Seltzer M L,Yu D,et al.Binary coding of speech spectrograms using a deep auto-encoder[C].Proc of the 11th Annual Conf on Int Speech Communication Association Makuhair,2010:1692-1695.

Chen Y,Zheng D Q,Zhao T J.Chinese relation extraction based on deep belief nets[J].J of Software,2012,23(8):2572-2585.

Bengio Y,Lecun Y.Scaling learning algorithms towards AI[M]//Proc of the Large-Scale Kernel Machines.Cambridge:MIT Press,2007:321-358.

Hinton G,Osindero S,Teh Y.A fast learning algorithm for deep belief nets[J].Neural Computation,2006,18(5):1527-1554.

Yoshua Bengio,Pascal Lamblin,Dan Popovici,et al.Greedy layer-wise training of deep networks[C].Advances n Neural Information Processing Systems 19(NIPS 2006).Vancouver,2007:153-160.

Neal R M,Edu E R T.Probabilistic Inference Using Markov Chain Monte Carlo Methods[J]//in Physics and Chemistry,Nato Science Series C:Mathematical and Physical Sciences,Vol.525,edited by M.P.Nightingale and C.J.Umrigar(Kluwer Academic,1993,92(440):497-537.

Hinton G E.Training Products of Experts by Minimizing Contrastive[J].Neural Computation,2003,14(6):1771-800.

Carreira-Perpinan M A,Hinton G E.On contrastive divergence learning[M]//Proc of the Artificial Intelligence and Statistics(AISTATS 2005).Barbados,2005:33-41.

Yu K,Jia L,Chen Y,et al.Deep Learning:Yesterday,Today,and Tomorrow[J].Journal of Computer Research&Development,2013,50(7):1799-1804.

Soon W M,Ng H T,Lim C Y.A machine learning approach to coreference resolution of noun phrases[J].Computational Linguistics,2001,27(2):521-544.

浏览量

118

下载量

CSCD

文章被引用时，请邮件提醒。

提交

工具集

关联资源

一种基于连体段的维吾尔文单词特征提取方法

基于机器视觉的番茄实时分级系统设计