计算机科学 ›› 2016, Vol. 43 ›› Issue (4): 260-263.doi: 10.11896/j.issn.1002-137X.2016.04.053

所属专题: 生物信息学

• 人工智能 • 上一篇    下一篇

基于深度学习的口服生物利用度分类研究

史新宇,禹龙,田生伟,叶飞跃,钱进,高双印   

  1. 新疆大学软件学院 乌鲁木齐830008,新疆大学网络中心 乌鲁木齐830046;江苏理工学院计算机工程学院 常州213000;江苏理工学院云计算与智能信息处理重点实验室 常州213000,新疆大学软件学院 乌鲁木齐830008;江苏理工学院计算机工程学院 常州213000;江苏理工学院云计算与智能信息处理重点实验室 常州213000,江苏理工学院计算机工程学院 常州213000;江苏理工学院云计算与智能信息处理重点实验室 常州213000,新疆大学软件学院 乌鲁木齐830008;江苏理工学院云计算与智能信息处理重点实验室 常州213000,新疆大学软件学院 乌鲁木齐830008
  • 出版日期:2018-12-01 发布日期:2018-12-01
  • 基金资助:
    本文受国家自然科学基金(31160341),自治区研究生科研创新项目(XJGRI2015034)资助

Research on Classification of Oral Bioavailability Based on Deep Learning

SHI Xin-yu, YU Long, TIAN Sheng-wei, YE Fei-yue, QIAN Jin and GAO Shuang-yin   

  • Online:2018-12-01 Published:2018-12-01

摘要: 针对采用传统方法测量口服生物利用度(OB)代价昂贵、花费周期长,而现有的一些机器学习方法对其预测精度较低的问题,提出了一种基于栈式自编码(SAE)神经网络的口服生物利用度分类方法,利用经筛选过的分子特征结合栈式自编码模型对生物利用度进行分类。实验表明,与浅层机器学习模型支持向量机(SVM)以及人工神经网络(ANN)相比,深度网络对化合物分子的特征有更本质的学习,采用经筛选过的2D和3D分子特征组合对人体口服生物利用度的分类效果较好,其平均预测精度为83%,灵敏度(SE)为94%,特异性(SP)为49%。

关键词: 口服生物利用度,深度学习,分子描述符,栈式自编码,softmax回归

Abstract: It is expensive and time-consuming to measure oral bioavailability using traditional methods,and existing machine learning methods show lower accuracy.To solve the problems,a classification method of human oral bioavailability based on stacked autoencoder(SAE) was presented.Filtered features of molecular are combined with the model of SAE to classify human oral bioavailability.Experimental results show that the deep network can study more essential features of molecules comparing with other shallow learning models like support vector machine and artificial neural network,and the combination of screened 2D and 3D molecular features achieves better classification effect of oral bioavailability,with a average accuracy value of 83%,a sensitivity(SE) value of 94% and a specificity(SP) value of 49%.

Key words: Oral bioavailability,Deep learning,Molecular descriptors,Stacked autoencoder,softmax regression

[1] Tian Sheng,Li You-yong,Wang Jun-mei,et al.ADME Evaluation in Drug Discovery.9.Prediction of Oral Bioavailability in Humans Based on Molecular Properties and Structural Fingerprints[J].Molecular Pharmaceutics,2011,8(3):841-851
[2] Hou Ting-jun,Wang Jun-mei,Zhang Wei,et al.ADME Evaluation in Drug Discovery.6.Can Oral Bioavailability in Humans Be Effectively Predicted by Simple Molecular Property-Based Rules?[J].Journal of Chemical Information and Modeling,2007,47(2):460-463
[3] Lai Jun,Liao Zheng-gen,Yang Ming-fu,et al.Research andprogress of bioavailability[J].Chinese Journal of Experimental Traditional Medical Formulae,2010,18:226-229(in Chinese) 赖珺,廖正根,杨明福,等.生物利用度研究进展[J].中国实验方剂学杂志,2010,18:226-229
[4] Wang Jun-mei,Hou Ting-jun.Advances in computationally mode-ling human oral bioavailability[J].Advanced Drug Delivery Reviews,2015,86(6):11-16
[5] Ma Chang-ying,Yang Sheng-yong, Zhang Hui,et al.Prediction models of human plasma protein binding rate and oral bioavai-lability derived using GA-CG-SVM method[J].Journal of Pharmaceutical and Biomedical Analysis,2008,47:677-682
[6] Tian Sheng.Theoretical studies on the prediction of drug-likeness and oral bioavailability[D].Suzhou:Soochow University,2011(in Chinese) 田盛.类药性和生物利用度的理论预测研究[D].苏州:苏州大学,2011
[7] Ahmed S S S J,Ramakrishnan V.Systems Biological Approach of Molecular Descriptors Connectivity:Optimal Descriptors for Oral Bioavailability Prediction[J].Plos One,2012,7(7):e40654
[8] Zhang Hui,Chen Qing-yi,Xiang Ming-li,et al.In silico prediction of mitochondrial toxicity by using GA-CG-SVM approach[J].Toxicology in Vitro,2009,3(1):134-140
[9] Liu Jian-wei,Liu Yuan,Luo Xiong-lin.Research and develop-ment on deep learning[J].Application Research of Computers,2014,31(7):128-134(in Chinese) 刘建伟,刘媛,罗雄麟.深度学习研究进展[J].计算机应用研究,2014,31(7):128-134
[10] Wang Yong,Zhao Jian-hui,Zhang Deng-yi,et al.Forest fire ima-ge classification based on deep neural network of sparse autoencoder[J].Computer Engineering and Applications,2014,50(24):173-177(in Chinese) 王勇,赵俭辉,章登义,等.基于稀疏自编码深度神经网络的林火图像分类[J].计算机工程与应用,2014,50(24):173-177
[11] Kim M T,Sedykhy A,Suman K,et al.Critical Evaluation of Human Oral Bioavailability for Pharmaceutical Drugs by Using Various Cheminformatics Approaches[J].Pharm Res,2014,31:1002-1014

No related articles found!
Viewed
Full text


Abstract

Cited

  Shared   
  Discussed   
No Suggested Reading articles found!