基于藥物互作網(wǎng)絡(luò)的協(xié)同與拮抗預(yù)測研究

劉文斌; 陳杰; 方剛; 石曉龍; 許鵬

doi:10.11999/JEIT190867

基于藥物互作網(wǎng)絡(luò)的協(xié)同與拮抗預(yù)測研究

doi: 10.11999/JEIT190867 cstr: 32379.14.JEIT190867

劉文斌^{1, 2, ,},
陳杰¹,
方剛²,
石曉龍²,
許鵬^{2, 3}

1.
溫州大學(xué)計(jì)算機(jī)與人工智能學(xué)院溫州 325035
2.
廣州大學(xué)計(jì)算科技研究院廣州 510006
3.
黔南民族師范學(xué)院計(jì)算機(jī)與信息學(xué)院都勻 558000

基金項(xiàng)目: 國家重點(diǎn)研發(fā)計(jì)劃(2019YFA0706402)，國家自然科學(xué)基金(61572367, 61573017, 61972107, 61972109)

詳細(xì)信息

作者簡介:
劉文斌：男，1969年生，教授，研究方向?yàn)樯镄畔W(xué)

陳杰：男，1994年生，碩士生，研究方向?yàn)樯镄畔W(xué)

方剛：男，1969年生，教授，研究方向?yàn)樯镄畔W(xué)

石曉龍：男，1975年生，教授，研究方向?yàn)樯镄畔W(xué)

許鵬：男，1986年生，博士后，研究方向?yàn)樯镄畔W(xué)

通訊作者:
劉文斌　wbliu6910@126.com

中圖分類號: TP301
計(jì)量
- 文章訪問數(shù): 2726
- HTML全文瀏覽量: 1603
- PDF下載量: 110
- 被引次數(shù): 0
出版歷程
- 收稿日期: 2019-11-01
- 修回日期: 2020-01-15
- 網(wǎng)絡(luò)出版日期: 2020-02-18
- 刊出日期: 2020-06-22

Prediction of Drug Synergy and Antagonism Based on Drug-Drug Interaction Network

Wenbin LIU^{1, 2
, ,},
Jie CHEN¹,
Gang FANG²,
Xiaolong SHI²,
Peng XU^{2, 3}

1.
College of Computer Science and Artificial Intelligence, Wenzhou University, Wenzhou 325035, China
2.
Institute of Computing Science and Technology, Guangzhou University, Guangzhou 510006, China
3.
School of Computer Science and Information Technology, Qiannan Normal University for Nationalities, Duyun 558000, China

Funds: The National Key R&D Program of China (2019YFA0706402), The National Natural Science Foundation of China (61572367, 61573017, 61972107, 61972109)

摘要

摘要: 藥物的協(xié)同與拮抗關(guān)系預(yù)測，有助于藥物的使用安全及組合用藥的發(fā)展。該文從藥物互作網(wǎng)絡(luò)(DDINet)出發(fā)，基于網(wǎng)絡(luò)拓?fù)浣Y(jié)構(gòu)構(gòu)造分類特征，提出一種預(yù)測藥物協(xié)同和拮抗關(guān)系的方法。從特征選擇結(jié)果可知，根據(jù)藥物與其公共鄰居節(jié)點(diǎn)關(guān)系構(gòu)造的特征表現(xiàn)出了明顯的正負(fù)樣本分布差距，能有效地反映出藥物的協(xié)同或拮抗關(guān)系。在使用不同特征分類器的分類結(jié)果中，最優(yōu)AUC和分類精度值分別達(dá)到了0.9687和0.9187。而在協(xié)同與拮抗關(guān)系預(yù)測結(jié)果中，其預(yù)測精度值達(dá)到了0.45和0.75以上。這說明基于網(wǎng)絡(luò)拓?fù)浣Y(jié)構(gòu)的方法能有效對藥物協(xié)同和拮抗關(guān)系進(jìn)行分類和預(yù)測。與傳統(tǒng)基于藥物功能、結(jié)構(gòu)、靶基因等相似性特征的方法相比，該方法計(jì)算簡單高效，將會有效促進(jìn)組合用藥的發(fā)展。
- 藥物相互作用預(yù)測 /
- 網(wǎng)絡(luò)拓?fù)浣Y(jié)構(gòu) /
- 藥物協(xié)同 /
- 藥物拮抗
Abstract: Accurately predicting the synergistic and antagonistic relationship of drugs is helpful to the safety of drug use and the development of drug combination. A method for predicting drug synergy and antagonistic is proposed, which based on the Drug-Drug Interaction Network (DDINet) and its topological structure. From the result of feature selection, it can be seen that the feature constructed based on the interaction between the drug and its common neighbor node shows an obvious difference in the distribution of positive and negative samples, which can effectively reflect the drug synergy or antagonism. In the classification results using different feature classifiers, the optimal Area Under the Curve (AUC) and classification accuracy value reache 0.9687 and 0.9187 respectively. In the prediction results of synergy and antagonism, the prediction accuracy also reache above 0.45 and 0.75. This shows that the method based on network topology can effectively classify and predict the synergistic and antagonistic effects of drugs. Compared with the traditional methods based on similarity features of drug function, structure, target gene, etc, this method is simple and efficient to calculate, and can effectively promote the development of combination drugs.
- Prediction Drug-Drug Interactions(DDIs) /
- Network topology /
- Synergy /
- Antagonism

HTML全文

圖 1 藥物D_i和D_j的1階鄰居節(jié)點(diǎn)拓?fù)潢P(guān)系示意

下載: 全尺寸圖片幻燈片

圖 2 特征x₁～x₅在正負(fù)樣本中的分布

下載: 全尺寸圖片幻燈片

圖 3 特征y₁～y₅, z₁在正負(fù)樣本中的分布

下載: 全尺寸圖片幻燈片

圖 4 特征x₃, x₄, y₂, y₃, y₄, z₁在正負(fù)樣本中的分布

下載: 全尺寸圖片幻燈片

圖 5 不同特征組合的ROC曲線

下載: 全尺寸圖片幻燈片

圖 6 不同f取值對應(yīng)的預(yù)測樣本分布情況

下載: 全尺寸圖片幻燈片

圖 7 不同f, L取值下的協(xié)同、拮抗關(guān)系預(yù)測精度

下載: 全尺寸圖片幻燈片

參考文獻(xiàn)(27)

VAN ROON E N, FLIKWEERT S, LE COMTE M, et al. Clinical relevance of drug-drug interactions[J]. Drug Safety, 2005, 28(12): 1131–1139. doi: 10.2165/00002018-200528120-00007

CHOU Tingchao. Theoretical basis, experimental design, and computerized simulation of synergism and antagonism in drug combination studies[J]. Pharmacological Reviews, 2006, 58(3): 621–681. doi: 10.1124/pr.58.3.10

LEHáR J, KRUEGER A S, AVERY W, et al. Synergistic drug combinations tend to improve therapeutically relevant selectivity[J]. Nature Biotechnology, 2009, 27(7): 659–666. doi: 10.1038/nbt.1549

CHAIT R, CRANEY A, and KISHONY R. Antibiotic interactions that select against resistance[J]. Nature, 2007, 446(7136): 668–671. doi: 10.1038/nature05685

VENKATAKRISHNAN K, VON MOLTKE L L, OBACH R S, et al. Drug metabolism and drug interactions: Application and clinical value of in vitro models[J]. Current Drug Metabolism, 2003, 4(5): 423–459. doi: 10.2174/1389200033489361

PIRMOHAMED M and ORME M L. Drug Interactions of Clinical Importance[M]. DAVIES D M, FERNER R E, and DE GLANVILLE H. Davies's Textbook of Adverse Drug Reactions. 5th ed. London: Chapman & Hall, 1998: 888–912.

TAKEDA T, HAO Ming, CHENG Tiejun, et al. Predicting drug-drug interactions through drug structural similarities and interaction networks incorporating pharmacokinetics and pharmacodynamics knowledge[J]. Journal of Cheminformatics, 2017, 9: 16. doi: 10.1186/s13321-017-0200-8

FOKOUE A, SADOGHI M, HASSANZADEH O, et al. Predicting drug-drug interactions through large-scale similarity-based link prediction[C]. The 13th International Conference European Semantic Web Conference, Heraklion, Greece, 2016: 774–789. doi: 10.1007/978-3-319-34129-3_47.

VILAR S, HARPAZ R, URIARTE E, et al. Drug—drug interaction through molecular structure similarity analysis[J]. Journal of the American Medical Informatics Association, 2012, 19(6): 1066–1074. doi: 10.1136/amiajnl-2012-000935

VILAR S, URIARTE E, SANTANA L, et al. Detection of drug-drug interactions by modeling interaction profile fingerprints[J]. PLoS One, 2013, 8(3): e58321. doi: 10.1371/journal.pone.0058321

KASTRIN A, FERK P, and LESKO?EK B. Predicting potential drug-drug interactions on topological and semantic similarity features using statistical learning[J]. PLoS One, 2018, 13(5): e0196865. doi: 10.1371/journal.pone.0196865

CHENG Feixiong and ZHAO Zhongming. Machine learning-based prediction of drug-drug interactions by integrating drug phenotypic, therapeutic, chemical, and genomic properties[J]. Journal of the American Medical Informatics Association, 2014, 21(e2): e278–e286. doi: 10.1136/amiajnl-2013-002512

RYU J Y, KIM H U, and LEE S Y. Deep learning improves prediction of drug-drug and drug-food interactions[J]. Proceedings of the National Academy of Sciences of the United States of America, 2018, 115(18): E4304–E4311. doi: 10.1073/pnas.1803294115

LUO Heng, ZHANG Ping, HUANG Hui, et al. DDI-CPI, a server that predicts drug-drug interactions through implementing the chemical-protein interactome[J]. Nucleic Acids Research, 2014, 42(W1): W46–W52. doi: 10.1093/nar/gku433

ZHANG Ping, WANG Fei, HU Jianying, et al. Label propagation prediction of drug-drug interactions based on clinical side effects[J]. Scientific Reports, 2015, 5: 12339. doi: 10.1038/srep12339

LIU Lili, CHEN Lei, ZHANG Yuhang, et al. Analysis and prediction of drug-drug interaction by minimum redundancy maximum relevance and incremental feature selection[J]. Journal of Biomolecular Structure and Dynamics, 2017, 35(2): 312–329. doi: 10.1080/07391102.2016.1138142

TAKARABE M, SHIGEMIZU D, KOTERA M, et al. Network-based analysis and characterization of adverse drug-drug interactions[J]. Journal of Chemical Information and Modeling, 2011, 51(11): 2977–2985. doi: 10.1021/ci200367w

GOTTLIEB A, STEIN G Y, ORON Y, et al. INDI: A computational framework for inferring drug interactions and their associated recommendations[J]. Molecular Systems Biology, 2012, 8: 592. doi: 10.1038/msb.2012.26

WISHART D S, FEUNANG Y D, GUO A C, et al. DrugBank 5.0: A major update to the DrugBank database for 2018[J]. Nucleic Acids Research, 2017, 46(D1): D1074–D1082. doi: 10.1093/nar/gkx1037

CORTES C and VAPNIK V. Support-vector networks[J]. Machine Learning, 1995, 20(3): 273–297. doi: 10.1007/bf00994018

陳素根, 吳小俊. 基于特征值分解的中心支持向量機(jī)算法[J]. 電子與信息學(xué)報(bào), 2016, 38(3): 557–564. doi: 10.11999/JEIT150693

CHEN Sugen and WU Xiaojun. Eigenvalue proximal support vector machine algorithm based on eigenvalue decoposition[J]. Journal of Electronics &Information Technology, 2016, 38(3): 557–564. doi: 10.11999/JEIT150693

汪廷華, 田盛豐, 黃厚寬. 特征加權(quán)支持向量機(jī)[J]. 電子與信息學(xué)報(bào), 2009, 31(3): 514–518. doi: 10.3724/SP.J.1146.2007.01711

WANG Tinghua, TIAN Shengfeng, and HUANG Houkuan. Feature weighted support vector machine[J]. Journal of Electronics &Information Technology, 2009, 31(3): 514–518. doi: 10.3724/SP.J.1146.2007.01711

WU Shaomin and FLACH P. A scored AUC metric for classifier evaluation and selection[C]. ICML 2005 Workshop on ROC Analysis in Machine Learning, Bonn, Germany, 2005.

HOSSIN M and SULAIMAN M N. A review on evaluation metrics for data classification evaluations[J]. International Journal of Data Mining & Knowledge Management Process, 2015, 5(2): 1–11. doi: 10.5121/ijdkp.2015.5201

ARLOT S and CELISSE A. A survey of cross-validation procedures for model selection[J]. Statistics Surveys, 2010, 4: 40–79. doi: 10.1214/09-SS054

LIU Weiping and Lü Linyuan. Link prediction based on local random walk[J]. EPL (Europhysics Letters) , 2010, 89(5): 58007. doi: 10.1209/0295-5075/89/58007

TANG Jiliang, ALELYANI S, and LIU Huan. Feature Selection for Classification: A Review[M]. AGGARWAL C C. Data Classification: Algorithms and Applications. New York: CRC Press, 2014: 37.

相關(guān)文章

施引文獻(xiàn)

資源附件(0)

訪問統(tǒng)計(jì)