More Web Proxy on the site http://driver.im/

research-article

A meta-learning framework using representation learning to predict drug-drug interaction

Authors:

T.V. GeethaAuthors Info & Claims

Volume 84, Issue C

Pages 136 - 147

https://doi.org/10.1016/j.jbi.2018.06.015

Published: 01 August 2018 Publication History

Graphical abstract

Display Omitted

Highlights

•

Predicting drug-drug interaction using a meta-learning framework.

•

Similar drugs interact with each other and the similarity calculated using network embedding algorithm.

•

Total of 15,395 new DDI predictions from 1,46,579 unique drug pairs.

•

Average prediction evidence of the meta-classifier at 57 out of 100.

Abstract

Motivation

Predicting Drug-Drug Interaction (DDI) has become a crucial step in the drug discovery and development process, owing to the rise in the number of drugs co-administered with other drugs. Consequently, the usage of computational methods for DDI prediction can greatly help in reducing the costs of in vitro experiments done during the drug development process. With lots of emergent data sources that describe the properties and relationships between drugs and drug-related entities (gene, protein, disease, and side effects), an integrated approach that uses multiple data sources would be most effective.

Method

We propose a semi-supervised learning framework which utilizes representation learning, positive-unlabeled (PU) learning and meta-learning efficiently to predict the drug interactions. Information from multiple data sources is used to create feature networks, which is used to learn the meta-knowledge about the DDIs. Given that DDIs have only positive labeled data, a PU learning-based classifier is used to generate meta-knowledge from feature networks. Finally, a meta-classifier that combines the predicted probability of interaction from the meta-knowledge learnt is designed.

Results

Node2vec, a network representation learning method and bagging SVM, a PU learning algorithm, are used in this work. Both representation learning and PU learning algorithms improve the performance of the system by 22% and 12.7% respectively. The meta-classifier performs better and predicts more reliable DDIs than the base classifiers.

References

[1]

J. Gerteis, et al., Multiple chronic conditions chartbook, Agency for Healthcare Research and Quality, Rockville, MD, 2014.

[2]

M. Kashyap, et al., Drug-drug interactions and their predictors: results from Indian elderly inpatients, Pharm. Practice 11 (4) (2013) 191.

[3]

D. Flockhart, et al., Preventable adverse drug reactions: a focus on drug interactions., Centers Educ. Res. Ther. (2009) 452.

[4]

S. Liu, et al., Drug-drug interaction extraction via convolutional neural networks, Comput. Math. Methods Med. (2016).

[5]

B. Percha, et al., Discovery and explanation of drug-drug interactions via text mining, in: Pacific Symposium on Biocomputing, NIH Public Access, 2012, p. 410.

[6]

L. Tari, et al., Discovering drug–drug interactions: a text-mining and reasoning approach based on properties of drug metabolism, Bioinformatics 26 (18) (2010) i547–i553.

[7]

J. Duke, et al., Literature based drug interaction prediction with clinical assessment using electronic medical records: novel myopathy associated drug interactions, PLoS Comput. Biol. 8 (8) (2012).

[8]

R. Kavuluru, et al., Extracting Drug-Drug Interactions with word and character-level recurrent neural networks, in: Healthcare Informatics (ICHI), 2017 IEEE International Conference on, IEEE, 2017, pp. 5–12.

[9]

S. Alaimo, et al., Drug–target interaction prediction through domain-tuned network-based inference, Bioinformatics 29 (16) (2013) 2004–2008.

[10]

H. Chen, et al., Network-based inference methods for drug repositioning, Comput. Math. Methods Med (2015).

[11]

W. Zhang, et al., Drug-target interaction prediction through label propagation with linear neighborhood information, Molecules 22 (12) (2017) 2056.

[12]

P. Zhang, et al., Label propagation prediction of drug-drug interactions based on clinical side effects, Scientific reports (2015) 5.

[13]

M. Takarabe, et al., Network-based analysis and characterization of adverse drug–drug interactions, J. Chem. Inf. Model. 51 (11) (2011) 2977–2985.

[14]

A. Cami, et al., Pharmacointeraction network models predict unknown drug-drug interactions, PloS One 8 (4) (2013).

[15]

D. Sridhar, et al., A probabilistic approach for collective similarity-based drug–drug interaction prediction, Bioinformatics 32 (20) (2016) 3175–3182.

[16]

P. Zhang, et al., Towards drug repositioning: a unified computational framework for integrating multiple aspects of drug similarity and disease similarity, in: AMIA Annual Symposium Proceedings, 2014, pp. 1258–1267.

[17]

S. Vilar, et al., Drug—drug interaction through molecular structure similarity analysis, J. Am. Med. Inf. Assoc. 19 (6) (2012) 1066–1074.

[18]

S. Vilar, et al., Similarity-based modeling in large-scale prediction of drug-drug interactions, Nat. Protocols 9 (9) (2014) 2147–2163.

[19]

H. Luo, et al., Drug repositioning based on comprehensive similarity measures and Bi-random walk algorithm, Bioinformatics 32 (17) (2016) 2664–2671.

[20]

A. Fokoue, et al., Predicting drug-drug interactions through large-scale similarity-based link prediction, Springer, Cham, 2016, pp. 774–789.

[21]

F. Cheng, Z. Zhao, Machine learning-based prediction of drug–drug interactions by integrating drug phenotypic, therapeutic, chemical, and genomic properties, J. Am. Med. Inform. Assoc. 21 (e2) (2014) e278–e286.

[22]

T. Takeda, et al., Predicting drug–drug interactions through drug structural similarities and interaction networks incorporating pharmacokinetics and pharmacodynamics knowledge, J. Cheminf. 9 (1) (2017) 16.

[23]

C. Elkan, K. Noto, Learning classifiers from only positive and unlabeled data, in: Proceedings of the 14th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, ACM, 2008, pp. 213–220.

[24]

D.S. Wishart, et al., DrugBank: a knowledgebase for drugs, drug actions and drug targets, Nucl. Acids Res. 36 (suppl_1) (2007) D901–D906.

[25]

N.P. Tatonetti, et al., Data-driven prediction of drug effects and interactions, Sci. Transl.Med. 4 (125) (2012) 125ra31-125ra31.

[26]

F. Mordelet, J.P. Vert, A bagging SVM to learn from positive and unlabeled examples, Pattern Recogn. Lett. 37 (2014) 201–209.

[27]

B. Schölkopf, et al., Estimating the support of a high-dimensional distribution, Neural Comput. 13 (7) (2001) 1443–1471.

Digital Library

[28]

B. Liu, et al., Building text classifiers using positive and unlabeled examples, in: Data Mining, 2003, ICDM 2003, Third IEEE International Conference on, 2003, pp. 179–186.

[29]

W.S. Lee, B. Liu, Learning with positive and unlabeled examples using weighted logistic regression, in: ICML, vol. 3, 2003, pp. 448–455.

[30]

Y. Liu, et al., Computational drug discovery with dyadic positive-unlabeled learning, in: Proceedings of the 2017 SIAM International Conference on Data Mining, 2017, pp. 45–53.

[31]

B. Liu, et al., Partially supervised classification of text documents, in: ICML, vol. 2, 2002, pp. 387–394.

[32]

P. Yang, et al., A review of ensemble methods in bioinformatics, Curr. Bioinf. 5 (4) (2010) 296–308.

[33]

C. Lemke, et al., Metalearning: a survey of trends and technologies, Artificial Intell. Rev. 44 (1) (2015) 117–130.

[34]

A. Abbasi, et al., Metafraud: a meta-learning framework for detecting financial fraud, Mis Quarterly 36 (4) (2012).

[35]

H. Seo, et al., A meta learning approach to grammatical error correction, in: Proceedings of the 50th Annual Meeting of the Association for Computational Linguistics: Short Papers-Volume 2, Association for Computational Linguistics, 2012, pp. 328–332.

[36]

Y.J. Hu, et al., A meta-learning approach for B-cell conformational epitope prediction, BMC Bioinf. 15 (1) (2014) 378.

[37]

Y. Kim, E. Riloff, Stacked generalization for medical concept extraction from clinical notes, Proc. BioNLP 15 (2015) 61–70.

[38]

M. Kuhn, et al., A side effect resource to capture phenotypic effects of drugs, Mol. Syst. Biol. 6 (1) (2010) 343.

[39]

J. Li, Z. Lu, A new method for computational drug repositioning using drug pairwise similarity, in: Bioinformatics and Biomedicine (BIBM), 2012 IEEE International Conference On, IEEE, 2012, pp. 1–4.

[40]

I. Segura Bedmar, et al., Semeval-2013 Task 9: Extraction of Drug-Drug Interactions from Biomedical Texts (ddiextraction 2013), Association for Computational Linguistics, 2013.

[41]

H. Kilicoglu, et al., SemMedDB: a PubMed-scale repository of biomedical semantic predications, Bioinformatics 28 (23) (2012) 3158–3160.

Digital Library

[42]

R. Guimerà, M. Sales-Pardo, A network inference method for large-scale unsupervised identification of novel drug-drug interactions, PLoS Comput. Biol. 9 (12) (2013).

[43]

L.G. Moyano, Learning network representations, Eur. Phys. J. Special Topics 226 (3) (2017) 499–518.

[44]

A. Grover, J. Leskovec, node2vec: Scalable feature learning for networks, in: Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, ACM, 2016, pp. 855–864.

[45]

Y. Bengio, et al., Representation learning: a review and new perspectives, IEEE Trans. Pattern Anal. Mach. Intell. 35 (8) (2013) 1798–1828.

Digital Library

[46]

A. Skrbo, et al., Classification of drugs using the ATC system (Anatomic, Therapeutic, Chemical Classification) and the latest changes, Medicinski arhiv 58 (1 Suppl 2) (2004) 138–141.

[47]

B. Chauvin, et al., Drug–drug interactions between HMG-CoA reductase inhibitors (statins) and antiviral protease inhibitors, Clin. Pharm. 52 (10) (2013) 815–831.

[48]

J.P. Fournier, et al., Drug interactions between antihypertensive drugs and non-steroidal anti-inflammatory agents: a descriptive study using the French Pharmacovigilance database, Fundam. Clin. Pharmacol. 28 (2) (2014) 230–235.

[49]

A.M. Baciewicz, et al., Update on rifampin, rifabutin, and rifapentine drug interactions, Curr. Med. Res. Opin. 29 (1) (2013) 1–12.

[50]

M. Kanehisa, S. Goto, KEGG: kyoto encyclopedia of genes and genomes, Nucl. Acids Res. 28 (1) (2000) 27–30.

[51]

M. Ashburner, et al., Gene Ontology: tool for the unification of biology, Nat. Genet. 25 (1) (2000) 25–29.

[52]

S. Vilar, et al., State of the art and development of a drug-drug interaction large scale predictor based on 3D pharmacophoric similarity, Curr. Drug Metab. 15 (5) (2014) 490–501.

Cited By

Iqbal AShah IInjila Assad AAhmed MShah S(2024)A review of deep learning algorithms for modeling drug interactionsMultimedia Systems10.1007/s00530-024-01325-930:3Online publication date: 14-Apr-2024
https://dl.acm.org/doi/10.1007/s00530-024-01325-9
Xi XWei JGuo YDuan W(2022)Academic collaborations: a recommender framework spanning research interests and network topologyScientometrics10.1007/s11192-022-04555-8127:11(6787-6808)Online publication date: 1-Nov-2022
https://dl.acm.org/doi/10.1007/s11192-022-04555-8

Index Terms

A meta-learning framework using representation learning to predict drug-drug interaction
1. Applied computing
  1. Life and medical sciences
2. Computing methodologies
  1. Machine learning
    1. Learning paradigms
      1. Supervised learning
    2. Machine learning approaches

Index terms have been assigned to the content through auto-classification.

Recommendations

Drug Repurposing: Targeting mTOR Inhibitors for Anticancer Activity
CSBio '17: Proceedings of the 8th International Conference on Computational Systems-Biology and Bioinformatics

In the search of safer and more effective drugs while reducing costs and increasing productivity of novel drug discovery, scientists are changing their focus to an approach known as drug repurposing. This involves finding a new therapeutic effect of an ...
Deep Learning for High-Order Drug-Drug Interaction Prediction
BCB '19: Proceedings of the 10th ACM International Conference on Bioinformatics, Computational Biology and Health Informatics

Drug-drug interactions (DDIs) and their associated adverse drug reactions (ADRs) represent a significant detriment to the public health. Existing research on DDIs is primarily focused on pairwise DDI detection and prediction. It is highly needed to ...
Drug promiscuity: Exploring the polypharmacology potential of 1, 3, 6-trisubstituted 1, 4-diazepane-7-ones as an inhibitor of the ‘god father’ of immune checkpoint
Graphical abstract

Display Omitted
Highlights
- We used the similarities in the binding site of unsimilar proteins to repurpose an existing inhibitor.
Abstract
High production cost, instability, low tumor penetration are some of the shortcomings that have characterized and undermined the use of antibodies as a target for Cytotoxic T-lymphocytes associated protein 4 (CTLA-4). Design and ...

Comments

Please enable JavaScript to view thecomments powered by Disqus.

Information & Contributors

Information

Published In

cover image Journal of Biomedical Informatics

Journal of Biomedical Informatics Volume 84, Issue C

Aug 2018

203 pages

ISSN:1532-0464

Issue’s Table of Contents

Elsevier Inc.

Publisher

Elsevier Science

San Diego, CA, United States

Publication History

Published: 01 August 2018

Author Tags

Qualifiers

Research-article

Contributors

Other Metrics

View Article Metrics

Bibliometrics & Citations

Bibliometrics

Article Metrics

2
Total Citations
View Citations
0
Total Downloads

Downloads (Last 12 months)0
Downloads (Last 6 weeks)0

Reflects downloads up to 03 Jan 2025

Other Metrics

View Author Metrics

Citations

Cited By

Iqbal AShah IInjila Assad AAhmed MShah S(2024)A review of deep learning algorithms for modeling drug interactionsMultimedia Systems10.1007/s00530-024-01325-930:3Online publication date: 14-Apr-2024
https://dl.acm.org/doi/10.1007/s00530-024-01325-9
Xi XWei JGuo YDuan W(2022)Academic collaborations: a recommender framework spanning research interests and network topologyScientometrics10.1007/s11192-022-04555-8127:11(6787-6808)Online publication date: 1-Nov-2022
https://dl.acm.org/doi/10.1007/s11192-022-04555-8

View Options

View options

Media

Figures

Other

Tables

View Issue’s Table of Contents