Call For Papers
Contact Us

  Semi-Supervised Drug Repositioning Framework based on Drug, Target, and Disease Fingerprints  
  Authors : Eman Ismail
  Cite as:


Drug Repositioning makes a significant contribution to industry and research due to its ability to reduce the time and cost of drug discovery through making use of the existing drugs. At the time of writing this research, many computational methods have been proposed; however, few of them were able to integrate chemical space (drugs) and genomic space (targets) with disease space. In addition, using the feature-based method in Drug Target Interaction (DTI) and Target Disease Interaction (TDI) models are not wellexploited. Hence, developing an efficient approach in order to predict potential DTI and TDI is necessary. In this research, we introduce an integrated computational framework to predict potential interactions of drug-target and target-disease basing on features extracted from drugs, targets, and diseases using various learning methods (e.g., Random Forest, Decision Trees, Logistic Regression).


Published In : IJCSN Journal Volume 8, Issue 3

Date of Publication : June 2019

Pages : 331-338

Figures :06

Tables : 03


Eman Ismail : Computer Science Department, Faculty of Computers and Information Helwan University, Cairo, Egypt.


Discriminant analysis, face recognition, featureextraction, graph-based embedding, local discriminant embedding (LDE), small-sample-size (SSS) problem

For enhancing the drug repositioning problem, we involved the target as a link between drug and disease classes; most of the developed approaches do not address the problem as two relations: drug-target and targetdisease. Conducted experiments revealed that involving the target information boosts the performance relatively. The two models we defined, i.e., the Drug Target Interaction (DTI) and Target Disease Interaction (TDI), showed that the target correlated with both the drug and disease. In addition, applying the Positive-Unlabeled (PU) approach to obtain distribution from the unlabeled space caused our models to be unbiased towards the positive predictions. Using the feature-based approach for the DTI and TDI models was an efficient solution to overcome the limitations practiced in the similarity and network approaches. Although Drug Repositioning is an efficient way to shorten the drug discovery process, we still need, not surprisingly, input from expertise in biochemistry to validate our findings.


[1] D. Cook, D. Brown, R. Alexander, R. March, P. Morgan,G. Satterthwaite, and M. N. Pangalos, "Lessons learned from the fate of AstraZeneca's drug pipeline: A five-dimensional framework," Nature Reviews Drug Discovery, vol. 13, no. 6, pp. 419-431, 2014. [2] K. Sharma, "CDER New Drugs Program: 2018 Update," p. 22, 2018. [3] W. Wang, S. Yang, X. Zhang, and J. Li, "Drug repositioning by integrating target information through a heterogeneous network model," Bioinformatics (Oxford, England), 2014. [4] W. Baalawi, O. Soufan, M. Essack, P. Kalnis, and V. B. Bajic, "DASPfind: new efficient method to predict drugtarget interactions," Journal of Cheminformatics, vol. 8, 2016.[Online]. [5] L. Perlman, A. Gottlieb, N. Atias, E. Ruppin, and R. Sharan, "Combining Drug and Gene Similarity Measures for Drug-Target Elucidation." [6] J. T. Dudley, E. Schadt, M. Sirota, A. J. Butte, and E. Ashley, "Drug discovery in a multidimensional world: Systems, patterns, and networks," Journal of Cardiovascular Translational Research, vol. 3, no. 5, pp. 438-447, 2010. [7] P. Zhang, F. Wang, and J. Hu, "Towards drug repositioning: a unified computational framework for integrating multiple aspects of drug similarity and disease similarity." AMIA ... Annual Symposium proceedings. AMIA Symposium, vol. 2014, pp. 1258- 67, 2014. [8] M. J. Keiser, V. Setola, J. J. Irwin, C. Laggner, A. Abbas, S. J. Hufeisen, N. H. Jensen, M. B. Kuijer, R. C. Matos, T. B. Tran, R. Whaley, R. A. Glennon, J. Hert, K. L. H. Thomas, D. D. Edwards, B. K. Shoichet, and B. L. Roth, "Predicting new molecular targets for known drugs," 2009. [9] Y. Yamanishi, M. Kotera, M. Kanehisa, and S. Goto, "Drug-target interaction prediction from chemical, genomic and pharmacological data in an integrated framework," Bioinformatics, 2010. [10] Z. Yu, M. D. Gonciarz, W. I. Sundquist, C. P. Hill, and J. Jensen, "A New Method for Computational Drug Repositioning Using Drug Pairwise Similarity," vol. 377, no. 2, pp. 364-377, 2012. [11] 000K. Zhao and H.-C. So, "A machine learning approach to drug repositioning based on drug expression profiles: Applications in psychiatry," arXiv preprint arXiv:1706.03014, 2017. [12] R. Hodos, B. Kidd, K. Shameer, B. Readhead, and J. Dudley, "Computational Approaches to Drug Repurposing and Pharmacology," Wiley interdisciplinary reviews. Systems biology and medicine, vol. 8, no. 3, [13] G. Wu, J. Liu, and C. Wang, "Semi-supervised graph cut algorithm for drug repositioning by integrating drug, disease and genomic associations," Proceedings - 2016 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2016, pp. 223-228, 2017. [14] D. H. Le and D. Nguyen-Ngoc, "Drug repositioning by integrating known disease-gene and drug-target associations in a semi-supervised learning model," Acta Biotheoretica, vol. 66, no. 4, pp. 315-331, 2018. [Online]. [15] J. Lamb, E. D. Crawford, D. Peck, J. W. Modell, I. C. Blat, M. J. Wrobel, J. Lerner, J.-P. Brunet, A. Subramanian, K. N. Ross et al., "The connectivity map: using gene-expression signatures to connect small molecules, genes, and disease," science, vol. 313, no. 5795, pp. 1929-1935, 2006. [16] A. C. Cheng, R. G. Coleman, K. T. Smyth, Q. Cao, P. Soulard, D. R. Caffrey, A. C. Salzberg, and E. S. Huang, "Structure-based maximal affinity model predicts smallmolecule druggability," Nature Biotechnology, vol. 25, no. 1, pp. 71-75, 2007. [17] Z.-C. Li, M.-H. Huang, W.-Q. Zhong, Z.-Q. Liu, Y. Xie, Z. Dai, and X.-Y. Zou, "Identification of drug-target interaction from interactome network with guilt-byassociation principle and topology features," Bioinformatics, vol. 32, no. 7, pp. 1057-1064, 2015. [18] K. Bleakley and Y. Yamanishi, "Supervised prediction of drug-target interactions using bipartite local models," Bioinformatics, 2009. [19] Y. Wang and J. Zeng, "Predicting drug-target interactions using restricted Boltzmann machines," in Bioinformatics, 2013. [20] C. Wang, J. Liu, F. Luo, Y. Tan, Z. Deng, and Q.-N. Hu, "Pairwise input neural network for target-ligand interaction prediction," in Bioinformatics and Biomedicine (BIBM), 2014 IEEE International Conference on. IEEE, 2014, pp. 67-70. [21] Z. C. Li, M. H. Huang, W. Q. Zhong, Z. Q. Liu, Y. Xie, Z. Dai, and X. Y. Zou, "Identification of drug-target interaction from interactome network with 'guilt-byassociation' principle and topology features," Bioinformatics, 2016. [22] B. Sushma, C. V. Suresh, S. Mary, and E. G. D. Ap, "DOCKING-A Review," Applicable Chemistry, vol. 1, no. 2, pp. 167-173, 2012. [23] F. Yang, J. Xu, and J. Zeng, "DRUG-TARGET INTERACTION PREDICTION BY INTEGRATING CHEMICAL, GENOMIC, FUNCTIONAL AND PHARMACOLOGICAL DATA HHS Public Access," Pac Symp Biocomput, pp. 148-159, 2014. [Online]. [24] L. Xie, T. Evangelidis, L. Xie, and P. E. Bourne, "Drug discovery using chemical systems biology: Weak inhibition of multiple kinases may contribute to the anticancer effect of nelfinavir," PLoS Computational Biology, vol. 7, no. 4, 2011. [25] L. Yang, K. Wang, J. Chen, A. G. Jegga, H. Luo, L. Shi, C. Wan, X. Guo, S. Qin, G. He, G. Feng, and L. He, "Exploring off-targets and off-systems for adverse drug reactions via chemical-protein interactome clozapineinduced agranulocytosis as a case study," PLoS Computational Biology, vol. 7, no. 3, 2011. [26] Z. Mousavian and A. Masoudi-Nejad, "Drug-target interaction prediction via chemogenomic space: learning-based methods," Expert opinion on drug metabolism & toxicology, vol. 10, no. 9, pp. 1273-1287, 2014. [27] S. Kim, D. Jin, and H. Lee, "Predicting drug-target interactions using drug-drug interactions," PLoS ONE, vol. 8, no. 11, pp. 1-12, 2013. [28] K. Tian, M. Shao, Y. Wang, J. Guan, and S. Zhou, "Boosting compound-protein interaction prediction by deep learning," 2016. [29] Y. Bromberg, "Chapter 15: Disease Gene Prioritization," PLoS Computational Biology, vol. 9, no. 4, 2013. [30] L. Huang, Y. Wang, Y. Wang, and T. Bai, "Gene- Disease Interaction Retrieval from Multiple Sources : A Network Based Method," vol. 2016, 2016. [31] K. Wysocki and L. Ritter, "An Approach to Understanding GeneDisease Interactions." [32] D. A. Davis and N. V. Chawla, "Exploring and Exploiting Disease Interactions from Multi-Relational Gene and Phenotype Networks," vol. 6, no. 7, 2011. [33] A. Suratanee and K. Plaimas, "Network-based association analysis to infer new disease-gene relationships using large-scale protein interactions," PLoS ONE, vol. 13, no. 6, pp. 1-20, 2018. [34] J. Zhao, T.-h. Yang, Y. Huang, and P. Holme, "Ranking Candidate Disease Genes from Gene Expression and Protein Interaction : A Katz-Centrality Based Approach," vol. 6, no. 9, 2011. [35] L. Katz, "a New Status INDEX DERIVED From Sociometric," Psychmetrika, vol. 18, no. 1, pp. 39-43, 1953. [37] S. S. Khan and M. G. Madden, "One-class classification: taxonomy of study and review of techniques," The Knowledge Engineering Review, vol. 29, no. 3, pp. 345-374, 2014. [38] P. Juszczak, "Learning to recognise: A study on oneclass classification and active learning," 2006. [39] R. Kiryo, G. Niu, M. C. du Plessis, and M. Sugiyama, "Positive-unlabeled learning with non-negative risk estimator," in Advances in neural information processing systems, 2017, pp. 1675-1685. [40] E. Sansone, F. G. De Natale, and Z.-H. Zhou, "Efficient training for positive unlabeled learning," IEEE Transactions on Pattern Analysis and Machine Intelligence, 2018. [41] J. Bekker and J. Davis, "Learning from positive and unlabeled data: A survey," arXiv preprint arXiv:1811.04820, 2018. [42] M. A. Pimentel, D. A. Clifton, L. Clifton, and L. Tarassenko, "A review of novelty detection," Signal Processing, vol. 99, pp. 215-249, 2014. [43] S. Marsland, "Novelty detection in learning systems," Neural computing surveys, vol. 3, no. 2, pp. 157-195, 2003. [44] A. Liaw, M. Wiener et al., "Classification and regression by randomforest," R news, vol. 2, no. 3, pp. 18-22, 2002. [45] S. R. Safavian and D. Landgrebe, "A survey of decision tree classifier methodology," IEEE transactions on systems, man, and cybernetics, vol. 21, no. 3, pp. 660- 674, 1991. [46] D. S. Wishart, Y. D. Feunang, A. C. Guo, E. J. Lo, A. Marcu, J. R. Grant, T. Sajed, D. Johnson, C. Li, Z. Sayeeda, N. Assempour, I. Iynkkaran, Y. Liu, A. MacIejewski, N. Gale, A. Wilson, L. Chin, R. Cummings, D. Le, A. Pon, C. Knox, and M. Wilson, "DrugBank 5.0: A major update to the DrugBank database for 2018," Nucleic Acids Research, vol. 46, no. D1, pp. D1074-D1082, 2018. [47] S. Kim, P. A. Thiessen, E. E. Bolton, J. Chen, G. Fu, A. Gindulyte, L. Han, J. He, S. He, B. A. Shoemaker, J. Wang, B. Yu, J. Zhang, and S. H. Bryant, "PubChem substance and compound databases," Nucleic Acids Research, vol. 44, no. D1, pp. D1202-D1213, 2016. [48] R. D. Finn, P. Coggill, R. Y. Eberhardt, S. R. Eddy, J. Mistry, A. L. Mitchell, S. C. Potter, M. Punta, M. Qureshi, A. Sangrador-Vegas, G. A. Salazar, J. Tate, and A. Bateman, "The Pfam protein families database: Towards a more sustainable future," Nucleic Acids Research, vol. 44, no. D1, pp. D279-D285, 2016. [49] R. Xu, L. Li, and Q. Wang, "Towards building a disease-phenotype knowledge base: Extracting diseasemanifestation relationship from literature," Bioinformatics, vol. 29, no. 17, pp. 2186-2194, 2013. [50] M. K. Gilson, T. Liu, M. Baitaluk, G. Nicola, L. Hwang, and J. Chong, "BindingDB in 2015: A public database for medicinal chemistry, computational chemistry and systems pharmacology," Nucleic Acids Research, vol. 44, no. D1, pp. D1045-D1053, 2016. [51] J. Piñero, Á. Bravo, N. Queralt-Rosinach, A. Gutiérrez- Sacristán, J. Deu-Pons, E. Centeno, J. Garci?a-Garci?a, F. Sanz, and L. I. Furlong, "Dis-GeNET: A comprehensive platform integrating information on human diseaseassociated genes and variants," Nucleic Acids Research, vol. 45, no. D1, pp. D833-D839, 2017. [52] D. G. Kleinbaum, K. Dietz, M. Gail, M. Klein, and M. Klein, Logistic regression. Springer, 2002. [53] M. Fishbein and I. Ajzen, Predicting and changing behavior: The reasoned action approach. Psychology Press, 2011. [54] C. D. Cunha, B. Agard, and A. Kusiak, "quality r P Fo r R w On ly," 2010. [55] M. Bee, "Simulating copula-based distributions and estimating tail probabilities by means of adaptive imporance sampling," 2010. [56] P. Trivedi and D. Zimmer, "A Note on Identification of Bivariate Copulas for Discrete Count Data," Econometrics, vol. 5, no. 1, p. 10, 2017. [57] P. K. Trivedi and D. M. Zimmer, "Copula Modeling: An Introduction for Practitioners," Foundations and Trends R in Econometrics, vol. 1, no. 1, pp. 1-111, 2006. [58] "simstudy update: improved correlated binary outcomes," 2018.