Comparative Study of Supervised and Semi-Supervised Learning for Enhanced Drug Prediction
DOI:
https://doi.org/10.26438/ijcse/v6i9.8389Keywords:
Drug query system, Data mining, Clustering, Classification, Semi-supervised learningAbstract
Several precautions should be taken in using pharmaceutical drugs, for both healthcare professionals, who prescribe and administer drugs, and for drug consumers. Factors such as interactions among the prescribed drugs, interactions with the patient’s current medication, side effects to be avoided, and contraindications, need to be carefully considered. Additionally, the presence of some drug properties, such as side effects and effectiveness, depends on characteristics of patients, such as age, gender, lifestyles, and genetic profiles. The goal is to provide a system to assist medical professionals and drug consumers in choosing and finding drugs that suit their needs. And develop an approach that allows querying for drugs that satisfy a set of conditions. The approach allows users to specify side effects and tailors the answers based on user specification. Finally utilize drug data from multiple data sources. However, drug data are usually noisy and incomplete as they are either manually curated or automatically extracted from text resources such as drug labels. To cope with incomplete and noisy data, data mining techniques were designed and implemented which include clustering and classification algorithms. Then the developed system was used for comparative analysis of supervised and semi-supervised learning using performance metrics. The result shows that Semi-supervised method provided 40% improved response time in comparison with Supervised method in Drug Retrieval System.
References
[1] E. Bressoet al., “Integrative relational machine-learningfor understanding drug side-effect profiles,`` BMC Bioinf.,vol. 14, Issue 2 Jun. 2013.
[2] T. Liu and R. B. Altman, ``Relating essential proteins to drug side effects using canonical component analysis: A structure-based approach,`` J. Chem. Inf. Model., vol. 55, no. 7, 2015.
[3] D. S.Wishartet al., ``DrugBank: A knowledgebase for drugs, drug actions and drug targets,`` Nucl. Acids Res., vol. 36, Issue 1, Nov. 2007.
[4] J. Bowes et al., ``Reducing safety-related drug attrition: The use of in vitro pharmacological profiling,`` Nature Rev. Drug Discovery, vol. 11, no. 12, 2012.
[5] X. Wang, B. Thijssen, and H. Yu, ``Target essentiality and centrality characterize drug side effects,`` PLoSComput. Biol., vol. 9, no. 7, p. 2013.
[6] M. Duran-Frigola and P. Aloy, ``Analysis of chemical and biological features yields mechanistic insights into drug side effects,`` Chem. Biol., vol. 20, no. 4, 2013.
[7] T. Liu and R. B. Altman, ``Relating essential proteins to drug side effects using canonical component analysis: A structure-based approach,`` J. Chem. Inf. Model., vol. 55, no. 7, 2015.
[8] S. Jamal, S. Goyal, A. Shanker, and A. Grover, ``Predicting neurological adverse drug reactions based on biological, chemical and phenotypic properties of drugs using machine learning models,`` Sci. Rep., vol. 7, Issue 2 Apr. 2017
[9] J. Scheiberet al., ``Mapping adverse drug reactions in chemical space,`` J. Med. Chem., vol. 52, no. 9, 2009.
[10] Y. Yamanishi, M. Kotera, M. Kanehisa, and S. Go to, ``Drug-target interaction prediction from chemical, genomic and pharmacological data in an integrated framework,`` Bioinformatics, vol. 26, no. 12, 2010.
[11] A. F. Fliri, W. T. Loging, P. F. Thadeio, and R. A. Volkmann, ``Analysis of drug-induced effect patterns to link structure and side effects of medicines,`` Nature Chem. Biol., vol. 1, no. 7, 2005.
[12] J. Scheiberet al., ``Gaining insight into off-target mediated effects of drug candidates with a comprehensive systems chemical biology analysis,`` J. Chem. Inf. Model., vol. 49, no. 2, 2009.
[13] F. Wang, P.Zhang, N. Cao, J. Hu, and R. Sorrentino, ``Exploring the associations between drug side-effects and therapeutic indications,``J.Biomed.Inform.,vol. 51, Oct.2014.
[14] S. Mizutani, E. Pauwels, V. Stoven, S. Goto, and Y. Yamanishi, ``Relating drug protein interaction network with drug sideeffects,`` Bioinformatics, vol. 28, no. 18, 2012.
[15] Y. Yamanishi, E. Pauwels, and M. Kotera, ``Drug side-effect prediction based on the integration of chemical and biological spaces,`` J. Chem. Inf.Model., vol. 52, no. 12, 2012.
[16] M. Liu et al., ``Determining molecular predictors of adverse drug reactions with causality analysis based on structure learning,`` J. Amer. Med. Inform.Assoc., vol. 21, no. 2, 2014.
[17] F. Cheng et al., ``Adverse drug events: Database construction and in silicoprediction,`` J. Chem. Inf. Model., vol. 53, no. 4, pp. 744-752, 2013
[18] W. Zhang, H. Zou, L. Luo, Q. Liu, W. Wu, and W. Xiao, ``Predictingpotential side effects of drugs by recommender methods and ensemble learning,`` Neurocomputing, vol. 173, pp. 979-987, Jan. 2016.
[19] Y.-G. Chen, Y.-Y. Wang, and X.-M.Zhao, ``A survey on computational approaches to predicting adverse drug reactions,`` Current Topics Med.Chem., vol. 16, no. 30, 2016.
[20] D. P. Williams and B. K. Park, ``Idiosyncratic toxicity: The role of toxicophores and bioactivation,`` Drug Discovery Today, vol. 8, no. 22, pp. 1044-1050, 2003.
Downloads
Published
How to Cite
Issue
Section
License
This work is licensed under a Creative Commons Attribution 4.0 International License.
Authors contributing to this journal agree to publish their articles under the Creative Commons Attribution 4.0 International License, allowing third parties to share their work (copy, distribute, transmit) and to adapt it, under the condition that the authors are given credit and that in the event of reuse or distribution, the terms of this license are made clear.
