藥物不良反應定義為人體在服用藥物後所產生的非預期且有害的反應。藥物不良反應可以對社會造成經濟上與醫學上的負擔；此外，由於近年來民眾同時服用多種藥物的趨勢增加，使得藥物不良反應所造成的問題更為顯著。因此，對藥物不良反應的預測與監控的方法是必要的。此研究的目的是預測藥物不良反應，不僅是對於單一藥物，也對多個藥物進行不良反應的預測。我們提出將隨機漫步模型運用於化學與表現型整合網路上以預測藥物不良反應，並分別對於單一藥物與多個藥物設計實驗。化學與表現型整合網路是由4種不同類型的資料所建構。單一藥物實驗的評估方式是基於5折交叉驗證，並對不同類型資料的組合方式進行評估。我們的隨機漫步模型在單一藥物實驗結果顯示，藉由適當地組合不同類型的資料，可以達到0.9431的準確率與0.5111的F1值。而在多藥物的實驗裡，我們評估的方式則是基於考量藥物不良反應在我們模型所產生的結果中的排名。實驗結果顯示出，我們的模型具有可以預測多藥物的藥物不良反應的潛力。

Adverse drug reaction (ADR) is defined as the unwanted and harmful reaction to a drug. ADR can significantly increase the clinical and economic burdens on the public. Additionally, an increased usage in polypharmacy was observed that makes ADR problems more significant. Thus, monitoring and prediction of ADRs becomes necessary. The purpose of this study is to predict ADRs not only for single drug but also for polypharmacy. A computational network-based approach, a random walk model, was proposed and applied on integrated chemical and phenotypic networks which were built from four types of data. Evaluations for single drug ADR prediction is based on the 5-fold cross validation. Different combinations of four types of data were evaluated. The results suggested that by combining four types of data appropriately, our ADR prediction model for single drug achieved the performance of 0.9431 for accuracy and 0.5111 for F1-score. For polypharmacy experiment, our evaluations were based on considering ranks of ADRs. The results suggested that our method had potential ability to predict ADRs for polypharmacy.

摘要 i
Abstract iii
Acknowledgement v
List of Tables x
List of Figures xi
1 Introduction 1
2 RelatedWork 5
2.1 Chemical-Based Methods . . . . . . . . . . . . . . . . . . . 5
2.2 Biological-Based and Phenotypic-Based Methods . . . . . . 6
2.3 Integrated-Information-Based Methods . . . . . . . . . . . . 7
3 Methodology 9
3.1 Drug-Drug Network . . . . . . . . . . . . . . . . . . . . . . 9
3.1.1 Chemical Structure Similarity . . . . . . . . . . . . 10
3.1.2 Chemical Association . . . . . . . . . . . . . . . . 12
3.2 ADR-ADR Network . . . . . . . . . . . . . . . . . . . . . 13
3.2.1 The SIDER Side Effect Resource . . . . . . . . . . 13
3.2.2 The Human Phenotype Ontology . . . . . . . . . . . 14
3.2.3 ADR Semantic Similarity . . . . . . . . . . . . . . 15
3.2.4 ADR Jaccard Similarity . . . . . . . . . . . . . . . 18
3.3 Drug-ADR Network . . . . . . . . . . . . . . . . . . . . . 19
3.4 Random Walk . . . . . . . . . . . . . . . . . . . . . . . . . 20
3.4.1 Preliminary . . . . . . . . . . . . . . . . . . . . . . 20
3.4.2 Homogeneous Propagation . . . . . . . . . . . . . . 21
3.4.3 Extended Random Walk . . . . . . . . . . . . . . . 22
3.4.4 Network Topological Bias . . . . . . . . . . . . . . 23
3.4.5 Adverse Drug Reaction Prediction Process . . . . . 24
4 Experiments and Results 27
4.1 Preprocessing . . . . . . . . . . . . . . . . . . . . . . . . . 28
4.2 Single Drug Experiment . . . . . . . . . . . . . . . . . . . 28
4.2.1 Evaluation of Different Data Combinations . . . . . 30
4.2.2 Evaluation of Different Diffusion Parameters . . . . 33
4.3 Polypharmacy Experiment . . . . . . . . . . . . . . . . . . 35
4.3.1 Evaluate Results Using Average Rank Differences . 39
4.3.2 Evaluate Results Using Weighted Rank Differences . 42
5 Conclusion and Future Work 46
5.1 Conclusion . . . . . . . . . . . . . . . . . . . . . . . . . . 46
5.2 Future Work . . . . . . . . . . . . . . . . . . . . . . . . . . 47
References 49
A Comparisons with Liu’s Work 58

[1] I. R. Edwards and J. K. Aronson. Adverse drug reactions: definitions,
diagnosis, and management. The Lancet, 356(9237):1255–1259, October
2000.
[2] A. Rohilla and S. Yadav. Adverse drug reactions: An overview. International
Journal of Pharmacological Research, 3, 2013.
[3] T. Kennedy. Managing the drug discovery/development interface.
Drug Discovery Today, 2(10):436–444, October 1997.
[4] G. Shepherd, P. Mohorn, K. Yacoub, and D. W. May. Adverse drug
reaction deaths reported in united states vital statistics, 1999-2006. Ann
Pharmacother, 46(2):169–175, February 2012.
[5] J. Sultana, P. Cutroneo, and G. Trifiro. Clinical and economic burden
of adverse drug reactions. Journal of Pharmacology and Pharmacotherapeutics,
4(5):73–77, 2013.
[6] T. J. Moore, M. R. Cohen, and C. D. Furberg. Serious adverse
drug events reported to the food and drug administration, 1998-2005.
Archives of Internal Medicine, 167(16):1752–1759, September 2007.
[7] K. B. Sonawane and R. A. Hansen. Serious adverse drug events reported
to the food and drug administration (fda): analysis of the fda
adverse event reporting system (faers) 2006-2011 database. Value in
Health, 18(3):A86, 2015.
[8] K. M. Giacomini, R. M. Krauss, D. M. Roden, M. Eichelbaum, M. R.
Hayden, and Y. Nakamura. When good drugs go bad. Nature, 446:
975, April 2007.
[9] E. J. Topol. Failing the public health – rofecoxib, merck, and the fda.
New England Journal of Medicine, 351(17):1707–1709, October 2004.
[10] S. Rambhade, A. Chakarborty, U. K. Shrivastava, A.and Patil, and
A. Rambhade. A survey on polypharmacy and use of inappropriate
medications. Toxicology International, 19(1):68–73, 2012.
[11] E. D. Kantor, C. D. Rehm, J. S. Haas, A. T. Chan, and E. L. Giovannucci.
Trends in prescription drug use among adults in the united states
from 1999-2012. The Journal of the American Medical Association,
314(17):1818–1830, November 2015.
[12] E. Pauwels, V. Stoven, and Y. Yamanishi. Predicting drug side-effect
profiles: a chemical fragment-based approach. BMC Bioinformatics,
12(1):169, May 2011.
[13] M. X. LaBute, X. Zhang, J. Lenderman, B. J. Bennion, S. E.Wong, and
F. C. Lightstone. Adverse drug reaction prediction using scores produced
by large-scale drug-protein target docking on high-performance
computing machines. PLOS ONE, 9(9):e106298, September 2014.
[14] L. Chen, J. Lu, J. Zhang, K.-R. Feng, M.-Y. Zheng, and Y.-D. Cai.
Predicting chemical toxicity effects based on chemical-chemical interactions.
PLOS ONE, 8(2):e56517, February 2013.
[15] U.S. Food and Drug Administration. The drug development process,
2018. URL https://www.fda.gov/ForPatients/
Approvals/Drugs/default.html. [updated 2018 Jan 4; cited
2018 Jan 13].
[16] L.-C. Huang, X.Wu, and J. Y. Chen. Predicting adverse side effects of
drugs. BMC Genomics, 12(5):S11, December 2011.
[17] M. Fukuzaki, M. Seki, H. Kashima, and J. Sese. Side effect prediction
using cooperative pathways. In 2009 IEEE International Conference
on Bioinformatics and Biomedicine, pages 142–147, Nov 2009.
[18] M. Campillos, M. Kuhn, A.-C. Gavin, L. J. Jensen, and P. Bork. Drug
target identification using side-effect similarity. Science, 321(5886):
263, July 2008.
[19] L. Chen, T. Huang, J. Zhang, M.-Y. Zheng, K.-Y. Feng, Y.-D. Cai, and
K.-C. Chou. Predicting drugs side effects based on chemical-chemical
interactions and protein-chemical interactions. BioMed Research International,
2013:8, 2013.
[20] Y. Yamanishi, E. Pauwels, and M. Kotera. Drug side-effect prediction
based on the integration of chemical and biological spaces. Journal of
Chemical Information and Modeling, 52(12):3284–3292, December
2012.
[21] M. Liu, Y. Wu, Y. Chen, J. Sun, Z. Zhao, X.-w. Chen, M. E. Matheny,
and H. Xu. Large-scale prediction of adverse drug reactions using
chemical, biological, and phenotypic properties of drugs. Journal of
the American Medical Informatics Association, 19(e1):e28–e35, June
2012.
[22] Y.-F. Huang, H.-Y. Yeh, and V.-W. Soo. Inferring drug-disease associations
from integration of chemical, genomic and phenotype data using
network propagation. BMC Medical Genomics, 6:S4, 2013.
[23] A. M. Johnson and G. M. Maggiora. Concepts and Applications of
Molecular Similarity. 1990.
[24] D.Weininger. Smiles, a chemical language and information system. 1.
introduction to methodology and encoding rules. J. Chem. Inf. Comput.
Sci.Journal of Chemical Information and Computer Sciences, 28(1):
31–36, February 1988.
[25] 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, 44(D1):D1202–D1213, January 2016.
[26] T. T. Tanimoto. An Elementary Mathematical Theory of Classification
and Prediction. International Business Machines Corporation, 1958.
[27] D. Bajusz, A. Rcz, and K. Hberger. Why is tanimoto index an appropriate
choice for fingerprint-based similarity calculations? Journal of
Cheminformatics, 7(1):20, May 2015.
[28] M. Kuhn, C. von Mering, M. Campillos, L. J. Jensen, and P. Bork.
Stitch: interaction networks of chemicals and proteins. Nucleic Acids
Research, 36:D684–D688, 2008.
[29] M. Kuhn, I. Letunic, L. J. Jensen, and P. Bork. The sider database of
drugs and side effects. Nucleic Acids Research, 44(Database issue):
D1075–D1079, August 2015.
[30] S. Khler, S. C. Doelken, C. J. Mungall, S. Bauer, H. V. Firth,
I. Bailleul-Forestier, G. C. M. Black, D. L. Brown, M. Brudno,
J. Campbell, D. R. FitzPatrick, J. T. Eppig, A. P. Jackson, K. Freson,
M. Girdea, I. Helbig, J. A. Hurst, J. Jhn, L. G. Jackson, A. M. Kelly,
D. H. Ledbetter, S. Mansour, C. L. Martin, C. Moss, A. Mumford,
W. H. Ouwehand, S.-M. Park, E. R. Riggs, R. H. Scott, S. Sisodiya,
S. V. Vooren, R. J. Wapner, A. O. M. Wilkie, C. F. Wright, A. T.
Vulto-van Silfhout, N. d. Leeuw, B. B. A. de Vries, N. L.Washingthon,
C. L. Smith, M. Westerfield, P. Schofield, B. J. Ruef, G. V. Gkoutos,
M. Haendel, D. Smedley, S. E. Lewis, and P. N. Robinson. The human
phenotype ontology project: linking molecular biology and disease
through phenotype data. Nucleic Acids Research, 42(D1):D966–
D974, January 2014.
[31] B. K. Park, N. R. Kitteringham, J. R. Kenny, and M. Pirmohamed.
Drug metabolism and drug toxicity. InflammoPharmacology, 9(1):
183–199, May 2001.
[32] Y. Deng, L. Gao, B. Wang, and X. Guo. Hposim: An r package for
phenotypic similarity measure and enrichment analysis based on the
human phenotype ontology. PLOS ONE, 10(2):e0115692, February
2015.
[33] P. Resnik. Semantic similarity in a taxonomy: An information-based
measure and its application to problems of ambiguity in natural language.
Journal of Artifcial Intelligence Research, 11:95–130, 1999.
[34] D. Lin. An information-theoretic definition of similarity. International
Conference on Machine Learning, pages 296–304, 1998.
[35] J. J. Jiang and D. W. Conrath. Semantic similarity based on corpus
statistics and lexical taxonomy. International Conference Research on
Computational Linguistics, page 9008, 1997.
[36] L. E. Page, S. Brin, R. Motwani, and T. Winograd. The pagerank
citation ranking: Bringing order to the web. Technical Report 1999-
66, Stanford InfoLab, November 1999. Previous number = SIDL-WP-
1999-0120.
[37] J. Davis and M. Goadrich. The relationship between precision-recall
and roc curves. In Proceedings of the 23rd international conference
on Machine learning, pages 233–240, Pittsburgh, Pennsylvania, USA,
2006.
[38] J. A. Ansari. Drug interaction and pharmacist. Journal of Young Pharmacists
: JYP, 2(3):326–331, 2010.
[39] G. Maggiora, M. Vogt, and J. Stumpfe, D.and Bajorath. Molecular
similarity in medicinal chemistry. Journal of Medicinal Chemistry, 57
(8):3186–3204, April 2014.
[40] Y. C. Martin, J. L. Kofron, and L. M. Traphagen. Do structurally similar
molecules have similar biological activity? Journal of Medicinal
Chemistry, 45(19):4350–4358, September 2002.
[41] I. Kahanda, C. Funk, and K. Verspoor. Phenostruct: Prediction of
human phenotype ontology terms using heterogeneous data sources,
2016.