簡易檢索 / 詳目顯示

回結果列表
研究生： 江歐狄
KOUTOU, Wend-Nougui Odilon
論文名稱： 基於相似度增強混合式條件受限玻爾茲曼機的藥物與標的之交互用預測
Similarity-Boosted Hybrid Conditional Restricted Boltzmann Machine (SB H-CRBM) for Drug-Target Interaction Prediction
指導教授： 蘇豐文
Soo, Von-Wun
口試委員: 李哲榮
Lee, Che-Rung
沈之涯
Shen, Chih-Ya
學位類別： 碩士
Master
系所名稱： 電機資訊學院 - 資訊系統與應用研究所
Institute of Information Systems and Applications
論文出版年： 2018
畢業學年度： 106
語文別： 英文
論文頁數： 47
中文關鍵詞： 藥物與標的之交互作用 、玻爾茲曼機 、深度學習
外文關鍵詞： drug-target interaction prediction, Restricted Boltzmann Machines, Hybrid, Similarity-Boosted, Weighted Profile Method
相關次數： 點閱：2  下載：0 
分享至:
查詢本校圖書館目錄 查詢臺灣博碩士論文知識加值系統 勘誤回報

    • 藥物研發的過程中，尚未被發現的藥物與標的之交互作用扮演著關鍵的角色。近來，電腦(對接模擬與基於機器學習)技術興起，以取代高成本、高耗時的生物實驗。在機器學習的技術裡，許多基於網路的方法被提出，例如：受限玻爾茲曼機、二分區域模型、基於網路之推演、加權資料方法和進階區域式藥物與蛋白質交互作用預測之技術。在此研究中，我們擴展受限玻爾茲曼機，藉由整合重要特徵，例如：藥物與藥物之間的相似度和標的與標的之間的相似度。此外，我們將尚未被考慮的藥物與藥物之間關聯性，合併至原始的受限玻爾茲曼機。最後，我們提出了相似性增強混合式條件受限玻爾茲曼機，其是受到推薦系統界中的內容增強式受限玻爾茲曼機所啟發。我們的實驗結果顯示出我們的方法優於先前由Wang與Zeng所提出的玻爾茲曼機。尚未被發現的藥物與標的之交互作用在藥物研發的過程中扮演著關鍵的角色。近來，電腦輔助(對接模擬與基於機器學習的方法)技術興起，以取代高成本、高耗時的生物實驗。在機器學習的領域裡，有許多基於網路的方法被提出，例如：受限玻爾茲曼機、二分區域模型、基於網路之推演、加權資料方法和進階區域式藥物與蛋白質交互作用預測之技術。在此研究中，我們透過整合重要特徵，例如：藥物與藥物之間的相似度和標的與標的之間的相似度，來擴展受限玻爾茲曼機。此外，我們將尚未被考慮的藥物與藥物之間的關聯性，合併至原始的受限玻爾茲曼機。最後，受到推薦系統界中的內容增強式受限玻爾茲曼機所啟發，我們提出了相似性增強混合式條件受限玻爾茲曼機。
    我們的實驗結果顯示出我們的方法優於先前由Wang與Zeng所提出的玻爾茲曼機。

    Uncovering drug-target interactions plays a key role in the drug development
    process. Recently, in silico (docking simulation and machine learningbased)
    techniques have emerged as an alternative to costly and time consuming
    biochemical experiments. In machine learning-based techniques, many
    network-based approaches have been proposed such as Restricted Boltzmann
    Machine (RBM), Bipartite Local Models (BLM), Network Based Inference
    (NII), Weighted profile method and Advanced Local Drug-Target
    Interaction Prediction Technique (ALADIN). In this research, we extend the
    RBM by integrating important features such as drug-drug and target-target
    similarity. In addition, we incorporate the correlations between drugs that
    have not been taken into account in the original RBM. Finally, we propose
    a Similarity-Boosted Hybrid Conditional RBM (SB H-CRBM) which is inspired
    by the Content-Boosted Restricted Boltzmann Machine(CB-RBM) [1] from the recommendation systems community.
    Our experimental results show that our method performs better than the
    RBM was previously proposed by Wang and Zeng.

    Contents Abstract 2 Acknowledgement 4 List of Tables 7 List of Figures 8 1 Introduction 1 2 RelatedWork 5 3 Methodology 8 3.1 RBM for drug-target interaction prediction . . . . . . . . . . 8 3.2 Conditional RBM for drug-target prediction . . . . . . . . . 13 3.3 Hybrid RBM for drug-target prediction . . . . . . . . . . . 14 3.4 Weighted Profile Method . . . . . . . . . . . . . . . . . . . 17 3.5 Similarity-Boosted CRBM . . . . . . . . . . . . . . . . . . 18 3.6 Similarity-Boosted Hybrid CRBM (SB H-CRBM) . . . . . . 19 3.7 Implementation . . . . . . . . . . . . . . . . . . . . . . . . 23 4 Experimental Evaluation 25 4.1 Experimental Settings . . . . . . . . . . . . . . . . . . . . . 25 4.1.1 Dataset . . . . . . . . . . . . . . . . . . . . . . . . 25 4.1.2 Evaluation Protocol and Metrics . . . . . . . . . . . 28 4.1.3 Baseline . . . . . . . . . . . . . . . . . . . . . . . . 29 4.2 Experimental Results and Discussion . . . . . . . . . . . . . 29 4.2.1 Distinction between direct and indirect interactions . 30 4.2.2 No distinction between direct and indirect interactions 34 5 Conclusion and Future Work 39 5.1 Conclusion . . . . . . . . . . . . . . . . . . . . . . . . . . 39 5.2 Future Work . . . . . . . . . . . . . . . . . . . . . . . . . . 40 References 41 List of Tables 4.1 Statistics of MATADOR dataset . . . . . . . . . . . . . . . 27 4.2 Statistics of MATADOR dataset after cross reference . . . . 28 List of Figures 2.1 RBM for drug-target interaction . . . . . . . . . . . . . . . 7 3.1 Drug-Target RBM for drug-target interaction prediction . . . 13 3.2 Drug-Drug chemical similarity matrix . . . . . . . . . . . . 15 3.3 Target-Target genomic similarity matrix . . . . . . . . . . . 16 3.4 Drug-Target interaction matrix . . . . . . . . . . . . . . . . 16 4.1 Comparison of AUROC for Direct interaction prediction. . . 31 4.2 Comparison of AUPR for Direct interaction prediction. . . . 32 4.3 Comparison of AUROC for Indirect interaction prediction. . 33 4.4 Comparison of AUPR for Indirect interaction prediction. . . 34 4.5 Comparison of AUROC for Direct interaction prediction (no distinction). . . . . . . . . . . . . . . . . . . . . . . . . . . 35 4.6 Comparison of AUPR for Direct interaction prediction (no distinction). . . . . . . . . . . . . . . . . . . . . . . . . . . 35 4.7 Comparison of AUROC for Indirect interaction prediction (no distinction). . . . . . . . . . . . . . . . . . . . . . . . . 36 4.8 Comparison of AUPR for Indirect interaction prediction (no distinction). . . . . . . . . . . . . . . . . . . . . . . . . . . 37

    References
    [1] Yongqi Liu, Qiuli Tong, Zhao Du, and Lantao Hu. Content-boosted
    restricted boltzmann machine for recommendation. pages 773–780,
    2014.
    [2] Yuhao Wang and Jianyang Zeng. Predicting drug-target interactions
    using restricted boltzmann machines. Bioinformatics, 29:i126–i134,
    2013. doi: http://doi.org/10.1093/bioinformatics/btt234.
    [3] Joseph A. DiMasi, Henry G. Grabowski, and Ronald W. Hansen. Innovation
    in the pharmaceutical industry: New estimates of r&d costs.
    Journal of Health Economics, 47:20–33, 2016. doi: https://doi.org/10.
    1016/j.jhealeco.2016.01.012.
    [4] Bruce Booth and Rodney Zemmel. Prospects for productivity. Nature
    Reviews Drug Discovery, 3:451–456, 2004. doi: http://dx.doi.org/10.
    1038/nrd1384.
    [5] Marnie L MacDonald, Jane Lamerdin, Stephen Owens, Brigitte H
    Keon, Graham K Bilter, Zhidi Shang, Zhengping Huang, Helen Yu,
    Jennifer Dias, Tomoe Minami, StephenWMichnick, and John KWestwick.
    Identifying off-target effects and hidden phenotypes of drugs
    in human cells. Nature Chemical Biology, 2:329–337, 2006. doi:
    http://dx.doi.org/10.1038/nchembio790.
    [6] Lei Xie, Li Xie, Sarah L. Kinnings, and Philip E. Bourne. Novel
    computational approaches to polypharmacology as a means to define
    responses to individual drugs. Annual Review of Pharmacology
    and Toxicology, 52:361–379, 2012. doi: https://doi.org/10.1146/
    annurev-pharmtox-010611-134630.
    [7] Alan C Cheng, Ryan G Coleman, Kathleen T Smyth, Qing Cao, Patricia
    Soulard, Daniel R Caffrey, Anna C Salzberg, and Enoch S Huang.
    Structure-based maximal affinity model predicts small-molecule druggability.
    Nature Biotechnology, 25:71, 2007. doi: http://dx.doi.org/10.
    1038/nbt1273.
    [8] Brian K Shoichet, Susan L McGovern, Binqing Wei, and John J Irwin.
    Lead discovery using molecular docking. Current Opinion in Chemical Biology, 6:439–446, 2002. doi: https://doi.org/10.1016/
    S1367-5931(02)00339-3.
    [9] Matthias Rarey, Bernd Kramer, Thomas Lengauer, and Gerhard Klebe.
    A fast flexible docking method using an incremental construction algorithm.
    Journal of Molecular Biology, 261:470–489, 1996. doi:
    https://doi.org/10.1006/jmbi.1996.0477.
    [10] Michael J Keiser, Bryan L Roth, Blaine N Armbruster, Paul Ernsberger,
    John J Irwin, and Brian K Shoichet. Relating protein pharmacology
    by ligand chemistry. Nature Biotechnology, 25:197, 2007.
    doi: http://dx.doi.org/10.1038/nbt1284.
    [11] Hiroaki Yabuuchi, Satoshi Niijima, Hiromu Takematsu, Tomomi Ida,
    Takatsugu Hirokawa, Takafumi Hara, Teppei Ogawa, Yohsuke Minowa,
    Gozoh Tsujimoto, and Yasushi Okuno. Analysis of multiple
    compound protein interactions reveals novel bioactive molecules.
    2011.
    [12] Kevin Bleakley and Yoshihiro Yamanishi. Supervised prediction of
    drugtarget interactions using bipartite local models. Bioinformatics,
    25:2397–2403, 2009. doi: http://doi.org/10.1093/bioinformatics/
    btp433.
    [13] Xing Chen, Ming-Xi Liu, and Gui-Ying Yan. Drug-target interaction
    prediction by random walk on the heterogeneous network. Molecular
    BioSystems, 8:1970–1978, 2012. doi: http://dx.doi.org/10.1039/
    C2MB00002D.
    [14] Feixiong Cheng, Chuang Liu, Jing Jiang, Weiqiang Lu, Weihua Li,
    Guixia Liu, Weixing Zhou, Jin Huang, and Yun Tang. Prediction
    of drug-target interactions and drug repositioning via networkbased
    inference. PLOS Computational Biology, 8(5):1–12, 05 2012.
    doi: 10.1371/journal.pcbi.1002503. URL https://doi.org/10.
    1371/journal.pcbi.1002503.
    [15] Jian-Ping Mei, Chee-Keong Kwoh, Peng Yang, Xiao-Li Li, and Jie
    Zheng. Drug-target interaction prediction by learning from local information
    and neighbors. Bioinformatics, 29(2):238–245, 2013. doi:
    10.1093/bioinformatics/bts670. URL http://dx.doi.org/10.
    1093/bioinformatics/bts670.
    [16] Stefan Gnther, Michael Kuhn, Mathias Dunkel, Monica Campillos,
    Christian Senger, Evangelia Petsalaki, Jessica Ahmed, Eduardo Garcia
    Urdiales, Andreas Gewiess, Lars Juhl Jensen, Reinhard Schneider,
    Roman Skoblo, Robert B. Russell, Philip E. Bourne, Peer Bork,
    and Robert Preissner. Supertarget and matador: resources for exploring
    drug-target relationships. Nucleic Acids Research, 36:D919–D922,
    2008. doi: 10.1093/nar/gkm862. URL http://dx.doi.org/10.
    1093/nar/gkm862.
    [17] Yoshihiro Yamanishi, Michihiro Araki, Alex Gutteridge, Wataru
    Honda, and Minoru Kanehisa. Prediction of drugtarget interaction
    networks from the integration of chemical and genomic spaces. Bioinformatics,
    24:i232–i240, 2008. doi: 10.1093/bioinformatics/btn162.
    [18] Hao Ding, Ichigaku Takigawa, Hiroshi Mamitsuka, and Shanfeng
    Zhu. Similarity-based machine learning methods for predicting
    drug-target interactions: a brief review. Briefings in Bioinformatics,
    15(5):734–747, 2014. doi: 10.1093/bib/bbt056. URL http:
    //dx.doi.org/10.1093/bib/bbt056.
    [19] G. E. Hinton and R. R. Salakhutdinov. Reducing the dimensionality
    of data with neural networks. Science, 313(5786):504–507,
    2006. ISSN 0036-8075. doi: 10.1126/science.1127647. URL http:
    //science.sciencemag.org/content/313/5786/504.
    [20] Geoffrey E. Hinton, Simon Osindero, and Yee-Whye Teh. A
    fast learning algorithm for deep belief nets. Neural Computation,
    18(7):1527–1554, 2006. doi: 10.1162/neco.2006.18.7.
    1527. URL https://doi.org/10.1162/neco.2006.18.
    7.1527. PMID: 16764513.
    [21] Abdel rahman Mohamed, George Dahl, and Geoffrey Hinton. Deep
    belief networks for phone recognition. 2009.
    [22] Geoffrey E Hinton and Ruslan R Salakhutdinov. Replicated
    softmax: an undirected topic model. pages 1607–
    1614, 2009. URL http://papers.nips.cc/paper/
    3856-replicated-softmax-an-undirected-topic-model.
    pdf.
    [23] Ruslan Salakhutdinov. Learning and evaluating boltzmann machines.
    2008.
    [24] Ruslan Salakhutdinov, Andriy Mnih, and Geoffrey Hinton. Restricted
    boltzmann machines for collaborative filtering. pages 791–798, 2007.
    doi: 10.1145/1273496.1273596. URL http://doi.acm.org/
    10.1145/1273496.1273596.
    [25] Kostadin Georgiev and Preslav Nakov. A non-iid framework for
    collaborative filtering with restricted boltzmann machines. 28(3):
    1148–1156, 17–19 Jun 2013. URL http://proceedings.mlr.
    press/v28/georgiev13.html.
    [26] Sunghwan Kim, Paul A Thiessen, Evan E Bolton, Jie Chen, Gang Fu,
    Asta Gindulyte, Lianyi Han, Jane He, Siqian He, Benjamin A Shoemaker,
    Jiyao Wang, Bo Yu, Jian Zhang, and Stephen H Bryant. Pubchem
    substance and compound databases. Nucleic Acids Research,
    pages D1202–D1213, 2016. doi: 10.1093/nar/gkv951. URL http:
    //www.ncbi.nlm.nih.gov/pmc/articles/PMC4702940.
    [27] TheUniProtConsortium. Uniprot: the universal protein knowledgebase.
    Nucleic Acids Research, 45(D1):D158–D169, 2017. doi:
    10.1093/nar/gkw1099. URL http://dx.doi.org/10.1093/
    nar/gkw1099.

    QR CODE