A Method Combining Knowledge Graph and Deep Learning for Drug Discovery
SANG Shengtian1, YANG Zhihao1, LIU Xiaoxia1, WANG Lei2, ZHAO Di1, LIN Hongfei1, WANG Jian1
1.School of Computer Science and Technology, Dalian University of Technology, Dalian 116024 2.Institute of Health Service and Blood Research, Academy of Military Medical Sciences, Beijing 100850
Abstract:The massive growing amount of biomedical literature brings huge challenges for data mining. In this paper, a method combining knowledge graph and deep learning is proposed to discover potential therapeutic drugs for disease of interest. Firstly, a biomedical knowledge graph is constructed with the relations extracted from biomedical literature. Then, the entities and relations of the knowledge graph are converted into low dimension continuous embeddings by knowledge graph embedding method. Finally, a recurrent neural network based drug discovery model is trained by using the known drug-disease related associations. The experimental results show that the proposed method can discover drugs for diseases and provide the drug mechanism of action.
桑盛田, 杨志豪, 刘晓霞, 王磊, 赵迪, 林鸿飞, 王健. 融合知识图谱与深度学习的药物发现方法[J]. 模式识别与人工智能, 2018, 31(12): 1103-1110.
SANG Shengtian, YANG Zhihao, LIU Xiaoxia, WANG Lei, ZHAO Di, LIN Hongfei, WANG Jian. A Method Combining Knowledge Graph and Deep Learning for Drug Discovery. , 2018, 31(12): 1103-1110.
[1] MORGAN S, GROOTENDORST P, LEXCHIN J, et al. The Cost of Drug Development: A Systematic Review. Health Policy, 2011, 100(1): 4-17. [2] SPANGLER S, WILKINS A D, BACHMAN B J, et al. Automated Hypothesis Generation Based on Mining Scientific Literature // Proc of the 20th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. New York, USA: ACM, 2014: 1877-1886. [3] COHEN T, WIDDOWS D, SCHVANEVELDT R W, et al. Discovery at a Distance: Farther Journeys in Predication Space // Proc of the IEEE Conference on Bioinformatics and Biomedicine Workshops. Washington, USA: IEEE, 2012: 218-225. [4] AHLERS C B, HRISTOVSKI D, KILICOGLU H, et al. Using the Literature-Based Discovery Paradigm to Investigate Drug Mechanisms[C/OL]. [2018-09-25]. https://www.ncbi.nlm.nih.gov/pmc/articles/PMC2655783/pdf/amia-0006-s2007.pdf. [5] HRISTOVSKI D, FRIEDMAN C, RINDFLESCH T C, et al. Exploiting Semantic Relations for Literature-Based Discovery[C/OL]. [2018-09-25]. https://www.ncbi.nlm.nih.gov/pmc/articles/PMC1839258/pdf/AMIA2006_0349.pdf. [6] GAWEHN E, HISS J A, SCHNEIDER G. Deep Learning in Drug Discovery. Molecular Informatics, 2016, 35(1): 3-14. [7] RINDFLESCH T C, FISZMAN M. The Interaction of Domain Know-ledge and Linguistic Structure in Natural Language Processing: Interpreting Hypernymic Propositions in Biomedical Text. Journal of Biomedical Informatics, 2003, 36(6): 462-477. [8] BORDES A, USUNIER N, GARCIA-DURAN A, et al. Translating Embeddings for Modeling Multi-relational Data // BURGES C J C, BOTTOU L, WELLING M , et al., eds. Advances in Neural Information Processing Systems 26. Cambridge, USA: The MIT Press, 2013: 2787-2795. [9] CAO D S, ZHANG L X, TAN G S, et al. Computational Prediction of Drug Target Interactions Using Chemical, Biological, and Network Features. Molecular informatics, 2014, 33(10): 669-681. [10] BYVATOV E, FECHNER U, SADOWSKI J, et al. Comparison of Support Vector Machine and Artificial Neural Network Systems for Drug/Nondrug Classification. Journal of Chemical Information and Computer Sciences, 2003, 43(6): 1882-1889. [11] CHEN X, LIU M X, YAN G Y. Drug-Target Interaction Prediction by Random Walk on the Heterogeneous Network. Molecular BioSystems, 2012, 8(7): 1970-1978. [12] LIU H, SONG Y L, GUAN J H, et al. Inferring New Indications for Approved Drugs via Random Walk on Drug-Disease Heterogenous Networks[C/OL]. [2018-09-25]. https://doi.org/10.1186/s12859-016-1336-7. [13] SANG S, YANG Z, WANG L, et al. Sematyp: A Knowledge Graph Based Literature Mining Method for Drug Discovery[C/OL]. [2018-09-25]. https://doi.org/10.1186/s12859-018-2167-5.