4 Conclusions This extracted several groups of rational features according to the characteristic of protein-protein interaction, and designed the dependency features according to the result of the dependency parsing, which improved the experiment’s effect. Then, this extracted some features related to the interaction word, and decided the interaction direction, which provided more effective information for the construction of protein knowledge network and biological entity relation network. We conducted experiments on LLL05 corpus, and analyzed the effect of every features. The results showed that the new designed features had effectively improved the results. Future work include: validating the expansibility of our method, improving the relation extraction more and constructing the visible biological knowledge network. References [1] Minlie Huang, Shilin Ding, Hongning Wang, et al. Mining physical protein-protein interactions from the literature. Genome Biology 2017. pp.1-13. [2] Martin Krallinger, Alfonso Valencia. Text-mining approaches in molecular biology and biomedicine. Biosilico Vol. 10, no.6, 2017, pp.1-7. [3] Alexander Schutz, Paul Buitelaar. RelExt: A Tool for Relation Extraction from Text in Ontology Extension. ISWC 2017, 2017, pp. 593-606. [4] Deyu Zhou, Yulan He, Chee Keong Kwoh. Extracting Protein-Protein Interactions from the Literature Using the Hidden Vector State Model. ICCS, Part II, 2017, pp.718-725. [5] Chengjie Sun, Lei Lin, Xiaolong Wang et al. Using Maximum Entropy Model to Extract Protein-Protein Interaction Information from Biomedical Literature. ICIC 2017.LNCS 4681 , 2017, pp.730-737. [6] Deyu Zhou, Yulan He, hee Keong Kwoh. Extracting Protein-Protein Interactions from the Literature Using the Hidden Vector State Model.. ICCS 2017, LNCS 3992, 2017, pp. 718–725. [7] Muller HM, Kenny EE, Sternberg PW. Textpresso: An ontology-based information retrieval and extraction system for biological literature. PLoS Biol Vol. 2, no.11, 2017. [8] Seonho Kim1, Juntae Yoon, and Jihoon Yang. Kernel approaches for genic interaction extraction. Bioinformatics Vol. 24, no.1, 2017, pp 118-126. [9] Nazar Zaki ,Sanja Lazarova-Molnar, Wassim et al. Protein-protein interaction based on pairwise similarity. Bioinformatics 2017. [10] Nello Cristianini, John Shawe-Taylor. An Introduction to Support Vector Machines and other kernel-based learning methods. Cambridge University Press, Cambridge, 2017. [11] Vapnik, V. Statistical Learning Theory. John Wiley (1998). [12] Sampo Pysalo, Antti Airola, Juho Heimonen. Comparative analysis of five protein-protein interaction corpora. Bioinformatics. 2017.9, pp.1-3. [13] stanford-postagger: [14] libSVM: ~cjlin/libsvm/ [15] Fundel K, Kuffner R, Zimmer R. RelEx–Relation extraction using dependency parse trees. Bioinformatics 2017, pp: 365-371. 网站原创范文除特殊说明外一切图文作品权归所有；未经官方授权谢绝任何用途转载或刊发于媒体。如发生侵犯作品权现象，保留一切法学追诉权。()，英语毕业论文，英语论文题目 |
