Deriving protein-protein interactions of dengue from literature based on pattern mining methods

• Main Author: Zhang, Xingjia
• Other Authors: Rajapakse Jagath Chandana
• Format: Final Year Project
• Language: English
• Published: 2015
• Subjects: DRNTU::Engineering::Computer science and engineering::Information systems
• Online Access: http://hdl.handle.net/10356/62871
• Institution: Nanyang Technological University

Dengue fever is a disease widespread through tropical areas. It is caused by the Dengue virus and is transmitted by Aedes, a kind of mosquito. The World Health Organization reports that number of global incidents of dengue has grown rapidly over the past decades. However, while progress has been made in development of vaccines for Dengue, there is no specific treatment or vaccine for dengue available at the moment. It is believed that building an interaction network among proteins of the dengue virus and human proteins would aid the development of vaccines and dengue specific treatment. However, to the author’s knowledge, there is no dengue specific protein interaction information in existing medical databases. Hence, this project looks into building a protein interaction network by utilizing pattern-based interaction extraction method. To reach this end, the following steps were taken. First, abstracts were downloaded from the Medline database with query ‘dengue’. These abstracts were filtered and ranked by their relevance to protein interactions. Protein mentions are extracted. Next, 1000 sentences were selected and annotated. From these sentences, patterns indicating protein interactions were extracted; they were then applied to other sentences to find protein interactions. 360 binary interactions were found. Lastly, a protein interaction network was drawn.