Text mining for building proteins interaction networks
Text mining algorithm is an important method for extracting information from biomedical literatures. Precious text mining algorithms are not specific to biological domain. Our purpose is to find an algorithm that is most suitable for biological domain. Changes and improvements have been done to the...
Saved in:
Main Author: | |
---|---|
Other Authors: | |
Format: | Final Year Project |
Language: | English |
Published: |
2012
|
Subjects: | |
Online Access: | http://hdl.handle.net/10356/49070 |
Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
Institution: | Nanyang Technological University |
Language: | English |
Summary: | Text mining algorithm is an important method for extracting information from biomedical literatures. Precious text mining algorithms are not specific to biological domain. Our purpose is to find an algorithm that is most suitable for biological domain. Changes and improvements have been done to the existing algorithms. A new algorithm is also designed.
The existing text mining algorithms are investigated and implemented first. Pattern Matching Algorithm is a commonly-used straightforward algorithm. Results from our implementation show that the performance is not good enough. A new algorithm, Terms Association Algorithm is therefore designed and implemented. Results of Terms Association Algorithm show that it’s suitable for English biomedical literature. Its performance is better than the existing text mining algorithm, especially under biological domain.
After determining the best text mining algorithm for biological domain, the text mining algorithm was integrated together with OSEE, KEGG pathways and IntAct to construct gene regulation networks and protein-protein interaction networks. The overall performance of the constructed networks is investigated. Our new text mining algorithm hasshow in constructing biological networks. |
---|