Gene name and relationship detection
The rapid growth of biomedical publication nowadays results the scenario of no standardization of gene name naming. This could create confusion among the researchers due to they do not realize the similar findings elsewhere as different gene name can be referring to the same gene. In order to solve...
Saved in:
Main Author: | |
---|---|
Format: | Final Year Project Report |
Language: | English |
Published: |
Universiti Malaysia Sarawak, (UNIMAS)
2013
|
Subjects: | |
Online Access: | http://ir.unimas.my/id/eprint/39036/1/Wendy%20Tan%20Wei%20Syn%20ft.pdf http://ir.unimas.my/id/eprint/39036/ |
Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
Summary: | The rapid growth of biomedical publication nowadays results the scenario of no standardization of gene name naming. This could create confusion among the researchers due to they do not realize the similar findings elsewhere as different gene name can be referring to the same gene. In order to solve this problem, this project is to identify gene name and gene relationship in biomedical texts. We are using part of speech tagging in NLTK method to identify gene name by taking proper noun as gene name. We also implemented dictionary based method to extract gene name. In order to know the relationship to two detected gene names from two documents whether both of them are related or not, we apply sentence similarity measure method by Li e. al. to compare the sentences obtained from the text. We assume that the words that appear before and after the gene name in the text are providing useful information. The sentence similarity measure computes the semantics contain in the sentence to reveal gene relationship. |
---|