Protein-Protein Interaction Document Mining

DOI

10.2991/jcis.2006.250How to use a DOI?

Keywords

Latent semantic index, document mining, support vector machine, protein-protein interaction

Abstract

Protein-protein interactions (PPI) are very important to the understanding of metabolic pathway. Many digital publications are available today; some of them discuss PPI and some of them do not. If machine learning techniques can be used to detect those PPI documents automatically, it would save researchers tremendous amount of time to construct a biological pathway. In this study, we analyze this document mining problem by using different kinds of feature representations and classification algorithms. Latent semantic indexing (LSI) and information gain (IG) were used to extract features from a document for classification, while support vector machine (SVM) and Naïve Bayesian (NB) were the selected algorithms. It is found that the combination of LSI and SVM provided the best solution.

Copyright

© 2006, the Authors. Published by Atlantis Press.

Open Access

This is an open access article distributed under the CC BY-NC license (http://creativecommons.org/licenses/by-nc/4.0/).

Download article (PDF)

TY  - CONF
AU  - Shing Doong
AU  - Shu-Fen Hong
PY  - 2006/10
DA  - 2006/10
TI  - Protein-Protein Interaction Document Mining
BT  - Proceedings of the 9th Joint International Conference on Information Sciences (JCIS-06)
PB  - Atlantis Press
SP  - 277
EP  - 280
SN  - 1951-6851
UR  - https://doi.org/10.2991/jcis.2006.250
DO  - 10.2991/jcis.2006.250
ID  - Doong2006/10
ER  -