Application of semantic kernels to literature-based gene function annotation

Authors:
Mathieu Blondel;Kazuhiro Seki;Kuniaki Uehara
Affiliations:
Kobe University, Nada, Kobe, Japan;Kobe University, Nada, Kobe, Japan;Kobe University, Nada, Kobe, Japan
Venue:
DS'11 Proceedings of the 14th international conference on Discovery science
Year:
2011

Citing 11
Cited 0

Exploiting generative models in discriminative classifiers

Proceedings of the 1998 conference on Advances in neural information processing systems II
Support Vector Machines: Training and Applications

Support Vector Machines: Training and Applications
In Defense of One-Vs-All Classification

The Journal of Machine Learning Research
Manual curation is not sufficient for annotation of genomic databases

Bioinformatics
Combining gene sequence similarity and textual information for gene function annotation in the literature

Information Retrieval
A dual coordinate descent method for large-scale linear SVM

Proceedings of the 25th international conference on Machine learning
Gene ontology annotation as text categorization: An empirical study

Information Processing and Management: an International Journal
LIBLINEAR: A Library for Large Linear Classification

The Journal of Machine Learning Research
Gene Functional Annotation with Dynamic Hierarchical Classification Guided by Orthologs

DS '09 Proceedings of the 12th International Conference on Discovery Science
LIBSVM: A library for support vector machines

ACM Transactions on Intelligent Systems and Technology (TIST)
Probabilistic latent semantic analysis

UAI'99 Proceedings of the Fifteenth conference on Uncertainty in artificial intelligence

Quantified Score

Hi-index	0.00

Visualization

Abstract

In recent years, a number of machine learning approaches to literature-based gene function annotation have been proposed. However, due to issues such as lack of labeled data, class imbalance and computational cost, they have usually been unable to surpass simpler approaches based on string-matching. In this paper, we investigate the use of semantic kernels as a way to address the task's inherent data scarcity and we propose a simple yet effective solution to deal with class imbalance. From experiments on the TREC Genomics Track data, our approach achieves better F1-score than two state-of-the-art approaches based on string-matching and cross-species information.