Protein Sequence Classification Using Feature Hashing

Description:

Article on protein sequence classification using feature hashing.

Creator(s):
Creation Date: June 21, 2012
Partner(s):
UNT College of Engineering
Collection(s):
UNT Scholarly Works
Usage:
Total Uses: 18
Past 30 days: 11
Yesterday: 0
Creator (Author):
Caragea, Cornelia

University of North Texas

Creator (Author):
Silvescu, Adrian

Naviance, Inc.

Creator (Author):
Mitra, Prasenjit

Pennsylvania State University

Publisher Info:
Publisher Name: BioMed Central Ltd.
Place of Publication: [London, United Kingdom]
Date(s):
  • Creation: June 21, 2012
Description:

Article on protein sequence classification using feature hashing.

Degree:
Note:

This article is part of the supplement: Selected articles from the IEEE International Conference on Bioinformatics and Biomedicine 2011: Proteome Science.

Note:

Abstract: Recent advances in next-generation sequencing technologies have resulted in an exponential increase in the rate at which protein sequence data are being acquired. The k-gram feature representation, commonly used for protein sequence classification, usually results in prohibitively high dimensional input spaces, for large values of k. Applying data mining algorithms to these input spaces may be intractable due to the large number of dimensions. Hence, using dimensionality reduction techniques can be crucial for the performance and the complexity of the learning algorithms. In this paper, we study the applicability of a recently introduced feature hashing technique to protein sequence classification, where the original high-dimensional space is "reduced" by hashing the features, using a hash function, into a lower-dimensional space, i.e., mapping features to hash keys, where multiple features can be mapped (at random) to the same hash key, and "aggregating" their counts. We compare feature hashing with the "bag of k-grams" and feature selection approaches. Our results show that feature hashing is an effective approach to reducing dimensionality on protein sequence classification tasks.

Physical Description:

8 p.: ill.

Language(s):
Subject(s):
Keyword(s): feature hashing | variable length k-grams | dimensionality reduction
Source: Proteome Science, 2012, London: BioMed Central Ltd.
Partner:
UNT College of Engineering
Collection:
UNT Scholarly Works
Identifier:
  • DOI: 10.1186/1477-5956-10-S1-S14
  • ARK: ark:/67531/metadc181699
Resource Type: Article
Format: Text
Rights:
Access: Public
Citation:
Publication Title: Proteome Science
Volume: 10
Issue: Suppl 1
Pages: 8
Peer Reviewed: Yes