Sparse logistic classifiers for interpretable protein homology detection

Pai Hsi Huang, Vladimir Pavlovic

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

Computational classification of proteins using methods such as string kernels and Fisher-SVM has demonstrated great success. However, the resulting models do not offer an immediate interpretation of the underlying biological mechanisms. In particular; some recent studies have postulated the existence of a small subset of positions and residues in protein sequences may be sufficient to discriminate among different protein classes. In this work, we propose a hybrid setting for the classification task. A generative model is trained as a feature extractor, followed by a sparse classifier in the extracted feature space to determine the membership of the sequence, while discovering features relevant for classification. The set of sparse biologically motivated features together with the discriminative method offer the desired biological interpretability. We apply the proposed method to a widely used dataset and show that the peqormance of our models is comparable to that of the state-of-the-art methods. The resulting models use fewer than 10% of the original features. At the same time, the sets of critical features discovered by the model appear to be consistent with confirmed biological findings.

Original languageEnglish (US)
Title of host publicationProceedings - ICDM Workshops 2006 - 6th IEEE International Conference on Data Mining - Workshops
Pages99-103
Number of pages5
StatePublished - 2006
Event6th IEEE International Conference on Data Mining - Workshops, ICDM 2006 - Hong Kong, China
Duration: Dec 18 2006Dec 18 2006

Publication series

NameProceedings - IEEE International Conference on Data Mining, ICDM
ISSN (Print)1550-4786

Other

Other6th IEEE International Conference on Data Mining - Workshops, ICDM 2006
Country/TerritoryChina
CityHong Kong
Period12/18/0612/18/06

All Science Journal Classification (ASJC) codes

  • General Engineering

Fingerprint

Dive into the research topics of 'Sparse logistic classifiers for interpretable protein homology detection'. Together they form a unique fingerprint.

Cite this