Dimensionality reduction in patch-signature based protein structure matching.
Huang, Zi; Zhou, Xiaofang; Song, Dawei; Bruza, Peter
Searching bio-chemical structures is becoming an important application domain of information re- trieval. This paper introduces a protein structure matching problem and formulates it as an infor- mation retrieval problem. We first present a novel vector representation for protein structures, in which a protein structural region, formed by the vectors within the region, is defined as a patch and indexed by its patch signature. For a k-sized patch, its patch signature consists of 7k ¡ 10 inter-atom distances which uniquely determine the patch's spatial struc- ture. A patch matching function is then defined. As structures for proteins are large and complex, it is computationally expensive to identify possible matching patches for a given protein against a large protein database. We propose to apply dimensional- ity reduction to the patch signatures and show how the two problems are adapted to fit each other. The Locality Preservation Projection (LPP) and Singular Value Decomposition (SVD) are chosen and tested for this purpose. Experimental results show that the dimensionality reduction improves the searching speed while maintaining acceptable precision and recall. From a more general point of view, this paper demonstrates that information retrieval techniques can play a crucial role in solving this biologically critical but computationally expensive problem.
HUANG, Z., ZHOU, X., SONG, D. and BRUZA, P. 2006. Dimensionality reduction in patch-signature based protein structure matching. In: Dobbie, G. and Bailey, J. (eds.) Proceedings of the 17th Australasian database conference (ADC'06), 16-19 January 2006, Hobart, Australia. Darlinghurst: Australian Computer Society [online], pages 89-97. Available from: https://dl.acm.org/citation.cfm?id=1151746
|Conference Name||17th Australasian database conference (ADC'06)|
|Conference Location||Hobart, Australia|
|Start Date||Jan 16, 2006|
|End Date||Jan 19, 2006|
|Acceptance Date||Jan 31, 2006|
|Online Publication Date||Jan 31, 2006|
|Publication Date||Dec 31, 2006|
|Deposit Date||Sep 7, 2009|
|Publicly Available Date||Sep 7, 2009|
|Publisher||Australian Computer Society Inc|
|Keywords||Protein structure matching; Similarity measure; Dimensionality reduction|
HUANG 2006 Dimensionality reduction in patch-signature
Publisher Licence URL
You might also like
Predicting emotional reaction in social networks.
Early fusion and query modification in their dual late fusion forms.
You have e-mail, what happens next? Tracking the eyes for genre.