Spectral clustering on neighborhood kernels with modified symmetry for remote homology detection
(2011) 2nd International Conference on Emerging Applications of Information Technology, EAIT 2011 p.269-272- Abstract
Remote homology detction among proteins in an unsupervised approach from sequences is an important problem in computational biology. The existing neighborhood cluster kernel methods and Markov clustering algorithms are most efficient for homolog detection. Yet they deviate from random walks with inflation or similarity depending on hard thresholds. Our spectral clustering approach with new combined local alignment kernels more effectively exploits state-ofthe- art neighborhood vectors globally. This appoarch combined with Markov clustering similarity after modified symmetry based corrections outperforms other six cluster kernels for unsupervised remote homolog detection even in multi-domain and promiscuous proteins from Genolevures... (More)
Remote homology detction among proteins in an unsupervised approach from sequences is an important problem in computational biology. The existing neighborhood cluster kernel methods and Markov clustering algorithms are most efficient for homolog detection. Yet they deviate from random walks with inflation or similarity depending on hard thresholds. Our spectral clustering approach with new combined local alignment kernels more effectively exploits state-ofthe- art neighborhood vectors globally. This appoarch combined with Markov clustering similarity after modified symmetry based corrections outperforms other six cluster kernels for unsupervised remote homolog detection even in multi-domain and promiscuous proteins from Genolevures database with better biological relevance. Source code available upon request.
(Less)
- author
- Sarkar, Anasua
LU
; Nikolski, Macha and Maulik, Ujjwal
- publishing date
- 2011-04-18
- type
- Chapter in Book/Report/Conference proceeding
- publication status
- published
- keywords
- Kernel matrix, Modified symmetry distance measure, Remote homology detection, Spectral clustering
- host publication
- Proceedings - 2nd International Conference on Emerging Applications of Information Technology, EAIT 2011
- article number
- 5734942
- pages
- 4 pages
- conference name
- 2nd International Conference on Emerging Applications of Information Technology, EAIT 2011
- conference location
- Kolkata, India
- conference dates
- 2011-02-19 - 2011-02-20
- external identifiers
-
- scopus:79953880257
- ISBN
- 9780769543291
- DOI
- 10.1109/EAIT.2011.81
- language
- English
- LU publication?
- no
- id
- 41e6b4ab-e517-47a6-9930-7b0c3093bc5f
- date added to LUP
- 2018-10-09 09:57:00
- date last changed
- 2022-01-31 05:58:12
@inproceedings{41e6b4ab-e517-47a6-9930-7b0c3093bc5f, abstract = {{<p>Remote homology detction among proteins in an unsupervised approach from sequences is an important problem in computational biology. The existing neighborhood cluster kernel methods and Markov clustering algorithms are most efficient for homolog detection. Yet they deviate from random walks with inflation or similarity depending on hard thresholds. Our spectral clustering approach with new combined local alignment kernels more effectively exploits state-ofthe- art neighborhood vectors globally. This appoarch combined with Markov clustering similarity after modified symmetry based corrections outperforms other six cluster kernels for unsupervised remote homolog detection even in multi-domain and promiscuous proteins from Genolevures database with better biological relevance. Source code available upon request.</p>}}, author = {{Sarkar, Anasua and Nikolski, Macha and Maulik, Ujjwal}}, booktitle = {{Proceedings - 2nd International Conference on Emerging Applications of Information Technology, EAIT 2011}}, isbn = {{9780769543291}}, keywords = {{Kernel matrix; Modified symmetry distance measure; Remote homology detection; Spectral clustering}}, language = {{eng}}, month = {{04}}, pages = {{269--272}}, title = {{Spectral clustering on neighborhood kernels with modified symmetry for remote homology detection}}, url = {{http://dx.doi.org/10.1109/EAIT.2011.81}}, doi = {{10.1109/EAIT.2011.81}}, year = {{2011}}, }