Access the full text.
Sign up today, get DeepDyve free for 14 days.
Loading next page...
/lp/oxford-university-press/remote-homology-detection-a-motif-based-approach-VABYItL2bx
References (22)
-
C. O’Donovan, M. Martin, Alexandre Gattiker, E. Gasteiger, A. Bairoch, R. Apweiler (2002)
High-quality Protein Knowledge Resource: SWISS-PROT and TrEMBLBriefings in bioinformatics, 3 3
-
S. Altschul, Thomas Madden, A. Schäffer, Jinghui Zhang, Zheng Zhang, W. Miller, D. Lipman (1997)
Gapped BLAST and PSI-BLAST: a new generation of protein database search programs.Nucleic acids research, 25 17
-
C. Leslie, E. Eskin, William Noble (2001)
The Spectrum Kernel: A String Kernel for SVM Protein ClassificationPacific Symposium on Biocomputing. Pacific Symposium on Biocomputing
-
Amir Atiya (2005)
Learning with Kernels: Support Vector Machines, Regularization, Optimization, and BeyondIEEE Transactions on Neural Networks, 16
-
S. Brenner, P. Koehl, M. Levitt (2000)
The ASTRAL compendium for protein structure and sequence analysisNucleic acids research, 28 1
-
Li Liao, William Noble (2002)
Combining pairwise sequence similarity and support vector machines for remote protein homology detection -
D. Boswell (2002)
Introduction to Support Vector Machines -
C. Leslie, E. Eskin, J. Weston, William Noble (2002)
Mismatch String Kernels for SVM Protein Classification -
S. Vishwanathan, Alex Smola (2002)
Fast Kernels for String and Tree Matching -
J. Egan (1975)
Signal detection theory and ROC analysis -
Jimmy Huang, D. Brutlag (2001)
The EMOTIF databaseNucleic acids research, 29 1
-
T. Jaakkola, M. Diekhans, D. Haussler (1999)
Using the Fisher Kernel Method to Detect Remote Protein HomologiesProceedings. International Conference on Intelligent Systems for Molecular Biology
-
S. Henikoff, J. Henikoff, S. Pietrokovski (1999)
Blocks+: a non-redundant database of protein alignment blocks derived from multiple compilationsBioinformatics, 15 6
-
Temple Smith, M. Waterman (1981)
Identification of common molecular subsequences.Journal of molecular biology, 147 1
-
J. Kennedy, L. Lloyd (1994)
Enzyme nomenclature — Recommendations of the Nomenclature Committee of the International Union of Biochemistry and Molecular Biology: Academic Press Ltd, London, UK, 1992. xiii + 862 pp. Price £40.00. ISBN 0-12-227165-3Carbohydrate Polymers, 23
-
(2003)
eBLOCKS : an automated database of protein conserved regions maximizing sensitivity and specificity -
A. Barrett (1995)
Nomenclature Committee of the International Union of Biochemistry and Molecular Biology (NC-IUBMB). Enzyme nomenclature. Recommendations 1992. Supplement 2: corrections and additions (1994).European journal of biochemistry, 232 1
-
D. Knuth (1998)
The Art of Computer Programming: Volume 3: Sorting and Searching -
A. Murzin, S. Brenner, T. Hubbard, C. Chothia (1995)
SCOP: a structural classification of proteins database for the investigation of sequences and structures.Journal of molecular biology, 247 4
-
L. Falquet, M. Pagni, P. Bucher, N. Hulo, Christian Sigrist, K. Hofmann, A. Bairoch (2002)
The PROSITE database, its status in 2002Nucleic acids research, 30 1
-
C. Nevill-Manning, Thomas Wu, D. Brutlag (1998)
Highly specific protein sequence motifs for genome analysis.Proceedings of the National Academy of Sciences of the United States of America, 95 11
-
B. Boser, Isabelle Guyon, V. Vapnik (1992)
A training algorithm for optimal margin classifiers
- Publisher
- Oxford University Press
- Copyright
- © Oxford University Press 2003
- ISSN
- 1367-4803
- eISSN
- 1460-2059
- DOI
- 10.1093/bioinformatics/btg1002
- Publisher site
- See Article on Publisher Site
Abstract
Motivation: Remote homology detection is the problem of detecting homologyin cases of low sequence similarity. It is a hard computationalproblem with no approach that works well in all cases.Results: We present a method for detecting remote homology that is basedon the presence of discrete sequence motifs. The motif contentof a pair of sequences is used to define a similarity that isused as a kernel for a Support Vector Machine (SVM) classifier.We test the method on two remote homology detection tasks:prediction of a previously unseen SCOP family and prediction ofan enzyme class given other enzymes that have a similar functionon other substrates. We find that it performs significantlybetter than an SVM method that uses BLAST or Smith-Watermansimilarity scores as features.Availability: The software is available from the authors upon request.Contact: [email protected]: remote homology, discrete sequence motifs, sequence similarity,Support Vector Machines, kernel methods*To whom correspondenceshould be addressed.
Journal
Bioinformatics – Oxford University Press
Published: Jul 3, 2003