Profile-based string kernels for remote homology detection and motif extraction.

We introduce novel profile-based string kernels for use with support vector machines (SVMs) for the problems of protein classification and remote homology detection. These kernels use probabilistic profiles, such as those produced by the PSI-BLAST algorithm, to define position-dependent mutation neighborhoods along protein sequences for inexact matching of k-length subsequences ("k-mers") in the data. By use of an efficient data structure, the kernels are fast to compute once the profiles have been obtained. For example, the time needed to run PSI-BLAST in order to build the profiles is significantly longer than both the kernel computation time and the SVM training time. We present remote homology detection experiments based on the SCOP database where we show that profile-based string kernels used with SVM classifiers strongly outperform all recently presented supervised SVM methods. We further examine how to incorporate predicted secondary structure information into the profile kernel to obtain a small but significant performance improvement. We also show how we can use the learned SVM classifier to extract "discriminative sequence motifs" — short regions of the original profile that contribute almost all the weight of the SVM classification score — and show that these discriminative motifs correspond to meaningful structural features in the protein data. The use of PSI-BLAST profiles can be seen as a semi-supervised learning technique, since PSI-BLAST leverages unlabeled data from a large sequence database to build more informative profiles. Recently presented "cluster kernels" give general semi-supervised methods for improving SVM protein classification performance. We show that our profile kernel results also outperform cluster kernels while providing much better scalability to large datasets. Supplementary website:.

[1]  W. Kabsch,et al.  Dictionary of protein secondary structure: Pattern recognition of hydrogen‐bonded and geometrical features , 1983, Biopolymers.

[2]  A. D. McLachlan,et al.  Profile analysis: detection of distantly related proteins. , 1987, Proceedings of the National Academy of Sciences of the United States of America.

[3]  Bernhard E. Boser,et al.  A training algorithm for optimal margin classifiers , 1992, COLT '92.

[4]  B. Rost,et al.  Prediction of protein secondary structure at better than 70% accuracy. , 1993, Journal of molecular biology.

[5]  D. Haussler,et al.  Hidden Markov models in computational biology. Applications to protein modeling. , 1993, Journal of molecular biology.

[6]  M. A. McClure,et al.  Hidden Markov models of biological primary sequence information. , 1994, Proceedings of the National Academy of Sciences of the United States of America.

[7]  M Wilmanns,et al.  Structure of the binding site for inositol phosphates in a PH domain. , 1995, The EMBO journal.

[8]  Michael Gribskov,et al.  Use of Receiver Operating Characteristic (ROC) Analysis to Evaluate Sequence Matching , 1996, Comput. Chem..

[9]  Thomas L. Madden,et al.  Gapped BLAST and PSI-BLAST: a new generation of protein database search programs. , 1997, Nucleic acids research.

[10]  E. Grishin,et al.  Three-dimensional structure of toxin OSK1 from Orthochirus scrobiculosus scorpion venom. , 1997, Biochemistry.

[11]  Robert G. Martin,et al.  A novel DNA-binding motif in MarA: the first structure for an AraC family transcriptional activator. , 1998, Proceedings of the National Academy of Sciences of the United States of America.

[12]  D. Brutlag,et al.  Highly specific protein sequence motifs for genome analysis. , 1998, Proceedings of the National Academy of Sciences of the United States of America.

[13]  D. Baker,et al.  Prediction of local structure in proteins using a library of sequence-structure motifs. , 1998, Journal of molecular biology.

[14]  D T Jones,et al.  Protein secondary structure prediction based on position-specific scoring matrices. , 1999, Journal of molecular biology.

[15]  Jean Garnier,et al.  FORESST: fold recognition from secondary structure predictions of proteins , 1999, Bioinform..

[16]  David Haussler,et al.  A Discriminative Framework for Detecting Remote Protein Homologies , 2000, J. Comput. Biol..

[17]  Douglas L. Brutlag,et al.  The EMOTIF database , 2001, Nucleic Acids Res..

[18]  Gunnar Rätsch,et al.  A New Discriminative Kernel from Probabilistic Models , 2001, Neural Computation.

[19]  Mong-Li Lee,et al.  Efficient remote homology detection using local structure , 2003, Bioinform..

[20]  K. Karplus,et al.  Hidden Markov models that use predicted local structure for fold recognition: Alphabets of backbone geometry , 2003, Proteins.