Improving prediction of zinc binding sites by modeling the linkage between residues close in sequence

Authors:
Sauro Menchetti;Andrea Passerini;Paolo Frasconi;Claudia Andreini;Antonio Rosato
Affiliations:
Machine Learning and Neural Networks Group, Dipartimento di Sistemi e Informatica, Università degli Studi di Firenze, Italy;Machine Learning and Neural Networks Group, Dipartimento di Sistemi e Informatica, Università degli Studi di Firenze, Italy;Machine Learning and Neural Networks Group, Dipartimento di Sistemi e Informatica, Università degli Studi di Firenze, Italy;Magnetic Resonance Center (CERM), Dipartimento di Chimica, Università degli Studi di Firenze, Italy;Magnetic Resonance Center (CERM), Dipartimento di Chimica, Università degli Studi di Firenze, Italy
Venue:
RECOMB'06 Proceedings of the 10th annual international conference on Research in Computational Molecular Biology
Year:
2006

Citing 7
Cited 0

Support-Vector Networks

Machine Learning
Linkage and Autocorrelation Cause Feature Selection Bias in Relational Learning

ICML '02 Proceedings of the Nineteenth International Conference on Machine Learning
Kernel Methods for Pattern Analysis

Kernel Methods for Pattern Analysis
Why collective inference improves relational classification

Proceedings of the tenth ACM SIGKDD international conference on Knowledge discovery and data mining
Disulfide connectivity prediction using recursive neural networks and evolutionary information

Bioinformatics
A hint to search for metalloproteins in gene banks

Bioinformatics
Discriminative probabilistic models for relational data

UAI'02 Proceedings of the Eighteenth conference on Uncertainty in artificial intelligence

Quantified Score

Hi-index	0.00

Visualization

Abstract

We describe and empirically evaluate machine learning methods for the prediction of zinc binding sites from protein sequences. We start by observing that a data set consisting of single residues as examples is affected by autocorrelation and we propose an ad-hoc remedy in which sequentially close pairs of candidate residues are classified as being jointly involved in the coordination of a zinc ion. We develop a kernel for this particular type of data that can handle variable length gaps between candidate coordinating residues. Our empirical evaluation on a data set of non redundant protein chains shows that explicit modeling the correlation between residues close in sequence allows us to gain a significant improvement in the prediction performance.