Issue No. 05 - Sept.-Oct. (2012 vol. 9)
DOI Bookmark: http://doi.ieeecomputersociety.org/10.1109/TCBB.2012.54
John C. Hawkins , Struct. Bioinf., Tech. Univ. Dresden, Dresden, Germany
Hongbo Zhu , Struct. Bioinf., Tech. Univ. Dresden, Dresden, Germany
Joan Teyra , Struct. Bioinf., Tech. Univ. Dresden, Dresden, Germany
M. Teresa Pisabarro , Struct. Bioinf., Tech. Univ. Dresden, Dresden, Germany
Identifying the binding partners of proteins is a problem of fundamental importance in computational biology. The PDZ is one of the most common and well-studied protein binding domains, hence it is a perfect model system for designing protein binding predictors. The standard approach to identifying the binding partners of PDZ domains uses multiple sequence alignments to infer the set of contact residues that are used in a predictive model. We expand on the sequence alignment approach by incorporating structural information to generate descriptors of the binding site geometry. Furthermore, we generate a real-value score for binary predictions by applying a filter based on models that predict the probability distributions of contact residues at each of the canonical PDZ ligand binding positions. Under training cross validation, our model produced an order of magnitude more predictions at a false positive proportion (FPP) of 10 percent than our benchmark model chosen from the literature. Evaluated using an independent cross validation, with computationally predicted structures, our model was able to make five times as many predictions as the benchmark model, with a Matthews' correlation coefficient (MCC) of 0.33. In addition, our model achieved a false positive proportion of 0.14, while the benchmark model had a 0.25 false positive proportion.
proteins, biological techniques, molecular biophysics, probability, Matthew correlation coefficient, reduced false positive proportion, PDZ binding prediction, structural descriptors, sequence descriptors, computational biology, protein binding domains, multiple sequence alignments, structural information, binding site geometry, probability distributions, benchmark model, Peptides, Proteins, Encoding, Predictive models, Probability distribution, Computational modeling, Data models, protein structure classification., PDZ binding, protein binding prediction, machine learning
M. T. Pisabarro, Hongbo Zhu, J. Teyra and J. C. Hawkins, "Reduced False Positives in PDZ Binding Prediction Using Sequence and Structural Descriptors," in IEEE/ACM Transactions on Computational Biology and Bioinformatics, vol. 9, no. , pp. 1492-1503, 2012.