Redundancy-weighting for better inference of protein structural features.

Bioinformatics

Machine Learning for Healthcare and Life-Sciences, Analytics Department, IBM Research Laboratory, Haifa, 3490002, Department of Software Engineering, Shamoon College of Engineering, Beer-Sheva 84100, Israel, Department of Structural Biology, Stanford University School of Medicine, Stanford, CA 94305, USA, Department of Computer Science, University of Haifa, Mount Carmel, Haifa, 3498838 and Departments of Life Sciences and Computer Science, Ben-Gurion University of the Negev, Beer-Sheva, 84105, Israel.

Published: August 2014

Motivation: Structural knowledge, extracted from the Protein Data Bank (PDB), underlies numerous potential functions and prediction methods. The PDB, however, is highly biased: many proteins have more than one entry, while entire protein families are represented by a single structure, or even not at all. The standard solution to this problem is to limit the studies to non-redundant subsets of the PDB. While alleviating biases, this solution hides the many-to-many relations between sequences and structures. That is, non-redundant datasets conceal the diversity of sequences that share the same fold and the existence of multiple conformations for the same protein. A particularly disturbing aspect of non-redundant subsets is that they hardly benefit from the rapid pace of protein structure determination, as most newly solved structures fall within existing families.

Results: In this study we explore the concept of redundancy-weighted datasets, originally suggested by Miyazawa and Jernigan. Redundancy-weighted datasets include all available structures and associate them (or features thereof) with weights that are inversely proportional to the number of their homologs. Here, we provide the first systematic comparison of redundancy-weighted datasets with non-redundant ones. We test three weighting schemes and show that the distributions of structural features that they produce are smoother (having higher entropy) compared with the distributions inferred from non-redundant datasets. We further show that these smoothed distributions are both more robust and more correct than their non-redundant counterparts. We suggest that the better distributions, inferred using redundancy-weighting, may improve the accuracy of knowledge-based potentials and increase the power of protein structure prediction methods. Consequently, they may enhance model-driven molecular biology.

Download full-text PDF

Source
http://www.ncbi.nlm.nih.gov/pmc/articles/PMC4192046PMC
http://dx.doi.org/10.1093/bioinformatics/btu242DOI Listing

Publication Analysis

Top Keywords

redundancy-weighted datasets
12
structural features
8
prediction methods
8
non-redundant subsets
8
non-redundant datasets
8
protein structure
8
distributions inferred
8
protein
6
non-redundant
6
datasets
5

Similar Publications

Redundancy-weighting for better inference of protein structural features.

Bioinformatics

August 2014

Machine Learning for Healthcare and Life-Sciences, Analytics Department, IBM Research Laboratory, Haifa, 3490002, Department of Software Engineering, Shamoon College of Engineering, Beer-Sheva 84100, Israel, Department of Structural Biology, Stanford University School of Medicine, Stanford, CA 94305, USA, Department of Computer Science, University of Haifa, Mount Carmel, Haifa, 3498838 and Departments of Life Sciences and Computer Science, Ben-Gurion University of the Negev, Beer-Sheva, 84105, Israel.

Motivation: Structural knowledge, extracted from the Protein Data Bank (PDB), underlies numerous potential functions and prediction methods. The PDB, however, is highly biased: many proteins have more than one entry, while entire protein families are represented by a single structure, or even not at all. The standard solution to this problem is to limit the studies to non-redundant subsets of the PDB.

View Article and Find Full Text PDF

Want AI Summaries of new PubMed Abstracts delivered to your In-box?

Enter search terms and have AI summaries delivered each week - change queries or unsubscribe any time!