Achieving High Accuracy Prediction of Minimotifs

Authors

Tian Mi, University of Connecticut - Storrs
Sanguthevar Rajasekaran, University of Connecticut - StorrsFollow
Jerlin Camilus Merlin, University of Connecticut - Storrs
Michael R. Gryk, University of Connecticut Health Center
Martin Schiller, University of Nevada, Las VegasFollow

Document Type

Article

Publication Date

9-2012

Publication Title

PLoS One

Volume

7

Issue

9

First page number:

1

Last page number:

7

Abstract

The low complexity of minimotif patterns results in a high false-positive prediction rate, hampering protein function prediction. A multi-filter algorithm, trained and tested on a linear regression model, support vector machine model, and neural network model, using a large dataset of verified minimotifs, vastly improves minimotif prediction accuracy while generating few false positives. An optimal threshold for the best accuracy reaches an overall accuracy above 90%, while a stringent threshold for the best specificity generates less than 1% false positives or even no false positives and still produces more than 90% true positives for the linear regression and neural network models. The minimotif multi-filter with its excellent accuracy represents the state-of-the-art in minimotif prediction and is expected to be very useful to biologists investigating protein function and how missense mutations cause disease.

Keywords

Amino acid sequence; Biology; Genetics; Minimotifs; Peptides; Proteins

Disciplines

Biology | Computer Sciences | Life Sciences | Molecular Biology | Structural Biology

Language

English

Creative Commons License

This work is licensed under a Creative Commons Attribution 3.0 License.

Repository Citation

Mi, T., Rajasekaran, S., Merlin, J. C., Gryk, M. R., Schiller, M. (2012). Achieving High Accuracy Prediction of Minimotifs. PLoS One, 7(9), 1-7.
http://dx.doi.org/10.1371/journal.pone.0045589