Table of Contents Author Guidelines Submit a Manuscript
Advances in Bioinformatics
Volume 2016, Article ID 5670851, 6 pages
http://dx.doi.org/10.1155/2016/5670851
Research Article

Feature Selection Has a Large Impact on One-Class Classification Accuracy for MicroRNAs in Plants

1Computer Science, The College of Sakhnin, 30810 Sakhnin, Israel
2The Institute of Applied Research, The Galilee Society, P.O. Box 437, 20200 Shefa Amr, Israel
3Molecular Biology and Genetics, Izmir Institute of Technology, Urla, 35430 Izmir, Turkey
4Bionia Incorporated, IZTEKGEB A8, Urla, 35430 Izmir, Turkey

Received 31 October 2015; Accepted 16 March 2016

Academic Editor: Paul Harrison

Copyright © 2016 Malik Yousef et al. This is an open access article distributed under the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.

Supplementary Material

Different feature selection methods were employed and the outcome was submitted to machine learning.

Supplementary File 1 contains the computational workflows detailing how feature selection was performed for the different methods. Figures 1 and 2 show training and testing schemes and figures 3 to 10 show the calculation workflow for the feature selection methods in this study.

Supplementary Table 1 contains the selected features and their information gain on a per feature selection algorithm basis (separated into work sheets) and on a per species basis (combined in one work sheet).

Supplementary Table 2 contains the classifier performance (RawData Sheet), Accuracy Plot for the individual selection methods (AccuracyFigure Sheet) and for the combined feature selection (Accuracy Sheet). Additional information like deviation among methods (Deviation Sheet), performance ranking (Sequence Sheet), and the construction of classifier performance (Comparison Sheet) are also provided.

  1. Supplementary Materials