Online

A filter-based feature selection method for temporal gene expression data based on maximum relevance and minimum redundancy criteria. TMRMR incorporates temporal information by combining relevance, which is calculated as an average F-statistic value across different time steps, with redundancy, which is calculated by employing dynamical time warping approach. The incorporation of the temporal information into the feature selection process leads to selection of more discriminative features.

User report

0 user reviews

0 user reviews

No review has been posted.

TMRMR forum

No open topic.

TMRMR versioning

No versioning.

TMRMR classification

TMRMR specifications

Software type:
Package
Restrictions to use:
None
Output data:
The ranked list of the top genes.
Computer skills:
Advanced
Interface:
Command line interface
Input data:
A set of temporally aligned gene expression data.
Programming languages:
MATLAB
Stability:
Stable
Source code URL:
https://github.com/radovicmiloskg/TMRMR.git

Credits

Publications

  • (Radovic et al., 2017) Minimum redundancy maximum relevance feature selection approach for temporal gene expression data. BMC Bioinformatics.
    PMID: 28049413

Institution(s)

Center for Data Analytics and Biomedical Informatics, College of Science and Technology, Temple University, Philadelphia, PA, USA; Bioengineering Research and Development Center - BioIRC, Kragujevac, Serbia; Mathematics Department, Faculty of Science, Ain Shams University, Cairo, Egypt; Center for Computational Health, IBM T.J. Watson Research Center, Cambridge, MA, USA; Faculty of Engineering, University of Kragujevac, Kragujevac, Serbia

Funding source(s)

This work was partially supported by the Defense Advanced Research Projects Agency (DARPA) and the Army Research Office (ARO) under Contract No. W911NF-16-C-0050, by DARPA grant No. 66001-11-1-4183 negotiated by SSC Pacific grant, and Serbian Ministry of Education, Science and Technological Development grants III41007 and ON174028.

By using OMICtools you acknowledge that you have read and accepted the terms of the end user license agreement.