Medical Systems Biology

You are here:  Research > Bioinformatics > Feature Selection

Feature Selection

Current biomolecular technologies yield extremely high-dimensional data, often involving thousands or even millions of features (e.g. gene expression measurements or SNPs). By contrast, a common hypothesis is that many biological processes only depend on a very small number of markers. Feature selection techniques are required to identify those biomarkers that are associated with certain phenotypes.

Feature Selection

Our research focuses on the application of feature selection techniques in clinical settings as well as the development and evaluation of feature selection methods. In particular, we apply feature selection in combination with classifiers. This includes extensions of the Set Covering Machine, visualization and evaluation of feature subset stability in resampling settings.

 

Selected publications

 

L. Lausser, C. Müssel, M. Maucher, and H. A. Kestler. Measuring and visualizing the stability of biomarker selection techniques. Computational Statistics, 28(1):51–65, 2013.

H. A. Kestler, L. Lausser, W. Lindner, and G. Palm. On the fusion of threshold classifiers for categorization and dimensionality reduction. Computational Statistics, 26(2):321–340, 2011.

H. A. Kestler, W. Lindner, and A. Müller. Learning and feature selection using the set covering machine with data-dependent rays on gene expression profiles. In F. Schwenker and S. Marinai, editors, Artificial Neural Networks in Pattern Recognition (ANNPR 06), volume LNAI 4087, pages 286–297. Springer-Verlag, Heidelberg, 2006.

 

 

Latest News

 

Congratulations to Dr. Silke Werle for winning the 1st Prize with her pitch at the 1. Science Day held by ProTrainU. 

 

Our paper "Reconstructing Boolean network ensembles from single-cell data for unraveling dynamics in the aging of human hematopoietic stem cells" has been published in the Computational and Structural Biotechnology Journal.

 

The position paper "Is there a role for statistics in artificial intelligence" has been published online first in Advances in Data Analysis and Classification.

 

Our paper "Corona Health - A Study- and Sensor-Based Mobile App Platform Exploring Aspects of the COVID-19 Pandemic" has been published in the International Journal of Environmental Research and Public Health.

 

Our paper "Patient empowerment during the COVID-19 pandemic: Ensuring safe and fast communication of test results" has been published in the Journal of Medical Internet Research.

 

Our paper "Perspective on mHealth Concepts to Ensure Users’ Empowerment–From Adverse Event Tracking for COVID-19 Vaccinations to Oncological Treatment" has been published in IEEE Access.

  

Our report protocol "Digitalization of adverse event management in oncology to improve treatment outcome—A prospective study protocol" has been published in PLoS One.

 

We are happy we could contribute to Beutel et al (2021) "A prospective Feasibility Trial to Challenge Patient-Derived Pancreatic Cancer Organoids in Predicting Treatment Response" published in MDPI Cancers.