Analysis of the inducing factors involved in stem cell differentiation using feature selection techniques, support vector machines and decision trees

  • Authors:

  • A. M. Trujillo;Ignacio Rojas;Héctor Pomares;A. Prieto;B. Prieto;A. Aránega;Francisco Rodríguez;P. J. Álvarez-Aranega;J. C. Prados

  • Affiliations:

  • FIBAO Bio-Health Research Foundation of Eastern Andalucía, University of Granada, Granada, Spain;Computer Architecture and Computer Technology Department, University of Granada, Granada, Spain;Computer Architecture and Computer Technology Department, University of Granada, Granada, Spain;Computer Architecture and Computer Technology Department, University of Granada, Granada, Spain;Computer Architecture and Computer Technology Department, University of Granada, Granada, Spain;Anatomy and Human Embryology Department, University of Granada, Granada, Spain;Anatomy and Human Embryology Department, University of Granada, Granada, Spain;Anatomy and Human Embryology Department, University of Granada, Granada, Spain;Anatomy and Human Embryology Department, University of Granada, Granada, Spain

  • Venue:
  • IEA/AIE'10 Proceedings of the 23rd international conference on Industrial engineering and other applications of applied intelligent systems - Volume Part I
  • Year:
  • 2010

Quantified Score

Hi-index 0.00

Visualization

Abstract

Stem cells represent a potential source of cells for regeneration, thanks to their ability to renew and differentiate into functional cells of different tissues. The studies and results related to stem cell differentiation are diverse and sometimes contradictory due to the various sources of production and the different variables involved in the differentiation problem. In this paper a new methodology is proposed in order to select the relevant factors involved in stem cell differentiation into cardiac lineage and forecast its behaviour and response in the differentiation process. We have built a database from the results of experiments on stem cell differentiation into cardiac tissue and using this database we have applied state-of-the-art classification and predictive techniques such as support vector machine and decision trees, as well as several feature selection techniques. The results obtained are very promising and demonstrate that with only a reduced subset of variables high prediction rates are possible.