Article: A mixture-of-experts approach for gene regulatory network inference Journal: International Journal of Data Mining and Bioinformatics (IJDMB) 2016 Vol.14 No.3 pp.258 - 275 Abstract: Gene regulatory network (GRN) inference is an important problem in bioinformatics. Many machine learning methods have been applied to increase the inference accuracy. Ensemble learning methods are shown in DREAM3 and DREAM5 challenges to yield a higher inference accuracy than individual algorithms. However, no ensemble method has been proposed to take advantage of the complementarity among existing algorithms from the perspective of network motifs. We propose an ensemble method based on the principle of Mixture-of-Experts ensemble learning. The method can quantitatively evaluate the accuracy of individual algorithms on predicting each type of the network motifs and assign weights to the algorithms accordingly. The individual predictions are then used to generate the ensemble prediction. By performing controlled experiments and statistical tests, the proposed ensemble method is shown to yield a significantly higher accuracy than the generic average ranking method used in the DREAM5 challenge. In addition, a new type of network motif is found in GRN, the inclusion of which can increase the accuracy of the proposed method significantly. Inderscience Publishers - linking academia, business and industry through research

Title: A mixture-of-experts approach for gene regulatory network inference

Authors: Borong Shao; Niklas Lavesson; Veselka Boeva; Raja Khurram Shahzad

Addresses: Department of Mathematics and Computer Science, Freie Universität Berlin, Berlin, Germany ' Department of Computer Science & Engineering, Blekinge Institute of Technology, Karlskrona, Sweden ' Computer Systems and Technologies Department, Technical University of Sofia - Branch Plovdiv, Plovdiv, Bulgaria ' Department of Computer Science & Engineering, Blekinge Institute of Technology, Karlskrona, Sweden

Abstract: Gene regulatory network (GRN) inference is an important problem in bioinformatics. Many machine learning methods have been applied to increase the inference accuracy. Ensemble learning methods are shown in DREAM3 and DREAM5 challenges to yield a higher inference accuracy than individual algorithms. However, no ensemble method has been proposed to take advantage of the complementarity among existing algorithms from the perspective of network motifs. We propose an ensemble method based on the principle of Mixture-of-Experts ensemble learning. The method can quantitatively evaluate the accuracy of individual algorithms on predicting each type of the network motifs and assign weights to the algorithms accordingly. The individual predictions are then used to generate the ensemble prediction. By performing controlled experiments and statistical tests, the proposed ensemble method is shown to yield a significantly higher accuracy than the generic average ranking method used in the DREAM5 challenge. In addition, a new type of network motif is found in GRN, the inclusion of which can increase the accuracy of the proposed method significantly.

Keywords: GRN inference; ensemble learning; mixture-of-experts; network motif analysis; gene regulatory networks; bioinformatics.

DOI: 10.1504/IJDMB.2016.074876

International Journal of Data Mining and Bioinformatics, 2016 Vol.14 No.3, pp.258 - 275

Received: 11 Sep 2014
Accepted: 06 Aug 2015
Published online: 22 Feb 2016 *

Full-text access for editors Full-text access for subscribers Purchase this article Comment on this article

Title: A mixture-of-experts approach for gene regulatory network inference

Keep up-to-date